[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-azure-agentops-agent":3,"mdc-u571xw-key":38,"related-org-azure-agentops-agent":910,"related-repo-azure-agentops-agent":1089},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":27,"repoUrl":28,"updatedAt":29,"license":30,"forks":31,"topics":32,"repo":33,"sourceUrl":36,"mdContent":37},"agentops-agent","diagnose agent performance with AgentOps","AgentOps Doctor - surface release-readiness findings, regressions, latency spikes, error rates, and safety hits across AgentOps eval history, Azure Monitor traces, and Foundry control plane.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"azure","Azure (Microsoft)","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fazure.png","Azure",[13,17,18,21,24],{"name":14,"slug":15,"type":16},"Observability","observability","tag",{"name":11,"slug":8,"type":16},{"name":19,"slug":20,"type":16},"Evals","evals",{"name":22,"slug":23,"type":16},"Agents","agents",{"name":25,"slug":26,"type":16},"Debugging","debugging",10,"https:\u002F\u002Fgithub.com\u002FAzure\u002Fagentops","2026-07-12T08:19:05.564606",null,7,[],{"repoUrl":28,"stars":27,"forks":31,"topics":34,"description":35},[],"AgentOps Accelerator is an open source framework and CLI for adding continuous evaluation and observability to enterprise AI agents. It standardizes evaluation patterns, automates assessments in CI\u002FCD workflows, and generates structured signals that help teams monitor, control, and safely operate agentic systems at scale.","https:\u002F\u002Fgithub.com\u002FAzure\u002Fagentops\u002Ftree\u002FHEAD\u002Fplugins\u002Fagentops\u002Fskills\u002Fagentops-agent","---\nname: agentops-agent\ndescription: AgentOps Doctor - surface release-readiness findings, regressions, latency spikes, error rates, and safety hits across AgentOps eval history, Azure Monitor traces, and Foundry control plane.\n---\n\n# `agentops-agent` - Doctor skill\n\nUse this skill when the user asks any of:\n\n- *\"Are my agents healthy in production?\"*\n- *\"Run the doctor\"*\n- *\"Anything regressed in our last evals?\"*\n- *\"Show latency \u002F error spikes from Azure Monitor\"*\n- *\"Open the AgentOps doctor report\"*\n\nThis skill is the front door to `agentops doctor` and the\n`agentops agent serve` Copilot Extension. It does **not** invent\nfindings - it shells out to the CLI which reads real data from:\n\n1. `.agentops\u002Fresults\u002F*\u002Fresults.json` (eval history)\n2. Application Insights traces emitted by Foundry agents\n3. Foundry control plane (`azure-ai-projects`)\n\nDoctor and Cockpit are read-only readiness tools. They help answer \"can we ship\nit, and where is the proof?\" They do not create, deploy, mutate, or delete\nFoundry or Azure resources.\n\n## Workflow\n\n### 1. Validate the workspace\n\nLook for `.agentops\u002Fagent.yaml`. If absent, copy the template:\n\n```bash\nmkdir -p .agentops\ncp $(python -c \"import agentops, os, pathlib;\nprint(pathlib.Path(agentops.__file__).parent \u002F 'templates' \u002F 'agent.yaml')\") .agentops\u002Fagent.yaml\n```\n\nEdit `app_insights_resource_id` and `project_endpoint_env` if the user\nwants the Azure Monitor \u002F Foundry sources to be live. Without those\nvalues the sources skip gracefully.\n\n### 2. Run the analyzer\n\n```bash\nagentops doctor --severity-fail critical\n```\n\nThe command writes `.agentops\u002Fagent\u002Freport.md`. Exit codes:\n\n- `0` - no findings at or above the configured severity floor\n- `2` - at least one finding meets the severity floor (use this in CI)\n- `1` - runtime \u002F configuration error\n\n### 3. Read and summarize\n\nOpen `.agentops\u002Fagent\u002Freport.md`. The report has:\n\n- **Verdict banner** - overall pass \u002F warning \u002F critical\n- **Summary** - counts by severity\n- **Sources** - which sources ran, which were skipped and why\n- **Findings** - sorted by severity, each with a recommendation\n- **Recent runs** - appendix of the last `lookback_runs` evals\n\nWhen summarising for the user, lead with the verdict, then the top\n3 findings, each with the recommendation. Always cite the finding `id`\nso the user can grep them later.\n\nGovernance findings use the `governance.*` prefix. They are read-only checks for\nASSERT, ACS, and red-team evidence paths declared in `agentops.yaml` or\ndiscovered in the workspace. If governance is not configured, Doctor should stay\nsilent; if a configured artifact is missing, invalid, or ACS coverage is\npartial, route the user to the `agentops-governance` skill.