[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-aiq-research":3,"mdc-jpordi-key":30,"related-repo-openai-aiq-research":2284,"related-org-openai-aiq-research":2405},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":19,"repoUrl":20,"updatedAt":21,"license":22,"forks":23,"topics":24,"repo":25,"sourceUrl":28,"mdContent":29},"aiq-research","conduct deep AI-Q research","Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"openai","OpenAI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fopenai.png",[12,16],{"name":13,"slug":14,"type":15},"Research","research","tag",{"name":17,"slug":18,"type":15},"AI Infrastructure","ai-infrastructure",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-06-30T19:00:57.102","Apache-2.0",465,[],{"repoUrl":20,"stars":19,"forks":23,"topics":26,"description":27},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fnvidia\u002Fskills\u002Faiq-research","---\nname: aiq-research\ndescription: |\n  Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.\nlicense: Apache-2.0\npermissions:\n  env:\n    - AIQ_SERVER_URL\n  network:\n    - http:\u002F\u002Flocalhost:8000\ncompatibility: |\n  Designed for Claude Code, OpenCode, Codex, and Agent Skills-compatible tools. Requires Python 3.11+ and network\n  access to a running local AI-Q Blueprint server at `http:\u002F\u002Flocalhost:8000` by default. Non-local backends must be\n  explicitly trusted by the user and granted by the host tool outside this public skill.\nmetadata:\n  version: \"2.1.0\"\n  author: \"NVIDIA AI-Q Blueprint Team \u003Caiq-blueprint@nvidia.com>\"\n  github-url: \"https:\u002F\u002Fgithub.com\u002FNVIDIA-AI-Blueprints\u002Faiq\"\n  tags:\n    - nvidia\n    - aiq\n    - blueprint\n    - deep-research\n    - research-agents\n    - agent-skills\n  languages:\n    - python\n    - bash\n  domain: \"research-agents\"\nallowed-tools: Read Bash\n---\n\n# AIQ Research Skill\n\n## Purpose\n\nUse this skill to call a locally running NVIDIA AI-Q Blueprint server through the helper script at\n`scripts\u002Faiq.py`.\n\nUse this skill for research-shaped requests, including:\n\n- \"deep research on ...\"\n- \"AIQ research ...\"\n- \"research ...\"\n- \"use AI-Q to answer ...\"\n- \"ask AI-Q about ...\"\n\nDo not use this skill for install, deploy, start, stop, UI, CLI, Docker, Helm, or troubleshooting requests. Those\nbelong to `aiq-deploy`.\n\n## Prerequisites\n\nUsers need:\n\n- Python 3.11+ available as `python3`.\n- A reachable local or self-hosted AI-Q Blueprint backend.\n- `AIQ_SERVER_URL` set when the backend is not running at `http:\u002F\u002Flocalhost:8000`; non-local values must be trusted by\n  the user before any query is sent.\n- A backend configured with authentication disabled for this public helper, or a separate authenticated AI-Q skill for\n  authenticated environments.\n- Network access from the local machine to the AI-Q backend URL.\n- Credentials configured in the backend environment, not in this skill. This public helper does not collect or manage\n  API keys.\n\nThe helper script has no third-party Python package dependencies; it uses Python standard-library HTTP modules.\n\n## Instructions\n\n1. Resolve the target backend URL.\n2. Run `health` before sending research requests.\n3. If no backend is reachable, ask for a backend URL or hand off to `aiq-deploy`.\n4. Before sending any user query, state the exact AI-Q backend URL that will receive it. For non-local URLs, continue\n   only if the user has explicitly confirmed that URL is trusted in the current conversation.\n5. Poll asynchronous deep research jobs when AI-Q returns a job ID.\n6. Present returned reports with citations and source URLs intact.\n7. Stop on failed jobs and show the returned error; do not retry automatically.\n\n### Step 1 - Resolve the backend\n\nUse `AIQ_SERVER_URL` when set. Otherwise try the default local backend:\n\n```bash\npython3 $SKILL_DIR\u002Fscripts\u002Faiq.py health\n```\n\nExpected output: JSON from a reachable AI-Q health endpoint.\n\nIf `health` fails and no explicit `AIQ_SERVER_URL` was set, ask:\n\n```text\nI do not see a reachable local AI-Q backend. Do you already have an AI-Q backend URL you want to use, or should I deploy a local Skill backend?\n```\n\n- If the user provides a URL, set `AIQ_SERVER_URL` for subsequent helper calls and rerun `health`.\n- If the user wants local deployment, hand off to `aiq-deploy` and preserve the original research request.\n- If a reachable backend returns `401` or `403`, stop and explain that this public skill does not manage\n  authentication. Ask the user to use an authenticated AI-Q skill or configure authentication for their environment.\n- If `health` succeeds but `\u002Fchat` or `\u002Fv1\u002Fjobs\u002Fasync\u002Fagents` fails, report that the backend is reachable but not\n  compatible with this public research flow, then offer to run `aiq-deploy` validation.\n\n### Step 2 - Send the routed research request\n\nBefore sending the request, state the resolved endpoint:\n\n```text\nI will send this query to \u003CAIQ_SERVER_URL>. Make sure this endpoint is trusted before sending sensitive information.\n```\n\nDo not send credentials, cookies, bearer tokens, or secret values through the query text.\n\nRun:\n\n```bash\npython3 $SKILL_DIR\u002Fscripts\u002Faiq.py chat \"\u003CUSER_QUESTION>\"\n```\n\nExpected output:\n\n- A normal JSON response for shallow or direct answers.\n- Or structured JSON containing `{\"status\": \"deep_research_running\", \"job_id\": \"\u003CJOB_ID>\"}` for asynchronous deep\n  research.\n\nIf the response is normal JSON, present the result immediately. Do not force polling when there is no `job_id`.\n\n### Step 3 - Poll asynchronous jobs\n\nIf the response includes `deep_research_running`, extract the `job_id` and poll with the same absolute script path:\n\n```bash\npython3 $SKILL_DIR\u002Fscripts\u002Faiq.py research_poll \u003CJOB_ID>\n```\n\nExpected output: the final report JSON when the job completes successfully.\n\nUse the runtime's non-blocking or background execution mechanism when available. If the chosen execution method requires\nescalated permissions, request explicit user approval first and explain why. Tell the user that deep research is running\nin the background.\n\n### Step 4 - Resume after interruptions\n\nIf polling is interrupted, the job continues server-side. Resume with:\n\n```bash\npython3 $SKILL_DIR\u002Fscripts\u002Faiq.py status \u003CJOB_ID>\npython3 $SKILL_DIR\u002Fscripts\u002Faiq.py report \u003CJOB_ID>\npython3 $SKILL_DIR\u002Fscripts\u002Faiq.py research_poll \u003CJOB_ID>\n```\n\nUse `status` to inspect job status and saved artifacts. Use `report` when the job has already finished and you only need\nthe final output. Use `research_poll` to keep waiting for completion.\n\n### Step 5 - Present the report\n\nWhen `research_poll` completes successfully, fetch and present the full report. Keep citations and source URLs intact.\nIf the job status is `failed`, `failure`, or `cancelled`, show the error from the status response and ask whether the\nuser wants to retry with a narrower query or different approach.\n\n## Version Compatibility\n\n**IMPORTANT:** This skill is designed for NVIDIA AI-Q Blueprint version 2.1.0.\n\nSemantic Versioning Compatibility Rules:\n\n```text\nSkill version: X.Y.Z\nBlueprint or endpoint version: A.B.C\n\nCompatible IF:\n1. A == X (Major versions MUST match)\n2. B >= Y (Minor version must be equal or greater)\n3. C can be anything (Patch version does not affect compatibility)\n```\n\nExamples:\n\n- Skill version 2.1.0 is compatible with Blueprint version 2.1.0.\n- Skill version 2.1.0 is compatible with Blueprint version 2.2.0.\n- Skill version 2.1.0 is compatible with Blueprint version 2.1.5.\n- Skill version 2.1.0 is not compatible with Blueprint version 3.0.0.\n- Skill version 2.1.0 is not compatible with Blueprint version 2.0.0.\n\nIf your Blueprint version is not compatible:\n\n1. Check for an updated skill version matching your Blueprint version.\n2. Use a Blueprint version compatible with this skill.\n3. Proceed with caution only when the user accepts the compatibility risk; API routes or response shapes may have\n   changed.\n\n## Available Scripts\n\n| Script | Purpose | Arguments |\n|---|---|---|\n| `scripts\u002Faiq.py health` | Check whether the configured server responds | none |\n| `scripts\u002Faiq.py chat` | POST `\u002Fchat`; may return inline output or a deep-research job ID | `\u003Cquery>` |\n| `scripts\u002Faiq.py agents` | List available async agent types | none |\n| `scripts\u002Faiq.py submit` | Submit an explicit async job | `\u003Cquery> [agent_type]` |\n| `scripts\u002Faiq.py research` | Submit an async job, poll, and print the final report JSON | `\u003Cquery> [agent_type]` |\n| `scripts\u002Faiq.py research_poll` | Resume polling an existing async job | `\u003Cjob_id>` |\n| `scripts\u002Faiq.py status` | Fetch job status plus `\u002Fstate` artifacts | `\u003Cjob_id>` |\n| `scripts\u002Faiq.py state` | Fetch event-store artifacts only | `\u003Cjob_id>` |\n| `scripts\u002Faiq.py report` | Fetch the final report for a completed job | `\u003Cjob_id>` |\n| `scripts\u002Faiq.py stream` | Stream SSE events from a job | `\u003Cjob_id>` |\n| `scripts\u002Faiq.py cancel` | Cancel a running job | `\u003Cjob_id>` |\n\nWhen the host supports a `run_script()` helper, call it with `scripts\u002Faiq.py` and the arguments above. Otherwise, run\nthe equivalent shell command, such as `python3 $SKILL_DIR\u002Fscripts\u002Faiq.py health`.\n\n## Environment Variables\n\n| Variable | Required | Default | Description |\n|---|---:|---|---|\n| `AIQ_SERVER_URL` | No | `http:\u002F\u002Flocalhost:8000` | Local or self-hosted AI-Q server base URL |\n\n## Security Best Practices\n\n- Do not put API keys, bearer tokens, cookies, or basic-auth credentials in `AIQ_SERVER_URL`.\n- Store backend credentials in the AI-Q deployment environment, not in this skill or command examples.\n- User query text is transmitted to the configured `AIQ_SERVER_URL`. Confirm the endpoint is trusted before sending\n  sensitive or confidential information.\n- Treat returned reports as potentially sensitive if the backend uses private data sources.\n- Do not truncate citations or source URLs from returned reports.\n\n## Limitations\n\n- This skill requires a running AI-Q backend; it does not deploy one.\n- The public helper does not manage authentication tokens or cookies.