\n\n### 4. Drive remediation, do not invent it\n\nFor each finding the report includes a `Recommendation`. Follow it\nverbatim - for example, if the finding says \"compare the latest run\nagainst the baseline runs in `.agentops\u002Fresults\u002F`\", actually open\nthose folders.\n\n## Local cockpit (`agentops cockpit`)\n\nFor a workspace-level operations view the user can open a local\nCockpit:\n\n```bash\npip install \"agentops-accelerator[agent] @ git+https:\u002F\u002Fgithub.com\u002FAzure\u002Fagentops.git@main\"\nagentops cockpit\n# → http:\u002F\u002F127.0.0.1:8090\n```\n\nCockpit reads local AgentOps artifacts first: `.agentops\u002Fresults\u002F`,\ngenerated reports, `.agentops\u002Fagent\u002Fhistory.jsonl`, and workflow files.\nWhen a Foundry project is configured, it also resolves telemetry\nreadiness and links to the matching Foundry and Azure Monitor views.\nIt is read-only and bound to localhost.\n\nWhen telemetry is enabled the analyzer **also** emits OpenTelemetry\nspans for the Doctor run with per-severity \u002F per-category counters,\nuseful for long-term retention in App Insights or any OTel backend.\nResolution order:\n\n1. `APPLICATIONINSIGHTS_CONNECTION_STRING` (or the AgentOps-prefixed\n   variant) - explicit user configuration always wins.\n2. `AGENTOPS_OTLP_ENDPOINT` - generic OTLP\u002FHTTP exporter.\n3. **Auto-discovery** - when `AZURE_AI_FOUNDRY_PROJECT_ENDPOINT` is\n   set but no explicit env var is, AgentOps asks the Foundry project\n   for the connection string of the Application Insights resource\n   attached to it. Zero configuration when the user is already on\n   Foundry.\n\n## Copilot Extension server\n\nIf the user wants the Doctor inside Copilot Chat, they can:\n\n```bash\npip install \"agentops-accelerator[agent] @ git+https:\u002F\u002Fgithub.com\u002FAzure\u002Fagentops.git@main\"\nagentops agent serve --no-verify       # local dev\n```\n\nFor production, point them at:\n\n- `src\u002Fagentops\u002Ftemplates\u002Fagent-server\u002FDockerfile`\n- `src\u002Fagentops\u002Ftemplates\u002Fagent-server\u002Fmain.bicep`\n- `src\u002Fagentops\u002Ftemplates\u002Fagent-server\u002FREADME.md`\n\nThese are the deploy scaffold for hosting the Doctor as a Copilot\nExtension on Azure Container Apps.\n\n## Guardrails\n\n- Do **not** fabricate findings, metric values, or recommendations.\n- Do **not** invent CLI flags. The contract is exactly:\n  - `agentops doctor [--workspace] [--config] [--out] [--lookback-days] [--severity-fail]`\n  - `agentops agent serve [--host] [--port] [--config] [--no-verify] [--workers]`\n  - `agentops cockpit [--host] [--port] [--workspace]`\n- If a source is `skipped` or `error`, surface that as the *first*\n  thing in the user-facing summary so they know the analyzer ran with\n  partial data.\n- Never suggest disabling content-safety checks - recommend filtering\n  the offending row or tightening the system prompt instead.\n- Never suggest that AgentOps executes ASSERT, applies ACS controls, or runs\n  red-team campaigns. It only records evidence and readiness findings.\n",{"data":39,"body":40},{"name":4,"description":6},{"type":41,"children":42},"root",[43,58,64,110,139,172,177,184,191,204,296,317,323,353,366,402,408,420,481,494,523,529,550,563,568,623,643,655,698,704,709,766,771,801,806,812,904],{"type":44,"tag":45,"props":46,"children":48},"element","h1",{"id":47},"agentops-agent-doctor-skill",[49,56],{"type":44,"tag":50,"props":51,"children":53},"code",{"className":52},[],[54],{"type":55,"value":4},"text",{"type":55,"value":57}," - Doctor skill",{"type":44,"tag":59,"props":60,"children":61},"p",{},[62],{"type":55,"value":63},"Use this skill when the user asks any of:",{"type":44,"tag":65,"props":66,"children":67},"ul",{},[68,78,86,94,102],{"type":44,"tag":69,"props":70,"children":71},"li",{},[72],{"type":44,"tag":73,"props":74,"children":75},"em",{},[76],{"type":55,"value":77},"\"Are my agents healthy in production?\"",{"type":44,"tag":69,"props":79,"children":80},{},[81],{"type":44,"tag":73,"props":82,"children":83},{},[84],{"type":55,"value":85},"\"Run the doctor\"",{"type":44,"tag":69,"props":87,"children":88},{},[89],{"type":44,"tag":73,"props":90,"children":91},{},[92],{"type":55,"value":93},"\"Anything regressed in our last evals?