\n- Remote `AIQ_SERVER_URL` endpoints may log prompts, responses, and metadata.\n- If the backend returns HTTP 500 or lacks async agents, report the failure instead of fabricating a research answer.\n\n## Examples\n\n### Example 1: Run a routed chat or research request\n\n```bash\npython3 $SKILL_DIR\u002Fscripts\u002Faiq.py health\npython3 $SKILL_DIR\u002Fscripts\u002Faiq.py chat \"Compare local AIQ deep research with a standard web search workflow\"\n```\n\nExpected output:\n\n```text\n\u003Chealth JSON from AI-Q>\n\u003CJSON chat response or {\"status\": \"deep_research_running\", \"job_id\": \"\u003CJOB_ID>\"}>\n```\n\nIf AI-Q returns a job ID, continue with `research_poll`.\n\n### Example 2: Resume an existing job\n\n```bash\npython3 $SKILL_DIR\u002Fscripts\u002Faiq.py status \u003CJOB_ID>\npython3 $SKILL_DIR\u002Fscripts\u002Faiq.py research_poll \u003CJOB_ID>\n```\n\nReplace `\u003CJOB_ID>` with the UUID returned by AI-Q. Expected output: status JSON followed by the report JSON when the\njob completes. If the job failed, show the returned status and do not retry automatically.\n\n## References\n\n| Topic | Documentation |\n|---|---|\n| Helper script | `scripts\u002Faiq.py` |\n| Deployment and backend validation | `..\u002Faiq-deploy\u002FSKILL.md` |\n\n## Common Issues\n\n### Issue: No backend is reachable\n\n**Symptoms:**\n\n- `health` fails with connection refused.\n- The default `http:\u002F\u002Flocalhost:8000` URL does not respond.\n\n**Causes:**\n\n- AI-Q is not running.\n- AI-Q is running on a different host or port.\n- A local firewall or network setting blocks the connection.\n\n**Solutions:**\n\n1. Ask whether the user has an existing AI-Q backend URL.\n2. If they provide one, set it and rerun health:\n   ```bash\n   export AIQ_SERVER_URL=\"http:\u002F\u002Flocalhost:\u003CPORT>\"\n   python3 $SKILL_DIR\u002Fscripts\u002Faiq.py health\n   ```\n3. If they want a local backend, hand off to `aiq-deploy` and preserve the original research request.\n\n### Issue: Backend requires authentication\n\n**Symptoms:**\n\n- Requests fail with HTTP 401 or HTTP 403.\n- The backend is reachable but rejects `\u002Fchat` or async job calls.\n\n**Causes:**\n\n- The backend was deployed with authentication enabled.\n- The public helper does not attach user tokens or cookies.\n\n**Solutions:**\n\n1. Stop and explain that this public skill does not manage authentication.\n2. Ask the user to use an authenticated AI-Q skill or configure their backend for this public local workflow.\n3. Rerun `health` and the original query only after the authentication boundary is resolved.\n\n### Issue: Health succeeds but research routes fail\n\n**Symptoms:**\n\n- `health` returns successfully.\n- `\u002Fchat`, `\u002Fv1\u002Fjobs\u002Fasync\u002Fagents`, or polling commands fail.\n\n**Causes:**\n\n- The backend is not using an API-enabled AI-Q config.\n- The async job registry is not available in the selected backend.\n- The backend version is incompatible with this skill.\n\n**Solutions:**\n\n1. Run:\n   ```bash\n   python3 $SKILL_DIR\u002Fscripts\u002Faiq.py agents\n   ```\n2. If agents are unavailable, report the compatibility failure and offer to run `aiq-deploy` validation.\n3. Confirm the deployed Blueprint version is compatible with skill version 2.1.0.\n\n### Issue: Job is interrupted or appears stuck\n\n**Symptoms:**\n\n- Local polling is interrupted.\n- The job keeps showing `running`.\n- Poll output shows `running`, but a report is returned or cancel says the job is already `success`.\n\n**Causes:**\n\n- Deep research is asynchronous and continues server-side.\n- Local polling output can lag behind terminal server state.\n\n**Solutions:**\n\n1. Check current state:\n   ```bash\n   python3 $SKILL_DIR\u002Fscripts\u002Faiq.py status \u003CJOB_ID>\n   ```\n2. If `has_report: true` or `job_status.status: success`, fetch the report:\n   ```bash\n   python3 $SKILL_DIR\u002Fscripts\u002Faiq.py report \u003CJOB_ID>\n   ```\n3. If the job is still running, continue polling:\n   ```bash\n   python3 $SKILL_DIR\u002Fscripts\u002Faiq.py research_poll \u003CJOB_ID>\n   ```\n",{"data":31,"body":53},{"name":4,"description":6,"license":22,"permissions":32,"compatibility":37,"metadata":38,"allowed-tools":52},{"env":33,"network":35},[34],"AIQ_SERVER_URL",[36],"http:\u002F\u002Flocalhost:8000","Designed for Claude Code, OpenCode, Codex, and Agent Skills-compatible tools. Requires Python 3.11+ and network\naccess to a running local AI-Q Blueprint server at `http:\u002F\u002Flocalhost:8000` by default. Non-local backends must be\nexplicitly trusted by the user and granted by the host tool outside this public skill.\n",{"version":39,"author":40,"github-url":41,"tags":42,"languages":49,"domain":47},"2.1.0","NVIDIA AI-Q Blueprint Team \u003Caiq-blueprint@nvidia.com>","https:\u002F\u002Fgithub.com\u002FNVIDIA-AI-Blueprints\u002Faiq",[43,44,45,46,47,48],"nvidia","aiq","blueprint","deep-research","research-agents","agent-skills",[50,51],"python","bash","Read Bash",{"type":54,"children":55},"root",[56,65,72,87,92,122,134,140,145,197,202,208,261,268,280,318,323,342,352,439,445,450,459,464,469,512,517,538,550,556,576,623,628,633,639,644,760,788,794,830,836,847,852,861,866,894,899,917,923,1241,1268,1274,1336,1342,1383,1389,1419,1425,1431,1489,1493,1502,1513,1519,1596,1609,1615,1670,1676,1682,1690,1715,1723,1741,1749,1832,1838,1845,1865,1872,1885,1892,1917,1923,1930,1959,1966,1984,1991,2042,2048,2055,2094,2101,2114,2121,2278],{"type":57,"tag":58,"props":59,"children":61},"element","h1",{"id":60},"aiq-research-skill",[62],{"type":63,"value":64},"text","AIQ Research Skill",{"type":57,"tag":66,"props":67,"children":69},"h2",{"id":68},"purpose",[70],{"type":63,"value":71},"Purpose",{"type":57,"tag":73,"props":74,"children":75},"p",{},[76,78,85],{"type":63,"value":77},"Use this skill to call a locally running NVIDIA AI-Q Blueprint server through the helper script at\n",{"type":57,"tag":79,"props":80,"children":82},"code",{"className":81},[],[83],{"type":63,"value":84},"scripts\u002Faiq.py",{"type":63,"value":86},".",{"type":57,"tag":73,"props":88,"children":89},{},[90],{"type":63,"value":91},"Use this skill for research-shaped requests, including:",{"type":57,"tag":93,"props":94,"children":95},"ul",{},[96,102,107,112,117],{"type":57,"tag":97,"props":98,"children":99},"li",{},[100],{"type":63,"value":101},"\"deep research on ...\"",{"type":57,"tag":97,"props":103,"children":104},{},[105],{"type":63,"value":106},"\"AIQ research ...\"",{"type":57,"tag":97,"props":108,"children":109},{},[110],{"type":63,"value":111},"\"research ...\"",{"type":57,"tag":97,"props":113,"children":114},{},[115],{"type":63,"value":116},"\"use AI-Q to answer ...\"",{"type":57,"tag":97,"props":118,"children":119},{},[120],{"type":63,"value":121},"\"ask AI-Q about ...\"",{"type":57,"tag":73,"props":123,"children":124},{},[125,127,133],{"type":63,"value":126},"Do not use this skill for install, deploy, start, stop, UI, CLI, Docker, Helm, or troubleshooting requests. Those\nbelong to ",{"type":57,"tag":79,"props":128,"children":130},{"className":129},[],[131],{"type":63,"value":132},"aiq-deploy",{"type":63,"value":86},{"type":57,"tag":66,"props":135,"children":137},{"id":136},"prerequisites",[138],{"type":63,"value":139},"Prerequisites",{"type":57,"tag":73,"props":141,"children":142},{},[143],{"type":63,"value":144},"Users need:",{"type":57,"tag":93,"props":146,"children":147},{},[148,160,165,182,187,192],{"type":57,"tag":97,"props":149,"children":150},{},[151,153,159],{"type":63,"value":152},"Python 3.11+ available as ",{"type":57,"tag":79,"props":154,"children":156},{"className":155},[],[157],{"type":63,"value":158},"python3",{"type":63,"value":86},{"type":57,"tag":97,"props":161,"children":162},{},[163],{"type":63,"value":164},"A reachable local or self-hosted AI-Q Blueprint backend.",{"type":57,"tag":97,"props":166,"children":167},{},[168,173,175,180],{"type":57,"tag":79,"props":169,"children":171},{"className":170},[],[172],{"type":63,"value":34},{"type":63,"value":174}," set when the backend is not running at ",{"type":57,"tag":79,"props":176,"children":178},{"className":177},[],[179],{"type":63,"value":36},{"type":63,"value":181},"; non-local values must be trusted by\nthe user before any query is sent.",{"type":57,"tag":97,"props":183,"children":184},{},[185],{"type":63,"value":186},"A backend configured with authentication disabled for this public helper, or a separate authenticated AI-Q skill for\nauthenticated environments.",{"type":57,"tag":97,"props":188,"children":189},{},[190],{"type":63,"value":191},"Network access from the local machine to the AI-Q backend URL.",{"type":57,"tag":97,"props":193,"children":194},{},[195],{"type":63,"value":196},"Credentials configured in the backend environment, not in this skill. This public helper does not collect or manage\nAPI keys.",{"type":57,"tag":73,"props":198,"children":199},{},[200],{"type":63,"value":201},"The helper script has no third-party Python package dependencies; it uses Python standard-library HTTP modules.",{"type":57,"tag":66,"props":203,"children":205},{"id":204},"instructions",[206],{"type":63,"value":207},"Instructions",{"type":57,"tag":209,"props":210,"children":211},"ol",{},[212,217,230,241,246,251,256],{"type":57,"tag":97,"props":213,"children":214},{},[215],{"type":63,"value":216},"Resolve the target backend URL.",{"type":57,"tag":97,"props":218,"children":219},{},[220,222,228],{"type":63,"value":221},"Run ",{"type":57,"tag":79,"props":223,"children":225},{"className":224},[],[226],{"type":63,"value":227},"health",{"type":63,"value":229}," before sending research requests.",{"type":57,"tag":97,"props":231,"children":232},{},[233,235,240],{"type":63,"value":234},"If no backend is reachable, ask for a backend URL or hand off to ",{"type":57,"tag":79,"props":236,"children":238},{"className":237},[],[239],{"type":63,"value":132},{"type":63,"value":86},{"type":57,"tag":97,"props":242,"children":243},{},[244],{"type":63,"value":245},"Before sending any user query, state the exact AI-Q backend URL that will receive it. For non-local URLs, continue\nonly if the user has explicitly confirmed that URL is trusted in the current conversation.",{"type":57,"tag":97,"props":247,"children":248},{},[249],{"type":63,"value":250},"Poll asynchronous deep research jobs when AI-Q returns a job ID.",{"type":57,"tag":97,"props":252,"children":253},{},[254],{"type":63,"value":255},"Present returned reports with citations and