\"",{"type":44,"tag":69,"props":95,"children":96},{},[97],{"type":44,"tag":73,"props":98,"children":99},{},[100],{"type":55,"value":101},"\"Show latency \u002F error spikes from Azure Monitor\"",{"type":44,"tag":69,"props":103,"children":104},{},[105],{"type":44,"tag":73,"props":106,"children":107},{},[108],{"type":55,"value":109},"\"Open the AgentOps doctor report\"",{"type":44,"tag":59,"props":111,"children":112},{},[113,115,121,123,129,131,137],{"type":55,"value":114},"This skill is the front door to ",{"type":44,"tag":50,"props":116,"children":118},{"className":117},[],[119],{"type":55,"value":120},"agentops doctor",{"type":55,"value":122}," and the\n",{"type":44,"tag":50,"props":124,"children":126},{"className":125},[],[127],{"type":55,"value":128},"agentops agent serve",{"type":55,"value":130}," Copilot Extension. It does ",{"type":44,"tag":132,"props":133,"children":134},"strong",{},[135],{"type":55,"value":136},"not",{"type":55,"value":138}," invent\nfindings - it shells out to the CLI which reads real data from:",{"type":44,"tag":140,"props":141,"children":142},"ol",{},[143,154,159],{"type":44,"tag":69,"props":144,"children":145},{},[146,152],{"type":44,"tag":50,"props":147,"children":149},{"className":148},[],[150],{"type":55,"value":151},".agentops\u002Fresults\u002F*\u002Fresults.json",{"type":55,"value":153}," (eval history)",{"type":44,"tag":69,"props":155,"children":156},{},[157],{"type":55,"value":158},"Application Insights traces emitted by Foundry agents",{"type":44,"tag":69,"props":160,"children":161},{},[162,164,170],{"type":55,"value":163},"Foundry control plane (",{"type":44,"tag":50,"props":165,"children":167},{"className":166},[],[168],{"type":55,"value":169},"azure-ai-projects",{"type":55,"value":171},")",{"type":44,"tag":59,"props":173,"children":174},{},[175],{"type":55,"value":176},"Doctor and Cockpit are read-only readiness tools. They help answer \"can we ship\nit, and where is the proof?\" They do not create, deploy, mutate, or delete\nFoundry or Azure resources.",{"type":44,"tag":178,"props":179,"children":181},"h2",{"id":180},"workflow",[182],{"type":55,"value":183},"Workflow",{"type":44,"tag":185,"props":186,"children":188},"h3",{"id":187},"_1-validate-the-workspace",[189],{"type":55,"value":190},"1. Validate the workspace",{"type":44,"tag":59,"props":192,"children":193},{},[194,196,202],{"type":55,"value":195},"Look for ",{"type":44,"tag":50,"props":197,"children":199},{"className":198},[],[200],{"type":55,"value":201},".agentops\u002Fagent.yaml",{"type":55,"value":203},". If absent, copy the template:",{"type":44,"tag":205,"props":206,"children":211},"pre",{"className":207,"code":208,"language":209,"meta":210,"style":210},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","mkdir -p .agentops\ncp $(python -c \"import agentops, os, pathlib;\nprint(pathlib.Path(agentops.__file__).parent \u002F 'templates' \u002F 'agent.yaml')\") .agentops\u002Fagent.yaml\n","bash","",[212],{"type":44,"tag":50,"props":213,"children":214},{"__ignoreMap":210},[215,238,273],{"type":44,"tag":216,"props":217,"children":220},"span",{"class":218,"line":219},"line",1,[221,227,233],{"type":44,"tag":216,"props":222,"children":224},{"style":223},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[225],{"type":55,"value":226},"mkdir",{"type":44,"tag":216,"props":228,"children":230},{"style":229},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[231],{"type":55,"value":232}," -p",{"type":44,"tag":216,"props":234,"children":235},{"style":229},[236],{"type":55,"value":237}," .agentops\n",{"type":44,"tag":216,"props":239,"children":241},{"class":218,"line":240},2,[242,247,253,258,263,268],{"type":44,"tag":216,"props":243,"children":244},{"style":223},[245],{"type":55,"value":246},"cp",{"type":44,"tag":216,"props":248,"children":250},{"style":249},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[251],{"type":55,"value":252}," $(",{"type":44,"tag":216,"props":254,"children":255},{"style":223},[256],{"type":55,"value":257},"python",{"type":44,"tag":216,"props":259,"children":260},{"style":229},[261],{"type":55,"value":262}," -c",{"type":44,"tag":216,"props":264,"children":265},{"style":249},[266],{"type":55,"value":267}," \"",{"type":44,"tag":216,"props":269,"children":270},{"style":229},[271],{"type":55,"value":272},"import agentops, os, pathlib;\n",{"type":44,"tag":216,"props":274,"children":276},{"class":218,"line":275},3,[277,282,287,291],{"type":44,"tag":216,"props":278,"children":279},{"style":229},[280],{"type":55,"value":281},"print(pathlib.Path(agentops.__file__).parent \u002F 'templates' \u002F 'agent.yaml')",{"type":44,"tag":216,"props":283,"children":284},{"style":249},[285],{"type":55,"value":286},"\"",{"type":44,"tag":216,"props":288,"children":289},{"style":249},[290],{"type":55,"value":171},{"type":44,"tag":216,"props":292,"children":293},{"style":229},[294],{"type":55,"value":295}," .agentops\u002Fagent.yaml\n",{"type":44,"tag":59,"props":297,"children":298},{},[299,301,307,309,315],{"type":55,"value":300},"Edit ",{"type":44,"tag":50,"props":302,"children":304},{"className":303},[],[305],{"type":55,"value":306},"app_insights_resource_id",{"type":55,"value":308}," and ",{"type":44,"tag":50,"props":310,"children":312},{"className":311},[],[313],{"type":55,"value":314},"project_endpoint_env",{"type":55,"value":316}," if the user\nwants the Azure Monitor \u002F Foundry sources to be live. Without those\nvalues the sources skip gracefully.",{"type":44,"tag":185,"props":318,"children":320},{"id":319},"_2-run-the-analyzer",[321],{"type":55,"value":322},"2. Run the analyzer",{"type":44,"tag":205,"props":324,"children":326},{"className":207,"code":325,"language":209,"meta":210,"style":210},"agentops doctor --severity-fail critical\n",[327],{"type":44,"tag":50,"props":328,"children":329},{"__ignoreMap":210},[330],{"type":44,"tag":216,"props":331,"children":332},{"class":218,"line":219},[333,338,343,348],{"type":44,"tag":216,"props":334,"children":335},{"style":223},[336],{"type":55,"value":337},"agentops",{"type":44,"tag":216,"props":339,"children":340},{"style":229},[341],{"type":55,"value":342}," doctor",{"type":44,"tag":216,"props":344,"children":345},{"style":229},[346],{"type":55,"value":347}," --severity-fail",{"type":44,"tag":216,"props":349,"children":350},{"style":229},[351],{"type":55,"value":352}," critical\n",{"type":44,"tag":59,"props":354,"children":355},{},[356,358,364],{"type":55,"value":357},"The command writes ",{"type":44,"tag":50,"props":359,"children":361},{"className":360},[],[362],{"type":55,"value":363},".agentops\u002Fagent\u002Freport.md",{"type":55,"value":365},". Exit codes:",{"type":44,"tag":65,"props":367,"children":368},{},[369,380,391],{"type":44,"tag":69,"props":370,"children":371},{},[372,378],{"type":44,"tag":50,"props":373,"children":375},{"className":374},[],[376],{"type":55,"value":377},"0",{"type":55,"value":379}," - no findings at or above the configured severity floor",{"type":44,"tag":69,"props":381,"children":382},{},[383,389],{"type":44,"tag":50,"props":384,"children":386},{"className":385},[],[387],{"type":55,"value":388},"2",{"type":55,"value":390}," - at least one finding meets the severity floor (use this in CI)",{"type":44,"tag":69,"props":392,"children":393},{},[394,400],{"type":44,"tag":50,"props":395,"children":397},{"className":396},[],[398],{"type":55,"value":399},"1",{"type":55,"value":401}," - runtime \u002F configuration error",{"type":44,"tag":185,"props":403,"children":405},{"id":404},"_3-read-and-summarize",[406],{"type":55,"value":407},"3. Read and summarize",{"type":44,"tag":59,"props":409,"children":410},{},[411,413,418],{"type":55,"value":412},"Open ",{"type":44,"tag":50,"props":414,"children":416},{"className":415},[],[417],{"type":55,"value":363},{"type":55,"value":419},". The report has:",{"type":44,"tag":65,"props":421,"children":422},{},[423,433,443,453,463],{"type":44,"tag":69,"props":424,"children":425},{},[426,431],{"type":44,"tag":132,"props":427,"children":428},{},[429],{"type":55,"value":430},"Verdict banner",{"type":55,"value":432}," - overall pass \u002F warning \u002F critical",{"type":44,"tag":69,"props":434,"children":435},{},[436,441],{"type":44,"tag":132,"props":437,"children":438},{},[439],{"type":55,"value":440},"Summary",{"type":55,"value":442}," - counts by severity",{"type":44,"tag":69,"props":444,"children":445},{},[446,451],{"type":44,"tag":132,"props":447,"children":448},{},[449],{"type":55,"value":450},"Sources",{"type":55,"value":452}," - which sources ran, which were skipped and why",{"type":44,"tag":69,"props":454,"children":455},{},[456,461],{"type":44,"tag":132,"props":457,"children":458},{},[459],{"type":55,"value":460},"Findings",{"type":55,"value":462}," - sorted by severity, each with a recommendation",{"type":44,"tag":69,"props":464,"children":465},{},[466,471,473,479],{"type":44,"tag":132,"props":467,"children":468},{},[469],{"type":55,"value":470},"Recent runs",{"type":55,"value":472}," - appendix of the last ",{"type":44,"tag":50,"props":474,"children":476},{"className":475},[],[477],{"type":55,"value":478},"lookback_runs",{"type":55,"value":480}," evals",{"type":44,"tag":59,"props":482,"children":483},{},[484,486,492],{"type":55,"value":485},"When summarising for the user, lead with the verdict, then the top\n3 findings, each with the recommendation. Always cite the finding ",{"type":44,"tag":50,"props":487,"children":489},{"className":488},[],[490],{"type":55,"value":491},"id",{"type":55,"value":493},"\nso the user can grep them later.",{"type":44,"tag":59,"props":495,"children":496},{},[497,499,505,507,513,515,521],{"type":55,"value":498},"Governance findings use the ",{"type":44,"tag":50,"props":500,"children":502},{"className":501},[],[503],{"type":55,"value":504},"governance.