source URLs intact.",{"type":57,"tag":97,"props":257,"children":258},{},[259],{"type":63,"value":260},"Stop on failed jobs and show the returned error; do not retry automatically.",{"type":57,"tag":262,"props":263,"children":265},"h3",{"id":264},"step-1-resolve-the-backend",[266],{"type":63,"value":267},"Step 1 - Resolve the backend",{"type":57,"tag":73,"props":269,"children":270},{},[271,273,278],{"type":63,"value":272},"Use ",{"type":57,"tag":79,"props":274,"children":276},{"className":275},[],[277],{"type":63,"value":34},{"type":63,"value":279}," when set. Otherwise try the default local backend:",{"type":57,"tag":281,"props":282,"children":286},"pre",{"className":283,"code":284,"language":51,"meta":285,"style":285},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","python3 $SKILL_DIR\u002Fscripts\u002Faiq.py health\n","",[287],{"type":57,"tag":79,"props":288,"children":289},{"__ignoreMap":285},[290],{"type":57,"tag":291,"props":292,"children":295},"span",{"class":293,"line":294},"line",1,[296,301,307,313],{"type":57,"tag":291,"props":297,"children":299},{"style":298},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[300],{"type":63,"value":158},{"type":57,"tag":291,"props":302,"children":304},{"style":303},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[305],{"type":63,"value":306}," $SKILL_DIR",{"type":57,"tag":291,"props":308,"children":310},{"style":309},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[311],{"type":63,"value":312},"\u002Fscripts\u002Faiq.py",{"type":57,"tag":291,"props":314,"children":315},{"style":309},[316],{"type":63,"value":317}," health\n",{"type":57,"tag":73,"props":319,"children":320},{},[321],{"type":63,"value":322},"Expected output: JSON from a reachable AI-Q health endpoint.",{"type":57,"tag":73,"props":324,"children":325},{},[326,328,333,335,340],{"type":63,"value":327},"If ",{"type":57,"tag":79,"props":329,"children":331},{"className":330},[],[332],{"type":63,"value":227},{"type":63,"value":334}," fails and no explicit ",{"type":57,"tag":79,"props":336,"children":338},{"className":337},[],[339],{"type":63,"value":34},{"type":63,"value":341}," was set, ask:",{"type":57,"tag":281,"props":343,"children":347},{"className":344,"code":346,"language":63,"meta":285},[345],"language-text","I do not see a reachable local AI-Q backend. Do you already have an AI-Q backend URL you want to use, or should I deploy a local Skill backend?\n",[348],{"type":57,"tag":79,"props":349,"children":350},{"__ignoreMap":285},[351],{"type":63,"value":346},{"type":57,"tag":93,"props":353,"children":354},{},[355,373,385,406],{"type":57,"tag":97,"props":356,"children":357},{},[358,360,365,367,372],{"type":63,"value":359},"If the user provides a URL, set ",{"type":57,"tag":79,"props":361,"children":363},{"className":362},[],[364],{"type":63,"value":34},{"type":63,"value":366}," for subsequent helper calls and rerun ",{"type":57,"tag":79,"props":368,"children":370},{"className":369},[],[371],{"type":63,"value":227},{"type":63,"value":86},{"type":57,"tag":97,"props":374,"children":375},{},[376,378,383],{"type":63,"value":377},"If the user wants local deployment, hand off to ",{"type":57,"tag":79,"props":379,"children":381},{"className":380},[],[382],{"type":63,"value":132},{"type":63,"value":384}," and preserve the original research request.",{"type":57,"tag":97,"props":386,"children":387},{},[388,390,396,398,404],{"type":63,"value":389},"If a reachable backend returns ",{"type":57,"tag":79,"props":391,"children":393},{"className":392},[],[394],{"type":63,"value":395},"401",{"type":63,"value":397}," or ",{"type":57,"tag":79,"props":399,"children":401},{"className":400},[],[402],{"type":63,"value":403},"403",{"type":63,"value":405},", stop and explain that this public skill does not manage\nauthentication. Ask the user to use an authenticated AI-Q skill or configure authentication for their environment.",{"type":57,"tag":97,"props":407,"children":408},{},[409,410,415,417,423,424,430,432,437],{"type":63,"value":327},{"type":57,"tag":79,"props":411,"children":413},{"className":412},[],[414],{"type":63,"value":227},{"type":63,"value":416}," succeeds but ",{"type":57,"tag":79,"props":418,"children":420},{"className":419},[],[421],{"type":63,"value":422},"\u002Fchat",{"type":63,"value":397},{"type":57,"tag":79,"props":425,"children":427},{"className":426},[],[428],{"type":63,"value":429},"\u002Fv1\u002Fjobs\u002Fasync\u002Fagents",{"type":63,"value":431}," fails, report that the backend is reachable but not\ncompatible with this public research flow, then offer to run ",{"type":57,"tag":79,"props":433,"children":435},{"className":434},[],[436],{"type":63,"value":132},{"type":63,"value":438}," validation.",{"type":57,"tag":262,"props":440,"children":442},{"id":441},"step-2-send-the-routed-research-request",[443],{"type":63,"value":444},"Step 2 - Send the routed research request",{"type":57,"tag":73,"props":446,"children":447},{},[448],{"type":63,"value":449},"Before sending the request, state the resolved endpoint:",{"type":57,"tag":281,"props":451,"children":454},{"className":452,"code":453,"language":63,"meta":285},[345],"I will send this query to \u003CAIQ_SERVER_URL>. Make sure this endpoint is trusted before sending sensitive information.\n",[455],{"type":57,"tag":79,"props":456,"children":457},{"__ignoreMap":285},[458],{"type":63,"value":453},{"type":57,"tag":73,"props":460,"children":461},{},[462],{"type":63,"value":463},"Do not send credentials, cookies, bearer tokens, or secret values through the query text.",{"type":57,"tag":73,"props":465,"children":466},{},[467],{"type":63,"value":468},"Run:",{"type":57,"tag":281,"props":470,"children":472},{"className":283,"code":471,"language":51,"meta":285,"style":285},"python3 $SKILL_DIR\u002Fscripts\u002Faiq.py chat \"\u003CUSER_QUESTION>\"\n",[473],{"type":57,"tag":79,"props":474,"children":475},{"__ignoreMap":285},[476],{"type":57,"tag":291,"props":477,"children":478},{"class":293,"line":294},[479,483,487,491,496,502,507],{"type":57,"tag":291,"props":480,"children":481},{"style":298},[482],{"type":63,"value":158},{"type":57,"tag":291,"props":484,"children":485},{"style":303},[486],{"type":63,"value":306},{"type":57,"tag":291,"props":488,"children":489},{"style":309},[490],{"type":63,"value":312},{"type":57,"tag":291,"props":492,"children":493},{"style":309},[494],{"type":63,"value":495}," chat",{"type":57,"tag":291,"props":497,"children":499},{"style":498},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[500],{"type":63,"value":501}," \"",{"type":57,"tag":291,"props":503,"children":504},{"style":309},[505],{"type":63,"value":506},"\u003CUSER_QUESTION>",{"type":57,"tag":291,"props":508,"children":509},{"style":498},[510],{"type":63,"value":511},"\"\n",{"type":57,"tag":73,"props":513,"children":514},{},[515],{"type":63,"value":516},"Expected output:",{"type":57,"tag":93,"props":518,"children":519},{},[520,525],{"type":57,"tag":97,"props":521,"children":522},{},[523],{"type":63,"value":524},"A normal JSON response for shallow or direct answers.",{"type":57,"tag":97,"props":526,"children":527},{},[528,530,536],{"type":63,"value":529},"Or structured JSON containing ",{"type":57,"tag":79,"props":531,"children":533},{"className":532},[],[534],{"type":63,"value":535},"{\"status\": \"deep_research_running\", \"job_id\": \"\u003CJOB_ID>\"}",{"type":63,"value":537}," for asynchronous deep\nresearch.",{"type":57,"tag":73,"props":539,"children":540},{},[541,543,549],{"type":63,"value":542},"If the response is normal JSON, present the result immediately. Do not force polling when there is no ",{"type":57,"tag":79,"props":544,"children":546},{"className":545},[],[547],{"type":63,"value":548},"job_id",{"type":63,"value":86},{"type":57,"tag":262,"props":551,"children":553},{"id":552},"step-3-poll-asynchronous-jobs",[554],{"type":63,"value":555},"Step 3 - Poll asynchronous jobs",{"type":57,"tag":73,"props":557,"children":558},{},[559,561,567,569,574],{"type":63,"value":560},"If the response includes ",{"type":57,"tag":79,"props":562,"children":564},{"className":563},[],[565],{"type":63,"value":566},"deep_research_running",{"type":63,"value":568},", extract the ",{"type":57,"tag":79,"props":570,"children":572},{"className":571},[],[573],{"type":63,"value":548},{"type":63,"value":575}," and poll with the same absolute script path:",{"type":57,"tag":281,"props":577,"children":579},{"className":283,"code":578,"language":51,"meta":285,"style":285},"python3 $SKILL_DIR\u002Fscripts\u002Faiq.py research_poll \u003CJOB_ID>\n",[580],{"type":57,"tag":79,"props":581,"children":582},{"__ignoreMap":285},[583],{"type":57,"tag":291,"props":584,"children":585},{"class":293,"line":294},[586,590,594,598,603,608,613,618],{"type":57,"tag":291,"props":587,"children":588},{"style":298},[589],{"type":63,"value":158},{"type":57,"tag":291,"props":591,"children":592},{"style":303},[593],{"type":63,"value":306},{"type":57,"tag":291,"props":595,"children":596},{"style":309},[597],{"type":63,"value":312},{"type":57,"tag":291,"props":599,"children":600},{"style":309},[601],{"type":63,"value":602}," research_poll",{"type":57,"tag":291,"props":604,"children":605},{"style":498},[606],{"type":63,"value":607}," \u003C",{"type":57,"tag":291,"props":609,"children":610},{"style":309},[611],{"type":63,"value":612},"JOB_I",{"type":57,"tag":291,"props":614,"children":615},{"style":303},[616],{"type":63,"value":617},"D",{"type":57,"tag":291,"props":619,"children":620},{"style":498},[621],{"type":63,"value":622},">\n",{"type":57,"tag":73,"props":624,"children":625},{},[626],{"type":63,"value":627},"Expected output: the final report JSON when the job completes successfully.",{"type":57,"tag":73,"props":629,"children":630},{},[631],{"type":63,"value":632},"Use the runtime's non-blocking or background execution mechanism when available. If the chosen execution method requires\nescalated permissions, request explicit user approval first and explain why. Tell the user that deep research is running\nin the background.",{"type":57,"tag":262,"props":634,"children":636},{"id":635},"step-4-resume-after-interruptions",[637],{"type":63,"value":638},"Step 4 - Resume after interruptions",{"type":57,"tag":73,"props":640,"children":641},{},[642],{"type":63,"value":643},"If polling is interrupted, the job continues server-side. Resume with:",{"type":57,"tag":281,"props":645,"children":647},{"className":283,"code":646,"language":51,"meta":285,"style":285},"python3 $SKILL_DIR\u002Fscripts\u002Faiq.py status \u003CJOB_ID>\npython3 $SKILL_DIR\u002Fscripts\u002Faiq.py report \u003CJOB_ID>\npython3 $SKILL_DIR\u002Fscripts\u002Faiq.py research_poll \u003CJOB_ID>\n",[648],{"type":57,"tag":79,"props":649,"children":650},{"__ignoreMap":285},[651,687,724],{"type":57,"tag":291,"props":652,"children":653},{"class":293,"line":294},[654,658,662,666,671,675,679,683],{"type":57,"tag":291,"props":655,"children":656},{"style":298},[657],{"type":63,"value":158},{"type":57,"tag":291,"props":659,"children":660},{"style":303},[661],{"type":63,"value":306},{"type":57,"tag":291,"props":663,"children":664},{"style":309},[665],{"type":63,"value":312},{"type":57,"tag":291,"props":667,"children":668},{"style":309},[669],{"type":63,"value":670}," status",{"type":57,"tag":291,"props":672,"children":673},{"style":498},[674],{"type":63,"value":607},{"type":57,"tag":291,"props":676,"children":677},{"style":309},[678],{"type":63,"value":612},{"type":57,"tag":291,"props":680,"children":681},{"style":303},[682],{"type":63,"value":617},{"type":57,"tag":291,"props":684,"children":685},{"style":498},[686],{"type":63,"value":622},{"type":57,"tag":291,"props":688,"children":690},{"class":293,"line":689},2,[691,695,699,703,708,712,716,720],{"type":57,"tag":291,"props":692,"children":693},{"style":298},[694],{"type":63,"value":158},{"type":57,"tag":291,"props":696,"children":697},{"style":303},[698],{"type":63,"value":306},{"type":57,"tag":291,"props":700,"children":701},{"style":309},[702],{"type":63,"value":312},{"type":57,"tag":291,"props":704,"children":705},{"style":309},[706],{"type":63,"value":707}," report",{"type":57,"tag":291,"props":709,"children":710},{"style":498},[711],{"type":63,"value":607},{"type":57,"tag":291,"props":713,"children":714},{"style":309},[715],{"type":63,"value":612},{"type":57,"tag":291,"props":717,"children":718},{"style":303},[719],{"type":63,"value":617},{"type":57,"tag":291,"props":721,"children":722},{"style":498},[723],{"type":63,"value":622},{"type":57,"tag":291,"props":725,"children":727},{"class":293,"line":726},3,[728,732,736,740,744,748,752,756],{"type":57,"tag":291,"props":729,"children":730},{"style":298},[731],{"type":63,"value":158},{"type":57,"tag":291,"props":733,"children":734},{"style":303},[735],{"type":63,"value":306},{"type":57,"tag":291,"props":737,"children":738},{"style":309},[739],{"type":63,"value":312},{"type":57,"tag":291,"props":741,"children":742},{"style":309},[743],{"type":63,"value":602},{"type":57,"tag":291,"props":745,"children":746},{"style":498},[747],{"type":63,"value":607},{"type":57,"tag":291,"props":749,"children":750},{"style":309},[751],{"type":63,"value":612},{"type":57,"tag":291,"props":753,"children":754},{"style":303},[755],{"type":63,"value":617},{"type":57,"tag":291,"props":757,"children":758},{"style":498},[759],{"type":63,"value":622},{"type":57,"tag":73,"props":761,"children":762},{},[763,764,770,772,778,780,786],{"type":63,"value":272},{"type":57,"tag":79,"props":765,"children":767},{"className":766},[],[768],{"type":63,"value":769},"status",{"type":63,"value":771}," to inspect job status and saved artifacts. Use ",{"type":57,"tag":79,"props":773,"children":775},{"className":774},[],[776],{"type":63,"value":777},"report",{"type":63,"value":779}," when the job has already finished and you only need\nthe final output. Use ",{"type":57,"tag":79,"props":781,"children":783},{"className":782},[],[784],{"type":63,"value":785},"research_poll",{"type":63,"value":787}," to keep waiting for completion.",{"type":57,"tag":262,"props":789,"children":791},{"id":790},"step-5-present-the-report",[792],{"type":63,"value":793},"Step 5 - Present the report",{"type":57,"tag":73,"props":795,"children":796},{},[797,799,804,806,812,814,820,822,828],{"type":63,"value":798},"When ",{"type":57,"tag":79,"props":800,"children":802},{"className":801},[],[803],{"type":63,"value":785},{"type":63,"value":805}," completes successfully, fetch and present the full report. Keep citations and source URLs intact.\nIf the job status is ",{"type":57,"tag":79,"props":807,"children":809},{"className":808},[],[810],{"type":63,"value":811},"failed",{"type":63,"value":813},", ",{"type":57,"tag":79,"props":815,"children":817},{"className":816},[],[818],{"type":63,"value":819},"failure",{"type":63,"value":821},", or ",{"type":57,"tag":79,"props":823,"children":825},{"className":824},[],[826],{"type":63,"value":827},"cancelled",{"type":63,"value":829},", show the error from the status response and ask whether the\nuser wants to retry with a narrower query or different approach.",{"type":57,"tag":66,"props":831,"children":833},{"id":832},"version-compatibility",[834],{"type":63,"value":835},"Version Compatibility",{"type":57,"tag":73,"props":837,"children":838},{},[839,845],{"type":57,"tag":840,"props":841,"children":842},"strong",{},[843],{"type":63,"value":844},"IMPORTANT:",{"type":63,"value":846}," This skill is designed for NVIDIA AI-Q Blueprint version 2.1.0.",{"type":57,"tag":73,"props":848,"children":849},{},[850],{"type":63,"value":851},"Semantic Versioning Compatibility Rules:",{"type":57,"tag":281,"props":853,"children":856},{"className":854,"code":855,"language":63,"meta":285},[345],"Skill version: X.Y.Z\nBlueprint or endpoint version: A.B.C\n\nCompatible IF:\n1. A == X (Major versions MUST match)\n2. B >= Y (Minor version must be equal or greater)\n3. C can be anything (Patch version does not affect compatibility)\n",[857],{"type":57,"tag":79,"props":858,"children":859},{"__ignoreMap":285},[860],{"type":63,"value":855},{"type":57,"tag":73,"props":862,"children":863},{},[864],{"type":63,"value":865},"Examples:",{"type":57,"tag":93,"props":867,"children":868},{},[869,874,879,884,889],{"type":57,"tag":97,"props":870,"children":871},{},[872],{"type":63,"value":873},"Skill version 2.1.0 is compatible with Blueprint version 2.1.0.",{"type":57,"tag":97,"props":875,"children":876},{},[877],{"type":63,"value":878},"Skill version 2.1.0 is compatible with Blueprint version 2.2.0.",{"type":57,"tag":97,"props":880,"children":881},{},[882],{"type":63,"value":883},"Skill version 2.1.0 is compatible with Blueprint version 2.1.5.",{"type":57,"tag":97,"props":885,"children":886},{},[887],{"type":63,"value":888},"Skill version 2.1.0 is not compatible with Blueprint version 3.0.0.",{"type":57,"tag":97,"props":890,"children":891},{},[892],{"type":63,"value":893},"Skill version 2.1.0 is not compatible with Blueprint version 2.0.0.",{"type":57,"tag":73,"props":895,"children":896},{},[897],{"type":63,"value":898},"If your Blueprint version is not compatible:",{"type":57,"tag":209,"props":900,"children":901},{},[902,907,912],{"type":57,"tag":97,"props":903,"children":904},{},[905],{"type":63,"value":906},"Check for an updated skill version matching your Blueprint version.",{"type":57,"tag":97,"props":908,"children":909},{},[910],{"type":63,"value":911},"Use a Blueprint version compatible with this skill.",{"type":57,"tag":97,"props":913,"children":914},{},[915],{"type":63,"value":916},"Proceed with caution only when the user accepts the compatibility risk; API routes or response shapes may have\nchanged.",{"type":57,"tag":66,"props":918,"children":920},{"id":919},"available-scripts",[921],{"type":63,"value":922},"Available Scripts",{"type":57,"tag":924,"props":925,"children":926},"table",{},[927,950],{"type":57,"tag":928,"props":929,"children":930},"thead",{},[931],{"type":57,"tag":932,"props":933,"children":934},"tr",{},[935,941,945],{"type":57,"tag":936,"props":937,"children":938},"th",{},[939],{"type":63,"value":940},"Script",{"type":57,"tag":936,"props":942,"children":943},{},[944],{"type":63,"value":71},{"type":57,"tag":936,"props":946,"children":947},{},[948],{"type":63,"value":949},"Arguments",{"type":57,"tag":951,"props":952,"children":953},"tbody",{},[954,977,1010,1031,1057,1082,1108,1141,1166,1191,1216],{"type":57,"tag":932,"props":955,"children":956},{},[957,967,972],{"type":57,"tag":958,"props":959,"children":960},"td",{},[961],{"type":57,"tag":79,"props":962,"children":964},{"className":963},[],[965],{"type":63,"value":966},"scripts\u002Faiq.py health",{"type":57,"tag":958,"props":968,"children":969},{},[970],{"type":63,"value":971},"Check whether the configured server responds",{"type":57,"tag":958,"props":973,"children":974},{},[975],{"type":63,"value":976},"none",{"type":57,"tag":932,"props":978,"children":979},{},[980,989,1001],{"type":57,"tag":958,"props":981,"children":982},{},[983],{"type":57,"tag":79,"props":984,"children":986},{"className":985},[],[987],{"type":63,"value":988},"scripts\u002Faiq.py chat",{"type":57,"tag":958,"props":990,"children":991},{},[992,994,999],{"type":63,"value":993},"POST ",{"type":57,"tag":79,"props":995,"children":997},{"className":996},[],[998],{"type":63,"value":422},{"type":63,"value":1000},"; may return inline output or a deep-research job ID",{"type":57,"tag":958,"props":1002,"children":1003},{},[1004],{"type":57,"tag":79,"props":1005,"children":1007},{"className":1006},[],[1008],{"type":63,"value":1009},"\u003Cquery>",{"type":57,"tag":932,"props":1011,"children":1012},{},[1013,1022,1027],{"type":57,"tag":958,"props":1014,"children":1015},{},[1016],{"type":57,"tag":79,"props":1017,"children":1019},{"className":1018},[],[1020],{"type":63,"value":1021},"scripts\u002Faiq.py agents",{"type":57,"tag":958,"props":1023,"children":1024},{},[1025],{"type":63,"value":1026},"List available async agent types",{"type":57,"tag":958,"props":1028,"children":1029},{},[1030],{"type":63,"value":976},{"type":57,"tag":932,"props":1032,"children":1033},{},[1034,1043,1048],{"type":57,"tag":958,"props":1035,"children":1036},{},[1037],{"type":57,"tag":79,"props":1038,"children":1040},{"className":1039},[],[1041],{"type":63,"value":1042},"scripts\u002Faiq.py submit",{"type":57,"tag":958,"props":1044,"children":1045},{},[1046],{"type":63,"value":1047},"Submit an explicit async job",{"type":57,"tag":958,"props":1049,"children":1050},{},[1051],{"type":57,"tag":79,"props":1052,"children":1054},{"className":1053},[],[1055],{"type":63,"value":1056},"\u003Cquery> [agent_type]",{"type":57,"tag":932,"props":1058,"children":1059},{},[1060,1069,1074],{"type":57,"tag":958,"props":1061,"children":1062},{},[1063],{"type":57,"tag":79,"props":1064,"children":1066},{"className":1065},[],[1067],{"type":63,"value":1068},"scripts\u002Faiq.py research",{"type":57,"tag":958,"props":1070,"children":1071},{},[1072],{"type":63,"value":1073},"Submit an async job, poll, and print the