*",{"type":55,"value":506}," prefix. They are read-only checks for\nASSERT, ACS, and red-team evidence paths declared in ",{"type":44,"tag":50,"props":508,"children":510},{"className":509},[],[511],{"type":55,"value":512},"agentops.yaml",{"type":55,"value":514}," or\ndiscovered in the workspace. If governance is not configured, Doctor should stay\nsilent; if a configured artifact is missing, invalid, or ACS coverage is\npartial, route the user to the ",{"type":44,"tag":50,"props":516,"children":518},{"className":517},[],[519],{"type":55,"value":520},"agentops-governance",{"type":55,"value":522}," skill.",{"type":44,"tag":185,"props":524,"children":526},{"id":525},"_4-drive-remediation-do-not-invent-it",[527],{"type":55,"value":528},"4. Drive remediation, do not invent it",{"type":44,"tag":59,"props":530,"children":531},{},[532,534,540,542,548],{"type":55,"value":533},"For each finding the report includes a ",{"type":44,"tag":50,"props":535,"children":537},{"className":536},[],[538],{"type":55,"value":539},"Recommendation",{"type":55,"value":541},". Follow it\nverbatim - for example, if the finding says \"compare the latest run\nagainst the baseline runs in ",{"type":44,"tag":50,"props":543,"children":545},{"className":544},[],[546],{"type":55,"value":547},".agentops\u002Fresults\u002F",{"type":55,"value":549},"\", actually open\nthose folders.",{"type":44,"tag":178,"props":551,"children":553},{"id":552},"local-cockpit-agentops-cockpit",[554,556,562],{"type":55,"value":555},"Local cockpit (",{"type":44,"tag":50,"props":557,"children":559},{"className":558},[],[560],{"type":55,"value":561},"agentops cockpit",{"type":55,"value":171},{"type":44,"tag":59,"props":564,"children":565},{},[566],{"type":55,"value":567},"For a workspace-level operations view the user can open a local\nCockpit:",{"type":44,"tag":205,"props":569,"children":571},{"className":207,"code":570,"language":209,"meta":210,"style":210},"pip install \"agentops-accelerator[agent] @ git+https:\u002F\u002Fgithub.com\u002FAzure\u002Fagentops.git@main\"\nagentops cockpit\n# → http:\u002F\u002F127.0.0.1:8090\n",[572],{"type":44,"tag":50,"props":573,"children":574},{"__ignoreMap":210},[575,602,614],{"type":44,"tag":216,"props":576,"children":577},{"class":218,"line":219},[578,583,588,592,597],{"type":44,"tag":216,"props":579,"children":580},{"style":223},[581],{"type":55,"value":582},"pip",{"type":44,"tag":216,"props":584,"children":585},{"style":229},[586],{"type":55,"value":587}," install",{"type":44,"tag":216,"props":589,"children":590},{"style":249},[591],{"type":55,"value":267},{"type":44,"tag":216,"props":593,"children":594},{"style":229},[595],{"type":55,"value":596},"agentops-accelerator[agent] @ git+https:\u002F\u002Fgithub.com\u002FAzure\u002Fagentops.git@main",{"type":44,"tag":216,"props":598,"children":599},{"style":249},[600],{"type":55,"value":601},"\"\n",{"type":44,"tag":216,"props":603,"children":604},{"class":218,"line":240},[605,609],{"type":44,"tag":216,"props":606,"children":607},{"style":223},[608],{"type":55,"value":337},{"type":44,"tag":216,"props":610,"children":611},{"style":229},[612],{"type":55,"value":613}," cockpit\n",{"type":44,"tag":216,"props":615,"children":616},{"class":218,"line":275},[617],{"type":44,"tag":216,"props":618,"children":620},{"style":619},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[621],{"type":55,"value":622},"# → http:\u002F\u002F127.0.0.1:8090\n",{"type":44,"tag":59,"props":624,"children":625},{},[626,628,633,635,641],{"type":55,"value":627},"Cockpit reads local AgentOps artifacts first: ",{"type":44,"tag":50,"props":629,"children":631},{"className":630},[],[632],{"type":55,"value":547},{"type":55,"value":634},",\ngenerated reports, ",{"type":44,"tag":50,"props":636,"children":638},{"className":637},[],[639],{"type":55,"value":640},".agentops\u002Fagent\u002Fhistory.jsonl",{"type":55,"value":642},", and workflow files.\nWhen a Foundry project is configured, it also resolves telemetry\nreadiness and links to the matching Foundry and Azure Monitor views.\nIt is read-only and bound to localhost.",{"type":44,"tag":59,"props":644,"children":645},{},[646,648,653],{"type":55,"value":647},"When telemetry is enabled the analyzer ",{"type":44,"tag":132,"props":649,"children":650},{},[651],{"type":55,"value":652},"also",{"type":55,"value":654}," emits OpenTelemetry\nspans for the Doctor run with per-severity \u002F per-category counters,\nuseful for long-term retention in App Insights or any OTel backend.