final report JSON",{"type":57,"tag":958,"props":1075,"children":1076},{},[1077],{"type":57,"tag":79,"props":1078,"children":1080},{"className":1079},[],[1081],{"type":63,"value":1056},{"type":57,"tag":932,"props":1083,"children":1084},{},[1085,1094,1099],{"type":57,"tag":958,"props":1086,"children":1087},{},[1088],{"type":57,"tag":79,"props":1089,"children":1091},{"className":1090},[],[1092],{"type":63,"value":1093},"scripts\u002Faiq.py research_poll",{"type":57,"tag":958,"props":1095,"children":1096},{},[1097],{"type":63,"value":1098},"Resume polling an existing async job",{"type":57,"tag":958,"props":1100,"children":1101},{},[1102],{"type":57,"tag":79,"props":1103,"children":1105},{"className":1104},[],[1106],{"type":63,"value":1107},"\u003Cjob_id>",{"type":57,"tag":932,"props":1109,"children":1110},{},[1111,1120,1133],{"type":57,"tag":958,"props":1112,"children":1113},{},[1114],{"type":57,"tag":79,"props":1115,"children":1117},{"className":1116},[],[1118],{"type":63,"value":1119},"scripts\u002Faiq.py status",{"type":57,"tag":958,"props":1121,"children":1122},{},[1123,1125,1131],{"type":63,"value":1124},"Fetch job status plus ",{"type":57,"tag":79,"props":1126,"children":1128},{"className":1127},[],[1129],{"type":63,"value":1130},"\u002Fstate",{"type":63,"value":1132}," artifacts",{"type":57,"tag":958,"props":1134,"children":1135},{},[1136],{"type":57,"tag":79,"props":1137,"children":1139},{"className":1138},[],[1140],{"type":63,"value":1107},{"type":57,"tag":932,"props":1142,"children":1143},{},[1144,1153,1158],{"type":57,"tag":958,"props":1145,"children":1146},{},[1147],{"type":57,"tag":79,"props":1148,"children":1150},{"className":1149},[],[1151],{"type":63,"value":1152},"scripts\u002Faiq.py state",{"type":57,"tag":958,"props":1154,"children":1155},{},[1156],{"type":63,"value":1157},"Fetch event-store artifacts only",{"type":57,"tag":958,"props":1159,"children":1160},{},[1161],{"type":57,"tag":79,"props":1162,"children":1164},{"className":1163},[],[1165],{"type":63,"value":1107},{"type":57,"tag":932,"props":1167,"children":1168},{},[1169,1178,1183],{"type":57,"tag":958,"props":1170,"children":1171},{},[1172],{"type":57,"tag":79,"props":1173,"children":1175},{"className":1174},[],[1176],{"type":63,"value":1177},"scripts\u002Faiq.py report",{"type":57,"tag":958,"props":1179,"children":1180},{},[1181],{"type":63,"value":1182},"Fetch the final report for a completed job",{"type":57,"tag":958,"props":1184,"children":1185},{},[1186],{"type":57,"tag":79,"props":1187,"children":1189},{"className":1188},[],[1190],{"type":63,"value":1107},{"type":57,"tag":932,"props":1192,"children":1193},{},[1194,1203,1208],{"type":57,"tag":958,"props":1195,"children":1196},{},[1197],{"type":57,"tag":79,"props":1198,"children":1200},{"className":1199},[],[1201],{"type":63,"value":1202},"scripts\u002Faiq.py stream",{"type":57,"tag":958,"props":1204,"children":1205},{},[1206],{"type":63,"value":1207},"Stream SSE events from a job",{"type":57,"tag":958,"props":1209,"children":1210},{},[1211],{"type":57,"tag":79,"props":1212,"children":1214},{"className":1213},[],[1215],{"type":63,"value":1107},{"type":57,"tag":932,"props":1217,"children":1218},{},[1219,1228,1233],{"type":57,"tag":958,"props":1220,"children":1221},{},[1222],{"type":57,"tag":79,"props":1223,"children":1225},{"className":1224},[],[1226],{"type":63,"value":1227},"scripts\u002Faiq.py cancel",{"type":57,"tag":958,"props":1229,"children":1230},{},[1231],{"type":63,"value":1232},"Cancel a running job",{"type":57,"tag":958,"props":1234,"children":1235},{},[1236],{"type":57,"tag":79,"props":1237,"children":1239},{"className":1238},[],[1240],{"type":63,"value":1107},{"type":57,"tag":73,"props":1242,"children":1243},{},[1244,1246,1252,1254,1259,1261,1267],{"type":63,"value":1245},"When the host supports a ",{"type":57,"tag":79,"props":1247,"children":1249},{"className":1248},[],[1250],{"type":63,"value":1251},"run_script()",{"type":63,"value":1253}," helper, call it with ",{"type":57,"tag":79,"props":1255,"children":1257},{"className":1256},[],[1258],{"type":63,"value":84},{"type":63,"value":1260}," and the arguments above. Otherwise, run\nthe equivalent shell command, such as ",{"type":57,"tag":79,"props":1262,"children":1264},{"className":1263},[],[1265],{"type":63,"value":1266},"python3 $SKILL_DIR\u002Fscripts\u002Faiq.py health",{"type":63,"value":86},{"type":57,"tag":66,"props":1269,"children":1271},{"id":1270},"environment-variables",[1272],{"type":63,"value":1273},"Environment Variables",{"type":57,"tag":924,"props":1275,"children":1276},{},[1277,1304],{"type":57,"tag":928,"props":1278,"children":1279},{},[1280],{"type":57,"tag":932,"props":1281,"children":1282},{},[1283,1288,1294,1299],{"type":57,"tag":936,"props":1284,"children":1285},{},[1286],{"type":63,"value":1287},"Variable",{"type":57,"tag":936,"props":1289,"children":1291},{"align":1290},"right",[1292],{"type":63,"value":1293},"Required",{"type":57,"tag":936,"props":1295,"children":1296},{},[1297],{"type":63,"value":1298},"Default",{"type":57,"tag":936,"props":1300,"children":1301},{},[1302],{"type":63,"value":1303},"Description",{"type":57,"tag":951,"props":1305,"children":1306},{},[1307],{"type":57,"tag":932,"props":1308,"children":1309},{},[1310,1318,1323,1331],{"type":57,"tag":958,"props":1311,"children":1312},{},[1313],{"type":57,"tag":79,"props":1314,"children":1316},{"className":1315},[],[1317],{"type":63,"value":34},{"type":57,"tag":958,"props":1319,"children":1320},{"align":1290},[1321],{"type":63,"value":1322},"No",{"type":57,"tag":958,"props":1324,"children":1325},{},[1326],{"type":57,"tag":79,"props":1327,"children":1329},{"className":1328},[],[1330],{"type":63,"value":36},{"type":57,"tag":958,"props":1332,"children":1333},{},[1334],{"type":63,"value":1335},"Local or self-hosted AI-Q server base URL",{"type":57,"tag":66,"props":1337,"children":1339},{"id":1338},"security-best-practices",[1340],{"type":63,"value":1341},"Security Best Practices",{"type":57,"tag":93,"props":1343,"children":1344},{},[1345,1356,1361,1373,1378],{"type":57,"tag":97,"props":1346,"children":1347},{},[1348,1350,1355],{"type":63,"value":1349},"Do not put API keys, bearer tokens, cookies, or basic-auth credentials in ",{"type":57,"tag":79,"props":1351,"children":1353},{"className":1352},[],[1354],{"type":63,"value":34},{"type":63,"value":86},{"type":57,"tag":97,"props":1357,"children":1358},{},[1359],{"type":63,"value":1360},"Store backend credentials in the AI-Q deployment environment, not in this skill or command examples.",{"type":57,"tag":97,"props":1362,"children":1363},{},[1364,1366,1371],{"type":63,"value":1365},"User query text is transmitted to the configured ",{"type":57,"tag":79,"props":1367,"children":1369},{"className":1368},[],[1370],{"type":63,"value":34},{"type":63,"value":1372},". Confirm the endpoint is trusted before sending\nsensitive or confidential information.",{"type":57,"tag":97,"props":1374,"children":1375},{},[1376],{"type":63,"value":1377},"Treat returned reports as potentially sensitive if the backend uses private data sources.",{"type":57,"tag":97,"props":1379,"children":1380},{},[1381],{"type":63,"value":1382},"Do not truncate citations or source URLs from returned reports.",{"type":57,"tag":66,"props":1384,"children":1386},{"id":1385},"limitations",[1387],{"type":63,"value":1388},"Limitations",{"type":57,"tag":93,"props":1390,"children":1391},{},[1392,1397,1402,1414],{"type":57,"tag":97,"props":1393,"children":1394},{},[1395],{"type":63,"value":1396},"This skill requires a running AI-Q backend; it does not deploy one.",{"type":57,"tag":97,"props":1398,"children":1399},{},[1400],{"type":63,"value":1401},"The public helper does not manage authentication tokens or cookies.",{"type":57,"tag":97,"props":1403,"children":1404},{},[1405,1407,1412],{"type":63,"value":1406},"Remote ",{"type":57,"tag":79,"props":1408,"children":1410},{"className":1409},[],[1411],{"type":63,"value":34},{"type":63,"value":1413}," endpoints may log prompts, responses, and metadata.",{"type":57,"tag":97,"props":1415,"children":1416},{},[1417],{"type":63,"value":1418},"If the backend returns HTTP 500 or lacks async agents, report the failure instead of fabricating a research answer.",{"type":57,"tag":66,"props":1420,"children":1422},{"id":1421},"examples",[1423],{"type":63,"value":1424},"Examples",{"type":57,"tag":262,"props":1426,"children":1428},{"id":1427},"example-1-run-a-routed-chat-or-research-request",[1429],{"type":63,"value":1430},"Example 1: Run a routed chat or research request",{"type":57,"tag":281,"props":1432,"children":1434},{"className":283,"code":1433,"language":51,"meta":285,"style":285},"python3 $SKILL_DIR\u002Fscripts\u002Faiq.py health\npython3 $SKILL_DIR\u002Fscripts\u002Faiq.py chat \"Compare local AIQ deep research with a standard web search workflow\"\n",[1435],{"type":57,"tag":79,"props":1436,"children":1437},{"__ignoreMap":285},[1438,1457],{"type":57,"tag":291,"props":1439,"children":1440},{"class":293,"line":294},[1441,1445,1449,1453],{"type":57,"tag":291,"props":1442,"children":1443},{"style":298},[1444],{"type":63,"value":158},{"type":57,"tag":291,"props":1446,"children":1447},{"style":303},[1448],{"type":63,"value":306},{"type":57,"tag":291,"props":1450,"children":1451},{"style":309},[1452],{"type":63,"value":312},{"type":57,"tag":291,"props":1454,"children":1455},{"style":309},[1456],{"type":63,"value":317},{"type":57,"tag":291,"props":1458,"children":1459},{"class":293,"line":689},[1460,1464,1468,1472,1476,1480,1485],{"type":57,"tag":291,"props":1461,"children":1462},{"style":298},[1463],{"type":63,"value":158},{"type":57,"tag":291,"props":1465,"children":1466},{"style":303},[1467],{"type":63,"value":306},{"type":57,"tag":291,"props":1469,"children":1470},{"style":309},[1471],{"type":63,"value":312},{"type":57,"tag":291,"props":1473,"children":1474},{"style":309},[1475],{"type":63,"value":495},{"type":57,"tag":291,"props":1477,"children":1478},{"style":498},[1479],{"type":63,"value":501},{"type":57,"tag":291,"props":1481,"children":1482},{"style":309},[1483],{"type":63,"value":1484},"Compare local AIQ deep research with a standard web search workflow",{"type":57,"tag":291,"props":1486,"children":1487},{"style":498},[1488],{"type":63,"value":511},{"type":57,"tag":73,"props":1490,"children":1491},{},[1492],{"type":63,"value":516},{"type":57,"tag":281,"props":1494,"children":1497},{"className":1495,"code":1496,"language":63,"meta":285},[345],"\u003Chealth JSON from AI-Q>\n\u003CJSON