\nResolution order:",{"type":44,"tag":140,"props":656,"children":657},{},[658,669,680],{"type":44,"tag":69,"props":659,"children":660},{},[661,667],{"type":44,"tag":50,"props":662,"children":664},{"className":663},[],[665],{"type":55,"value":666},"APPLICATIONINSIGHTS_CONNECTION_STRING",{"type":55,"value":668}," (or the AgentOps-prefixed\nvariant) - explicit user configuration always wins.",{"type":44,"tag":69,"props":670,"children":671},{},[672,678],{"type":44,"tag":50,"props":673,"children":675},{"className":674},[],[676],{"type":55,"value":677},"AGENTOPS_OTLP_ENDPOINT",{"type":55,"value":679}," - generic OTLP\u002FHTTP exporter.",{"type":44,"tag":69,"props":681,"children":682},{},[683,688,690,696],{"type":44,"tag":132,"props":684,"children":685},{},[686],{"type":55,"value":687},"Auto-discovery",{"type":55,"value":689}," - when ",{"type":44,"tag":50,"props":691,"children":693},{"className":692},[],[694],{"type":55,"value":695},"AZURE_AI_FOUNDRY_PROJECT_ENDPOINT",{"type":55,"value":697}," is\nset but no explicit env var is, AgentOps asks the Foundry project\nfor the connection string of the Application Insights resource\nattached to it. Zero configuration when the user is already on\nFoundry.",{"type":44,"tag":178,"props":699,"children":701},{"id":700},"copilot-extension-server",[702],{"type":55,"value":703},"Copilot Extension server",{"type":44,"tag":59,"props":705,"children":706},{},[707],{"type":55,"value":708},"If the user wants the Doctor inside Copilot Chat, they can:",{"type":44,"tag":205,"props":710,"children":712},{"className":207,"code":711,"language":209,"meta":210,"style":210},"pip install \"agentops-accelerator[agent] @ git+https:\u002F\u002Fgithub.com\u002FAzure\u002Fagentops.git@main\"\nagentops agent serve --no-verify       # local dev\n",[713],{"type":44,"tag":50,"props":714,"children":715},{"__ignoreMap":210},[716,739],{"type":44,"tag":216,"props":717,"children":718},{"class":218,"line":219},[719,723,727,731,735],{"type":44,"tag":216,"props":720,"children":721},{"style":223},[722],{"type":55,"value":582},{"type":44,"tag":216,"props":724,"children":725},{"style":229},[726],{"type":55,"value":587},{"type":44,"tag":216,"props":728,"children":729},{"style":249},[730],{"type":55,"value":267},{"type":44,"tag":216,"props":732,"children":733},{"style":229},[734],{"type":55,"value":596},{"type":44,"tag":216,"props":736,"children":737},{"style":249},[738],{"type":55,"value":601},{"type":44,"tag":216,"props":740,"children":741},{"class":218,"line":240},[742,746,751,756,761],{"type":44,"tag":216,"props":743,"children":744},{"style":223},[745],{"type":55,"value":337},{"type":44,"tag":216,"props":747,"children":748},{"style":229},[749],{"type":55,"value":750}," agent",{"type":44,"tag":216,"props":752,"children":753},{"style":229},[754],{"type":55,"value":755}," serve",{"type":44,"tag":216,"props":757,"children":758},{"style":229},[759],{"type":55,"value":760}," --no-verify",{"type":44,"tag":216,"props":762,"children":763},{"style":619},[764],{"type":55,"value":765},"       # local dev\n",{"type":44,"tag":59,"props":767,"children":768},{},[769],{"type":55,"value":770},"For production, point them at:",{"type":44,"tag":65,"props":772,"children":773},{},[774,783,792],{"type":44,"tag":69,"props":775,"children":776},{},[777],{"type":44,"tag":50,"props":778,"children":780},{"className":779},[],[781],{"type":55,"value":782},"src\u002Fagentops\u002Ftemplates\u002Fagent-server\u002FDockerfile",{"type":44,"tag":69,"props":784,"children":785},{},[786],{"type":44,"tag":50,"props":787,"children":789},{"className":788},[],[790],{"type":55,"value":791},"src\u002Fagentops\u002Ftemplates\u002Fagent-server\u002Fmain.bicep",{"type":44,"tag":69,"props":793,"children":794},{},[795],{"type":44,"tag":50,"props":796,"children":798},{"className":797},[],[799],{"type":55,"value":800},"src\u002Fagentops\u002Ftemplates\u002Fagent-server\u002FREADME.md",{"type":44,"tag":59,"props":802,"children":803},{},[804],{"type":55,"value":805},"These are the deploy scaffold for hosting the Doctor as a Copilot\nExtension on Azure Container Apps.",{"type":44,"tag":178,"props":807,"children":809},{"id":808},"guardrails",[810],{"type":55,"value":811},"Guardrails",{"type":44,"tag":65,"props":813,"children":814},{},[815,826,866,894,899],{"type":44,"tag":69,"props":816,"children":817},{},[818,820,824],{"type":55,"value":819},"Do ",{"type":44,"tag":132,"props":821,"children":822},{},[823],{"type":55,"value":136},{"type":55,"value":825}," fabricate findings, metric values, or recommendations.",{"type":44,"tag":69,"props":827,"children":828},{},[829,830,834,836],{"type":55,"value":819},{"type":44,"tag":132,"props":831,"children":832},{},[833],{"type":55,"value":136},{"type":55,"value":835}," invent CLI flags. The contract is exactly:\n",{"type":44,"tag":65,"props":837,"children":838},{},[839,848,857],{"type":44,"tag":69,"props":840,"children":841},{},[842],{"type":44,"tag":50,"props":843,"children":845},{"className":844},[],[846],{"type":55,"value":847},"agentops doctor [--workspace] [--config] [--out] [--lookback-days] [--severity-fail]",{"type":44,"tag":69,"props":849,"children":850},{},[851],{"type":44,"tag":50,"props":852,"children":854},{"className":853},[],[855],{"type":55,"value":856},"agentops agent serve [--host] [--port] [--config] [--no-verify] [--workers]",{"type":44,"tag":69,"props":858,"children":859},{},[860],{"type":44,"tag":50,"props":861,"children":863},{"className":862},[],[864],{"type":55,"value":865},"agentops cockpit [--host] [--port] [--workspace]",{"type":44,"tag":69,"props":867,"children":868},{},[869,871,877,879,885,887,892],{"type":55,"value":870},"If a source is ",{"type":44,"tag":50,"props":872,"children":874},{"className":873},[],[875],{"type":55,"value":876},"skipped",{"type":55,"value":878}," or ",{"type":44,"tag":50,"props":880,"children":882},{"className":881},[],[883],{"type":55,"value":884},"error",{"type":55,"value":886},", surface that as the ",{"type":44,"tag":73,"props":888,"children":889},{},[890],{"type":55,"value":891},"first",{"type":55,"value":893},"\nthing in the user-facing summary so they know the analyzer ran with\npartial data.",{"type":44,"tag":69,"props":895,"children":896},{},[897],{"type":55,"value":898},"Never suggest disabling content-safety checks - recommend filtering\nthe offending row or tightening the system prompt instead.",{"type":44,"tag":69,"props":900,"children":901},{},[902],{"type":55,"value":903},"Never suggest that AgentOps executes ASSERT, applies ACS controls, or runs\nred-team campaigns. It only records evidence and readiness findings.",{"type":44,"tag":905,"props":906,"children":907},"style",{},[908],{"type":55,"value":909},"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":911,"total":1088},[912,931,950,969,984,999,1012,1027,1038,1052,1063,1076],{"slug":913,"name":913,"fn":914,"description":915,"org":916,"tags":917,"stars":928,"repoUrl":929,"updatedAt":930},"azure-arg-external-evaluation-policy-author","author and test Azure Resource Graph policies","Use when the user wants to author, design, or test an Azure Policy that queries Azure Resource Graph (ARG) at request-time — i.e. a policy whose deny\u002Faudit decision depends on data from elsewhere in the subscription (sibling\u002Fparent resource state, RG-wide invariants, multi-hop relationships, etc.). Formally called Azure Policy External Evaluation; sometimes referred to colloquially as \"Invoke\". Drives an iterative KQL co-design loop against the user's real subscription via `az graph query`, then emits a policy definition, assignment, `.http` test flow, and an `EXPLANATION.md` companion. Read-only; never provisions anything.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[918,919,922,925],{"name":11,"slug":8,"type":16},{"name":920,"slug":921,"type":16},"Compliance","compliance",{"name":923,"slug":924,"type":16},"Governance","governance",{"name":926,"slug":927,"type":16},"Policy","policy",1686,"https:\u002F\u002Fgithub.com\u002FAzure\u002Fazure-policy","2026-07-12T08:17:48.378432",{"slug":932,"name":932,"fn":933,"description":934,"org":935,"tags":936,"stars":947,"repoUrl":948,"updatedAt":949},"azure-blueprints-migration","migrate Azure Blueprints to Template Specs","Use when a user needs to migrate off Azure Blueprints (definitions and\u002For assignments) to Template Specs and Deployment Stacks before the January 31, 2027 retirement. Covers inventory, export, conversion to Bicep, policy decoupling, Template Spec publishing, Deployment Stack deployment with deny-settings, validation, and cutover.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[937,938,941,944],{"name":11,"slug":8,"type":16},{"name":939,"slug":940,"type":16},"Deployment","deployment",{"name":942,"slug":943,"type":16},"Infrastructure as Code","infrastructure-as-code",{"name":945,"slug":946,"type":16},"Migration","migration",260,"https:\u002F\u002Fgithub.com\u002FAzure\u002Fazure-blueprints","2026-07-12T08:17:49.646405",{"slug":951,"name":951,"fn":952,"description":953,"org":954,"tags":955,"stars":966,"repoUrl":967,"updatedAt":968},"apiview-feedback-resolution","resolve APIView feedback on Azure SDKs","Analyze and resolve APIView review feedback on Azure SDK PRs. **UTILITY SKILL**. USE FOR: APIView comments, API review feedback, SDK API surface changes. DO NOT USE FOR: general code review, non-APIView feedback. INVOKES: azure-sdk-mcp:azsdk_apiview_get_comments, azure-sdk-mcp:azsdk_typespec_customized_code_update.