chat response or {\"status\": \"deep_research_running\", \"job_id\": \"\u003CJOB_ID>\"}>\n",[1498],{"type":57,"tag":79,"props":1499,"children":1500},{"__ignoreMap":285},[1501],{"type":63,"value":1496},{"type":57,"tag":73,"props":1503,"children":1504},{},[1505,1507,1512],{"type":63,"value":1506},"If AI-Q returns a job ID, continue with ",{"type":57,"tag":79,"props":1508,"children":1510},{"className":1509},[],[1511],{"type":63,"value":785},{"type":63,"value":86},{"type":57,"tag":262,"props":1514,"children":1516},{"id":1515},"example-2-resume-an-existing-job",[1517],{"type":63,"value":1518},"Example 2: Resume an existing job",{"type":57,"tag":281,"props":1520,"children":1522},{"className":283,"code":1521,"language":51,"meta":285,"style":285},"python3 $SKILL_DIR\u002Fscripts\u002Faiq.py status \u003CJOB_ID>\npython3 $SKILL_DIR\u002Fscripts\u002Faiq.py research_poll \u003CJOB_ID>\n",[1523],{"type":57,"tag":79,"props":1524,"children":1525},{"__ignoreMap":285},[1526,1561],{"type":57,"tag":291,"props":1527,"children":1528},{"class":293,"line":294},[1529,1533,1537,1541,1545,1549,1553,1557],{"type":57,"tag":291,"props":1530,"children":1531},{"style":298},[1532],{"type":63,"value":158},{"type":57,"tag":291,"props":1534,"children":1535},{"style":303},[1536],{"type":63,"value":306},{"type":57,"tag":291,"props":1538,"children":1539},{"style":309},[1540],{"type":63,"value":312},{"type":57,"tag":291,"props":1542,"children":1543},{"style":309},[1544],{"type":63,"value":670},{"type":57,"tag":291,"props":1546,"children":1547},{"style":498},[1548],{"type":63,"value":607},{"type":57,"tag":291,"props":1550,"children":1551},{"style":309},[1552],{"type":63,"value":612},{"type":57,"tag":291,"props":1554,"children":1555},{"style":303},[1556],{"type":63,"value":617},{"type":57,"tag":291,"props":1558,"children":1559},{"style":498},[1560],{"type":63,"value":622},{"type":57,"tag":291,"props":1562,"children":1563},{"class":293,"line":689},[1564,1568,1572,1576,1580,1584,1588,1592],{"type":57,"tag":291,"props":1565,"children":1566},{"style":298},[1567],{"type":63,"value":158},{"type":57,"tag":291,"props":1569,"children":1570},{"style":303},[1571],{"type":63,"value":306},{"type":57,"tag":291,"props":1573,"children":1574},{"style":309},[1575],{"type":63,"value":312},{"type":57,"tag":291,"props":1577,"children":1578},{"style":309},[1579],{"type":63,"value":602},{"type":57,"tag":291,"props":1581,"children":1582},{"style":498},[1583],{"type":63,"value":607},{"type":57,"tag":291,"props":1585,"children":1586},{"style":309},[1587],{"type":63,"value":612},{"type":57,"tag":291,"props":1589,"children":1590},{"style":303},[1591],{"type":63,"value":617},{"type":57,"tag":291,"props":1593,"children":1594},{"style":498},[1595],{"type":63,"value":622},{"type":57,"tag":73,"props":1597,"children":1598},{},[1599,1601,1607],{"type":63,"value":1600},"Replace ",{"type":57,"tag":79,"props":1602,"children":1604},{"className":1603},[],[1605],{"type":63,"value":1606},"\u003CJOB_ID>",{"type":63,"value":1608}," with the UUID returned by AI-Q. Expected output: status JSON followed by the report JSON when the\njob completes. If the job failed, show the returned status and do not retry automatically.",{"type":57,"tag":66,"props":1610,"children":1612},{"id":1611},"references",[1613],{"type":63,"value":1614},"References",{"type":57,"tag":924,"props":1616,"children":1617},{},[1618,1634],{"type":57,"tag":928,"props":1619,"children":1620},{},[1621],{"type":57,"tag":932,"props":1622,"children":1623},{},[1624,1629],{"type":57,"tag":936,"props":1625,"children":1626},{},[1627],{"type":63,"value":1628},"Topic",{"type":57,"tag":936,"props":1630,"children":1631},{},[1632],{"type":63,"value":1633},"Documentation",{"type":57,"tag":951,"props":1635,"children":1636},{},[1637,1653],{"type":57,"tag":932,"props":1638,"children":1639},{},[1640,1645],{"type":57,"tag":958,"props":1641,"children":1642},{},[1643],{"type":63,"value":1644},"Helper script",{"type":57,"tag":958,"props":1646,"children":1647},{},[1648],{"type":57,"tag":79,"props":1649,"children":1651},{"className":1650},[],[1652],{"type":63,"value":84},{"type":57,"tag":932,"props":1654,"children":1655},{},[1656,1661],{"type":57,"tag":958,"props":1657,"children":1658},{},[1659],{"type":63,"value":1660},"Deployment and backend validation",{"type":57,"tag":958,"props":1662,"children":1663},{},[1664],{"type":57,"tag":79,"props":1665,"children":1667},{"className":1666},[],[1668],{"type":63,"value":1669},"..\u002Faiq-deploy\u002FSKILL.md",{"type":57,"tag":66,"props":1671,"children":1673},{"id":1672},"common-issues",[1674],{"type":63,"value":1675},"Common Issues",{"type":57,"tag":262,"props":1677,"children":1679},{"id":1678},"issue-no-backend-is-reachable",[1680],{"type":63,"value":1681},"Issue: No backend is reachable",{"type":57,"tag":73,"props":1683,"children":1684},{},[1685],{"type":57,"tag":840,"props":1686,"children":1687},{},[1688],{"type":63,"value":1689},"Symptoms:",{"type":57,"tag":93,"props":1691,"children":1692},{},[1693,1703],{"type":57,"tag":97,"props":1694,"children":1695},{},[1696,1701],{"type":57,"tag":79,"props":1697,"children":1699},{"className":1698},[],[1700],{"type":63,"value":227},{"type":63,"value":1702}," fails with connection refused.",{"type":57,"tag":97,"props":1704,"children":1705},{},[1706,1708,1713],{"type":63,"value":1707},"The default ",{"type":57,"tag":79,"props":1709,"children":1711},{"className":1710},[],[1712],{"type":63,"value":36},{"type":63,"value":1714}," URL does not respond.",{"type":57,"tag":73,"props":1716,"children":1717},{},[1718],{"type":57,"tag":840,"props":1719,"children":1720},{},[1721],{"type":63,"value":1722},"Causes:",{"type":57,"tag":93,"props":1724,"children":1725},{},[1726,1731,1736],{"type":57,"tag":97,"props":1727,"children":1728},{},[1729],{"type":63,"value":1730},"AI-Q is not running.",{"type":57,"tag":97,"props":1732,"children":1733},{},[1734],{"type":63,"value":1735},"AI-Q is running on a different host or port.",{"type":57,"tag":97,"props":1737,"children":1738},{},[1739],{"type":63,"value":1740},"A local firewall or network setting blocks the connection.",{"type":57,"tag":73,"props":1742,"children":1743},{},[1744],{"type":57,"tag":840,"props":1745,"children":1746},{},[1747],{"type":63,"value":1748},"Solutions:",{"type":57,"tag":209,"props":1750,"children":1751},{},[1752,1757,1821],{"type":57,"tag":97,"props":1753,"children":1754},{},[1755],{"type":63,"value":1756},"Ask whether the user has an existing AI-Q backend URL.",{"type":57,"tag":97,"props":1758,"children":1759},{},[1760,1762],{"type":63,"value":1761},"If they provide one, set it and rerun health:\n",{"type":57,"tag":281,"props":1763,"children":1765},{"className":283,"code":1764,"language":51,"meta":285,"style":285},"export AIQ_SERVER_URL=\"http:\u002F\u002Flocalhost:\u003CPORT>\"\npython3 $SKILL_DIR\u002Fscripts\u002Faiq.py health\n",[1766],{"type":57,"tag":79,"props":1767,"children":1768},{"__ignoreMap":285},[1769,1802],{"type":57,"tag":291,"props":1770,"children":1771},{"class":293,"line":294},[1772,1778,1783,1788,1793,1798],{"type":57,"tag":291,"props":1773,"children":1775},{"style":1774},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[1776],{"type":63,"value":1777},"export",{"type":57,"tag":291,"props":1779,"children":1780},{"style":303},[1781],{"type":63,"value":1782}," AIQ_SERVER_URL",{"type":57,"tag":291,"props":1784,"children":1785},{"style":498},[1786],{"type":63,"value":1787},"=",{"type":57,"tag":291,"props":1789,"children":1790},{"style":498},[1791],{"type":63,"value":1792},"\"",{"type":57,"tag":291,"props":1794,"children":1795},{"style":309},[1796],{"type":63,"value":1797},"http:\u002F\u002Flocalhost:\u003CPORT>",{"type":57,"tag":291,"props":1799,"children":1800},{"style":498},[1801],{"type":63,"value":511},{"type":57,"tag":291,"props":1803,"children":1804},{"class":293,"line":689},[1805,1809,1813,1817],{"type":57,"tag":291,"props":1806,"children":1807},{"style":298},[1808],{"type":63,"value":158},{"type":57,"tag":291,"props":1810,"children":1811},{"style":303},[1812],{"type":63,"value":306},{"type":57,"tag":291,"props":1814,"children":1815},{"style":309},[1816],{"type":63,"value":312},{"type":57,"tag":291,"props":1818,"children":1819},{"style":309},[1820],{"type":63,"value":317},{"type":57,"tag":97,"props":1822,"children":1823},{},[1824,1826,1831],{"type":63,"value":1825},"If they want a local backend, hand off to ",{"type":57,"tag":79,"props":1827,"children":1829},{"className":1828},[],[1830],{"type":63,"value":132},{"type":63,"value":384},{"type":57,"tag":262,"props":1833,"children":1835},{"id":1834},"issue-backend-requires-authentication",[1836],{"type":63,"value":1837},"Issue: Backend requires authentication",{"type":57,"tag":73,"props":1839,"children":1840},{},[1841],{"type":57,"tag":840,"props":1842,"children":1843},{},[1844],{"type":63,"value":1689},{"type":57,"tag":93,"props":1846,"children":1847},{},[1848,1853],{"type":57,"tag":97,"props":1849,"children":1850},{},[1851],{"type":63,"value":1852},"Requests fail with HTTP 401 or HTTP 403.",{"type":57,"tag":97,"props":1854,"children":1855},{},[1856,1858,1863],{"type":63,"value":1857},"The backend is reachable but rejects ",{"type":57,"tag":79,"props":1859,"children":1861},{"className":1860},[],[1862],{"type":63,"value":422},{"type":63,"value":1864}," or async job calls.",{"type":57,"tag":73,"props":1866,"children":1867},{},[1868],{"type":57,"tag":840,"props":1869,"children":1870},{},[1871],{"type":63,"value":1722},{"type":57,"tag":93,"props":1873,"children":1874},{},[1875,1880],{"type":57,"tag":97,"props":1876,"children":1877},{},[1878],{"type":63,"value":1879},"The backend was deployed with authentication enabled.",{"type":57,"tag":97,"props":1881,"children":1882},{},[1883],{"type":63,"value":1884},"The public helper does not attach user tokens or cookies.",{"type":57,"tag":73,"props":1886,"children":1887},{},[1888],{"type":57,"tag":840,"props":1889,"children":1890},{},[1891],{"type":63,"value":1748},{"type":57,"tag":209,"props":1893,"children":1894},{},[1895,1900,1905],{"type":57,"tag":97,"props":1896,"children":1897},{},[1898],{"type":63,"value":1899},"Stop and explain that this public skill does not manage authentication.",{"type":57,"tag":97,"props":1901,"children":1902},{},[1903],{"type":63,"value":1904},"Ask the user to use an authenticated AI-Q skill or configure their backend for this public local workflow.",{"type":57,"tag":97,"props":1906,"children":1907},{},[1908,1910,1915],{"type":63,"value":1909},"Rerun ",{"type":57,"tag":79,"props":1911,"children":1913},{"className":1912},[],[1914],{"type":63,"value":227},{"type":63,"value":1916}," and the original query only after the authentication boundary is resolved.",{"type":57,"tag":262,"props":1918,"children":1920},{"id":1919},"issue-health-succeeds-but-research-routes-fail",[1921],{"type":63,"value":1922},"Issue: Health succeeds but research routes fail",{"type":57,"tag":73,"props":1924,"children":1925},{},[1926],{"type":57,"tag":840,"props":1927,"children":1928},{},[1929],{"type":63,"value":1689},{"type":57,"tag":93,"props":1931,"children":1932},{},[1933,1943],{"type":57,"tag":97,"props":1934,"children":1935},{},[1936,1941],{"type":57,"tag":79,"props":1937,"children":1939},{"className":1938},[],[1940],{"type":63,"value":227},{"type":63,"value":1942}," returns successfully.",{"type":57,"tag":97,"props":1944,"children":1945},{},[1946,1951,1952,1957],{"type":57,"tag":79,"props":1947,"children":1949},{"className":1948},[],[1950],{"type":63,"value":422},{"type":63,"value":813},{"type":57,"tag":79,"props":1953,"children":1955},{"className":1954},[],[1956],{"type":63,"value":429},{"type":63,"value":1958},", or polling commands fail.",{"type":57,"tag":73,"props":1960,"children":1961},{},[1962],{"type":57,"tag":840,"props":1963,"children":1964},{},[1965],{"type":63,"value":1722},{"type":57,"tag":93,"props":1967,"children":1968},{},[1969,1974,1979],{"type":57,"tag":97,"props":1970,"children":1971},{},[1972],{"type":63,"value":1973},"The backend is not using an API-enabled AI-Q config.",{"type":57,"tag":97,"props":1975,"children":1976},{},[1977],{"type":63,"value":1978},"The async job registry is not available in the selected backend.",{"type":57,"tag":97,"props":1980,"children":1981},{},[1982],{"type":63,"value":1983},"The backend version is incompatible with this skill.",{"type":57,"tag":73,"props":1985,"children":1986},{},[1987],{"type":57,"tag":840,"props":1988,"children":1989},{},[1990],{"type":63,"value":1748},{"type":57,"tag":209,"props":1992,"children":1993},{},[1994,2026,2037],{"type":57,"tag":97,"props":1995,"children":1996},{},[1997,1999],{"type":63,"value":1998},"Run:\n",{"type":57,"tag":281,"props":2000,"children":2002},{"className":283,"code":2001,"language":51,"meta":285,"style":285},"python3 $SKILL_DIR\u002Fscripts\u002Faiq.py agents\n",[2003],{"type":57,"tag":79,"props":2004,"children":2005},{"__ignoreMap":285},[2006],{"type":57,"tag":291,"props":2007,"children":2008},{"class":293,"line":294},[2009,2013,2017,2021],{"type":57,"tag":291,"props":2010,"children":2011},{"style":298},[2012],{"type":63,"value":158},{"type":57,"tag":291,"props":2014,"children":2015},{"style":303},[2016],{"type":63,"value":306},{"type":57,"tag":291,"props":2018,"children":2019},{"style":309},[2020],{"type":63,"value":312},{"type":57,"tag":291,"props":2022,"children":2023},{"style":309},[2024],{"type":63,"value":2025}," agents\n",{"type":57,"tag":97,"props":2027,"children":2028},{},[2029,2031,2036],{"type":63,"value":2030},"If agents are unavailable, report the compatibility failure and offer to run ",{"type":57,"tag":79,"props":2032,"children":2034},{"className":2033},[],[2035],{"type":63,"value":132},{"type":63,"value":438},{"type":57,"tag":97,"props":2038,"children":2039},{},[2040],{"type":63,"value":2041},"Confirm the deployed Blueprint version is compatible with skill version 2.1.0.",{"type":57,"tag":262,"props":2043,"children":2045},{"id":2044},"issue-job-is-interrupted-or-appears-stuck",[2046],{"type":63,"value":2047},"Issue: Job is interrupted or appears stuck",{"type":57,"tag":73,"props":2049,"children":2050},{},[2051],{"type":57,"tag":840,"props":2052,"children":2053},{},[2054],{"type":63,"value":1689},{"type":57,"tag":93,"props":2056,"children":2057},{},[2058,2063,2075],{"type":57,"tag":97,"props":2059,"children":2060},{},[2061],{"type":63,"value":2062},"Local polling is interrupted.",{"type":57,"tag":97,"props":2064,"children":2065},{},[2066,2068,2074],{"type":63,"value":2067},"The job keeps showing ",{"type":57,"tag":79,"props":2069,"children":2071},{"className":2070},[],[2072],{"type":63,"value":2073},"running",{"type":63,"value":86},{"type":57,"tag":97,"props":2076,"children":2077},{},[2078,2080,2085,2087,2093],{"type":63,"value":2079},"Poll output shows ",{"type":57,"tag":79,"props":2081,"children":2083},{"className":2082},[],[2084],{"type":63,"value":2073},{"type":63,"value":2086},", but a report is returned or cancel says the job is already ",{"type":57,"tag":79,"props":2088,"children":2090},{"className":2089},[],[2091],{"type":63,"value":2092},"success",{"type":63,"value":86},{"type":57,"tag":73,"props":2095,"children":2096},{},[2097],{"type":57,"tag":840,"props":2098,"children":2099},{},[2100],{"type":63,"value":1722},{"type":57,"tag":93,"props":2102,"children":2103},{},[2104,2109],{"type":57,"tag":97,"props":2105,"children":2106},{},[2107],{"type":63,"value":2108},"Deep research is asynchronous and continues server-side.",{"type":57,"tag":97,"props":2110,"children":2111},{},[2112],{"type":63,"value":2113},"Local polling output can lag behind terminal server state.",{"type":57,"tag":73,"props":2115,"children":2116},{},[2117],{"type":57,"tag":840,"props":2118,"children":2119},{},[2120],{"type":63,"value":1748},{"type":57,"tag":209,"props":2122,"children":2123},{},[2124,2171,2232],{"type":57,"tag":97,"props":2125,"children":2126},{},[2127,2129],{"type":63,"value":2128},"Check current state:\n",{"type":57,"tag":281,"props":2130,"children":2132},{"className":283,"code":2131,"language":51,"meta":285,"style":285},"python3 $SKILL_DIR\u002Fscripts\u002Faiq.py status \u003CJOB_ID>\n",[2133],{"type":57,"tag":79,"props":2134,"children":2135},{"__ignoreMap":285},[2136],{"type":57,"tag":291,"props":2137,"children":2138},{"class":293,"line":294},[2139,2143,2147,2151,2155,2159,2163,2167],{"type":57,"tag":291,"props":2140,"children":2141},{"style":298},[2142],{"type":63,"value":158},{"type":57,"tag":291,"props":2144,"children":2145},{"style":303},[2146],{"type":63,"value":306},{"type":57,"tag":291,"props":2148,"children":2149},{"style":309},[2150],{"type":63,"value":312},{"type":57,"tag":291,"props":2152,"children":2153},{"style":309},[2154],{"type":63,"value":670},{"type":57,"tag":291,"props":2156,"children":2157},{"style":498},[2158],{"type":63,"value":607},{"type":57,"tag":291,"props":2160,"children":2161},{"style":309},[2162],{"type":63,"value":612},{"type":57,"tag":291,"props":2164,"children":2165},{"style":303},[2166],{"type":63,"value":617},{"type":57,"tag":291,"props":2168,"children":2169},{"style":498},[2170],{"type":63,"value":622},{"type":57,"tag":97,"props":2172,"children":2173},{},[2174,2175,2181,2182,2188,2190],{"type":63,"value":327},{"type":57,"tag":79,"props":2176,"children":2178},{"className":2177},[],[2179],{"type":63,"value":2180},"has_report: true",{"type":63,"value":397},{"type":57,"tag":79,"props":2183,"children":2185},{"className":2184},[],[2186],{"type":63,"value":2187},"job_status.status: success",{"type":63,"value":2189},", fetch the report:\n",{"type":57,"tag":281,"props":2191,"children":2193},{"className":283,"code":2192,"language":51,"meta":285,"style":285},"python3 $SKILL_DIR\u002Fscripts\u002Faiq.py report \u003CJOB_ID>\n",[2194],{"type":57,"tag":79,"props":2195,"children":2196},{"__ignoreMap":285},[2197],{"type":57,"tag":291,"props":2198,"children":2199},{"class":293,"line":294},[2200,2204,2208,2212,2216,2220,2224,2228],{"type":57,"tag":291,"props":2201,"children":2202},{"style":298},[2203],{"type":63,"value":158},{"type":57,"tag":291,"props":2205,"children":2206},{"style":303},[2207],{"type":63,"value":306},{"type":57,"tag":291,"props":2209,"children":2210},{"style":309},[2211],{"type":63,"value":312},{"type":57,"tag":291,"props":2213,"children":2214},{"style":309},[2215],{"type":63,"value":707},{"type":57,"tag":291,"props":2217,"children":2218},{"style":498},[2219],{"type":63,"value":607},{"type":57,"tag":291,"props":2221,"children":2222},{"style":309},[2223],{"type":63,"value":612},{"type":57,"tag":291,"props":2225,"children":2226},{"style":303},[2227],{"type":63,"value":617},{"type":57,"tag":291,"props":2229,"children":2230},{"style":498},[2231],{"type":63,"value":622},{"type":57,"tag":97,"props":2233,"children":2234},{},[2235,2237],{"type":63,"value":2236},"If the job is still running, continue polling:\n",{"type":57,"tag":281,"props":2238,"children":2239},{"className":283,"code":578,"language":51,"meta":285,"style":285},[2240],{"type":57,"tag":79,"props":2241,"children":2242},{"__ignoreMap":285},[2243],{"type":57,"tag":291,"props":2244,"children":2245},{"class":293,"line":294},[2246,2250,2254,2258,2262,2266,2270,2274],{"type":57,"tag":291,"props":2247,"children":2248},{"style":298},[2249],{"type":63,"value":158},{"type":57,"tag":291,"props":2251,"children":2252},{"style":303},[2253],{"type":63,"value":306},{"type":57,"tag":291,"props":2255,"children":2256},{"style":309},[2257],{"type":63,"value":312},{"type":57,"tag":291,"props":2259,"children":2260},{"style":309},[2261],{"type":63,"value":602},{"type":57,"tag":291,"props":2263,"children":2264},{"style":498},[2265],{"type":63,"value":607},{"type":57,"tag":291,"props":2267,"children":2268},{"style":309},[2269],{"type":63,"value":612},{"type":57,"tag":291,"props":2271,"children":2272},{"style":303},[2273],{"type":63,"value":617},{"type":57,"tag":291,"props":2275,"children":2276},{"style":498},[2277],{"type":63,"value":622},{"type":57,"tag":2279,"props":2280,"children":2281},"style",{},[2282],{"type":63,"value":2283},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":2285,"total":2404},[2286,2304,2320,2332,2352,2374,2392],{"slug":2287,"name":2287,"fn":2288,"description":2289,"org":2290,"tags":2291,"stars":19,"repoUrl":20,"updatedAt":21},"accessibility-and-inclusive-visualization","make data visualizations accessible","Make data visualizations accessible and inclusive. Use when the user needs chart or diagram accessibility guidance, text alternatives for complex visuals, color and contrast review, keyboard support, reduced-motion behavior for animation or parallax, or an accessibility QA workflow for exported figures, UML-like diagrams, and dashboards.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2292,2295,2298,2301],{"name":2293,"slug":2294,"type":15},"Accessibility","accessibility",{"name":2296,"slug":2297,"type":15},"Charts","charts",{"name":2299,"slug":2300,"type":15},"Data Visualization","data-visualization",{"name":2302,"slug":2303,"type":15},"Design","design",{"slug":2305,"name":2305,"fn":2306,"description":2307,"org":2308,"tags":2309,"stars":19,"repoUrl":20,"updatedAt":2319},"agent-browser","automate browser interactions for agents","Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2310,2313,2316],{"name":2311,"slug":2312,"type":15},"Agents","agents",{"name":2314,"slug":2315,"type":15},"Browser Automation","browser-automation",{"name":2317,"slug":2318,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":2321,"name":2321,"fn":2322,"description":2323,"org":2324,"tags":2325,"stars":19,"repoUrl":20,"updatedAt":2331},"agent-browser-verify","verify dev server output with automated browser","Automated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass\u002Ffail before continuing.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2326,2327,2330],{"name":2314,"slug":2315,"type":15},{"name":2328,"slug":2329,"type":15},"Local Development","local-development",{"name":2317,"slug":2318,"type":15},"2026-04-06T18:41:17.526867",{"slug":2333,"name":2333,"fn":2334,"description":2335,"org":2336,"tags":2337,"stars":19,"repoUrl":20,"updatedAt":2351},"agents-sdk","build AI agents on Cloudflare Workers","Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2338,2339,2342,2345,2348],{"name":2311,"slug":2312,"type":15},{"name":2340,"slug":2341,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":2343,"slug":2344,"type":15},"SDK","sdk",{"name":2346,"slug":2347,"type":15},"Serverless","serverless",{"name":2349,"slug":2350,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":2353,"name":2353,"fn":2354,"description":2355,"org":2356,"tags":2357,"stars":19,"repoUrl":20,"updatedAt":2373},"ai-elements","build chat UIs with AI Elements","AI Elements component library guidance — pre-built React components for AI interfaces built on shadcn\u002Fui. Use when building chat UIs, message displays, tool call rendering, streaming responses, reasoning panels, or any AI-native interface with the AI SDK.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2358,2361,2364,2367,2370],{"name":2359,"slug":2360,"type":15},"Frontend","frontend",{"name":2362,"slug":2363,"type":15},"React","react",{"name":2365,"slug":2366,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":2368,"slug":2369,"type":15},"UI Components","ui-components",{"name":2371,"slug":2372,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":2375,"name":2375,"fn":2376,"description":2377,"org":2378,"tags":2379,"stars":19,"repoUrl":20,"updatedAt":2391},"ai-gateway","configure Vercel AI Gateway","Vercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2380,2381,2384,2387,2390],{"name":17,"slug":18,"type":15},{"name":2382,"slug":2383,"type":15},"Cost Optimization","cost-optimization",{"name":2385,"slug":2386,"type":15},"LLM","llm",{"name":2388,"slug":2389,"type":15},"Performance","performance",{"name":2371,"slug":2372,"type":15},"2026-04-06T18:40:44.377464",{"slug":2393,"name":2393,"fn":2394,"description":2395,"org":2396,"tags":2397,"stars":19,"repoUrl":20,"updatedAt":2403},"ai-generation-persistence","implement persistence patterns for AI generations","AI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2398,2399,2402],{"name":2382,"slug":2383,"type":15},{"name":2400,"slug":2401,"type":15},"Database","database",{"name":2385,"slug":2386,"type":15},"2026-04-06T18:41:08.513425",600,{"items":2406,"total":2602},[2407,2428,2451,2468,2484,2501,2520,2532,2546,2559,2571,2586],{"slug":2408,"name":2408,"fn":2409,"description":2410,"org":2411,"tags":2412,"stars":2425,"repoUrl":2426,"updatedAt":2427},"prior-auth-packet-builder","build healthcare prior authorization packets","Build a concise prior authorization packet from local case files and payer policy docs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2413,2416,2419,2422],{"name":2414,"slug":2415,"type":15},"Documents","documents",{"name":2417,"slug":2418,"type":15},"Healthcare","healthcare",{"name":2420,"slug":2421,"type":15},"Insurance","insurance",{"name":2423,"slug":2424,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":2429,"name":2429,"fn":2430,"description":2431,"org":2432,"tags":2433,"stars":2448,"repoUrl":2449,"updatedAt":2450},"aspnet-core","build ASP.NET Core web applications","Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2434,2437,2439,2442,2445],{"name":2435,"slug":2436,"type":15},".NET","dotnet",{"name":2438,"slug":2429,"type":15},"ASP.NET Core",{"name":2440,"slug":2441,"type":15},"Blazor","blazor",{"name":2443,"slug":2444,"type":15},"C#","csharp",{"name":2446,"slug":2447,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":2452,"name":2452,"fn":2453,"description":2454,"org":2455,"tags":2456,"stars":2448,"repoUrl":2449,"updatedAt":2467},"chatgpt-apps","build ChatGPT Apps SDK applications","Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2457,2460,2463,2466],{"name":2458,"slug":2459,"type":15},"Apps SDK","apps-sdk",{"name":2461,"slug":2462,"type":15},"ChatGPT","chatgpt",{"name":2464,"slug":2465,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":2469,"name":2469,"fn":2470,"description":2471,"org":2472,"tags":2473,"stars":2448,"repoUrl":2449,"updatedAt":2483},"cli-creator","build CLIs from API docs","Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read\u002Fwrite commands, return stable JSON, manage auth, and pair with a companion skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2474,2477,2480],{"name":2475,"slug":2476,"type":15},"API Development","api-development",{"name":2478,"slug":2479,"type":15},"CLI","cli",{"name":2481,"slug":2482,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":2485,"name":2485,"fn":2486,"description":2487,"org":2488,"tags":2489,"stars":2448,"repoUrl":2449,"updatedAt":2500},"cloudflare-deploy","deploy projects to Cloudflare","Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2490,2493,2496,2497],{"name":2491,"slug":2492,"type":15},"Cloudflare","cloudflare",{"name":2494,"slug":2495,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":2340,"slug":2341,"type":15},{"name":2498,"slug":2499,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":2502,"name":2502,"fn":2503,"description":2504,"org":2505,"tags":2506,"stars":2448,"repoUrl":2449,"updatedAt":2519},"define-goal","define and set measurable project goals","Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refinement only; it does not manage durable snapshots, decision logs, or long-running execution artifacts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2507,2510,2513,2516],{"name":2508,"slug":2509,"type":15},"Productivity","productivity",{"name":2511,"slug":2512,"type":15},"Project Management","project-management",{"name":2514,"slug":2515,"type":15},"Strategy","strategy",{"name":2517,"slug":2518,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":2521,"name":2521,"fn":2522,"description":2523,"org":2524,"tags":2525,"stars":2448,"repoUrl":2449,"updatedAt":2531},"figma","translate Figma designs into code","Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2526,2527,2529,2530],{"name":2302,"slug":2303,"type":15},{"name":2528,"slug":2521,"type":15},"Figma",{"name":2359,"slug":2360,"type":15},{"name":2464,"slug":2465,"type":15},"2026-04-12T05:06:47.939943",{"slug":2533,"name":2533,"fn":2534,"description":2535,"org":2536,"tags":2537,"stars":2448,"repoUrl":2449,"updatedAt":2545},"figma-code-connect-components","connect Figma designs to code components","Connects Figma design components to code components using Code Connect mapping tools. Use when user says \"code connect\", \"connect this component to code\", \"map this component\", \"link component to code\", \"create code connect mapping\", or wants to establish mappings between Figma designs and code implementations. For canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2538,2539,2542,2543,2544],{"name":2302,"slug":2303,"type":15},{"name":2540,"slug":2541,"type":15},"Design System","design-system",{"name":2528,"slug":2521,"type":15},{"name":2359,"slug":2360,"type":15},{"name":2368,"slug":2369,"type":15},"2026-05-10T05:59:52.971881",{"slug":2547,"name":2547,"fn":2548,"description":2549,"org":2550,"tags":2551,"stars":2448,"repoUrl":2449,"updatedAt":2558},"figma-create-design-system-rules","generate design system rules from Figma","Generates custom design system rules for the user's codebase. Use when user says \"create design system rules\", \"generate rules for my project\", \"set up design rules\", \"customize design system guidelines\", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2552,2553,2554,2556,2557],{"name":2302,"slug":2303,"type":15},{"name":2540,"slug":2541,"type":15},{"name":1633,"slug":2555,"type":15},"documentation",{"name":2528,"slug":2521,"type":15},{"name":2359,"slug":2360,"type":15},"2026-05-16T06:07:47.821474",{"slug":2560,"name":2560,"fn":2561,"description":2562,"org":2563,"tags":2564,"stars":2448,"repoUrl":2449,"updatedAt":2570},"figma-implement-design","translate Figma designs into application code","Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions \"implement design\", \"generate code\", \"implement component\", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2565,2566,2567,2568,2569],{"name":2302,"slug":2303,"type":15},{"name":2528,"slug":2521,"type":15},{"name":2359,"slug":2360,"type":15},{"name":2368,"slug":2369,"type":15},{"name":2446,"slug":2447,"type":15},"2026-05-16T06:07:40.583615",{"slug":2572,"name":2572,"fn":2573,"description":2574,"org":2575,"tags":2576,"stars":2448,"repoUrl":2449,"updatedAt":2585},"hatch-pet","create animated pets for Codex","Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2577,2580,2581,2584],{"name":2578,"slug":2579,"type":15},"Animation","animation",{"name":2481,"slug":2482,"type":15},{"name":2582,"slug":2583,"type":15},"Creative","creative",{"name":2302,"slug":2303,"type":15},"2026-05-02T05:31:48.48485",{"slug":2587,"name":2587,"fn":2588,"description":2589,"org":2590,"tags":2591,"stars":2448,"repoUrl":2449,"updatedAt":2601},"imagegen","generate and edit raster images","Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG\u002Fvector\u002Fcode-native assets, extending an established icon or logo system, or building the visual directly in HTML\u002FCSS\u002Fcanvas.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2592,2593,2594,2597,2600],{"name":2582,"slug":2583,"type":15},{"name":2302,"slug":2303,"type":15},{"name":2595,"slug":2596,"type":15},"Image Generation","image-generation",{"name":2598,"slug":2599,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675]