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[956,959,960,963],{"name":957,"slug":958,"type":16},"API Development","api-development",{"name":11,"slug":8,"type":16},{"name":961,"slug":962,"type":16},"Code Review","code-review",{"name":964,"slug":965,"type":16},"Documentation","documentation",133,"https:\u002F\u002Fgithub.com\u002FAzure\u002Fazure-sdk-tools","2026-07-12T08:17:43.350876",{"slug":970,"name":970,"fn":971,"description":972,"org":973,"tags":974,"stars":966,"repoUrl":967,"updatedAt":983},"azsdk-common-live-and-recorded-tests","deploy resources and run Azure SDK tests","Deploy test resources and run Azure SDK tests in live, record, or playback mode. WHEN: \"run live tests\", \"run recorded tests\", \"deploy test resources\", \"record tests\", \"run tests in record mode\", \"clean up test resources\", \"run tests against live resources\". DO NOT USE FOR: writing new tests, authoring Bicep templates, playback-only test runs without resource deployment. INVOKES: azure-sdk-mcp:azsdk_package_run_tests.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[975,976,977,980],{"name":11,"slug":8,"type":16},{"name":939,"slug":940,"type":16},{"name":978,"slug":979,"type":16},"SDK","sdk",{"name":981,"slug":982,"type":16},"Testing","testing","2026-07-12T08:17:44.718943",{"slug":985,"name":985,"fn":986,"description":987,"org":988,"tags":989,"stars":966,"repoUrl":967,"updatedAt":998},"azsdk-common-prepare-release-plan","manage Azure SDK release plan work items","Create, get, update, abandon, and link SDK PRs to release plan work items for Azure SDK releases. **UTILITY SKILL**. USE FOR: \"create release plan\", \"get release plan\", \"update release plan\", \"update API spec in release plan\", \"update SDK details in release plan\", \"abandon release plan\", \"link SDK PR to plan\", \"namespace approval\", \"check release plan status\". DO NOT USE FOR: SDK code generation, pipeline troubleshooting, API review feedback. INVOKES: azure-sdk-mcp:azsdk_create_release_plan, azure-sdk-mcp:azsdk_get_release_plan, azure-sdk-mcp:azsdk_get_release_plan_for_spec_pr, azure-sdk-mcp:azsdk_update_release_plan, azure-sdk-mcp:azsdk_update_api_spec_pull_request_in_release_plan, azure-sdk-mcp:azsdk_update_sdk_details_in_release_plan, azure-sdk-mcp:azsdk_abandon_release_plan, azure-sdk-mcp:azsdk_link_sdk_pull_request_to_release_plan, azure-sdk-mcp:azsdk_link_namespace_approval_issue.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[990,991,994,997],{"name":11,"slug":8,"type":16},{"name":992,"slug":993,"type":16},"GitHub","github",{"name":995,"slug":996,"type":16},"Project Management","project-management",{"name":978,"slug":979,"type":16},"2026-07-12T08:17:38.345387",{"slug":1000,"name":1000,"fn":1001,"description":1002,"org":1003,"tags":1004,"stars":966,"repoUrl":967,"updatedAt":1011},"azsdk-common-sdk-release","release Azure SDK packages","Check release readiness and trigger the release pipeline for Azure SDK packages. **UTILITY SKILL**. USE FOR: \"release SDK\", \"trigger release\", \"check release readiness\", \"release pipeline\", \"publish package\", \"ship SDK\". DO NOT USE FOR: SDK development, code generation, pipeline debugging, release plan creation. INVOKES: azure-sdk-mcp:azsdk_release_sdk.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1005,1006,1009,1010],{"name":11,"slug":8,"type":16},{"name":1007,"slug":1008,"type":16},"CI\u002FCD","ci-cd",{"name":939,"slug":940,"type":16},{"name":978,"slug":979,"type":16},"2026-07-12T08:17:34.27607",{"slug":1013,"name":1013,"fn":1014,"description":1015,"org":1016,"tags":1017,"stars":966,"repoUrl":967,"updatedAt":1026},"azure-typespec-author","author and modify Azure TypeSpec API specifications","Authors and modifies Azure TypeSpec (.tsp) API specifications. USE FOR: any TypeSpec\u002Ftsp change — api versions (add, bump, preview, stable, promote), resources, operations, models, properties, decorators, visibility, constraints, breaking changes, LRO, suppressions, operationId, spread model. Covers ARM resource-manager and data-plane services. DO NOT USE FOR: SDK generation, releasing SDK packages, or single MCP tool calls. INVOKES: azure-sdk-mcp:azsdk_typespec_generate_authoring_plan, azure-sdk-mcp:azsdk_run_typespec_validation.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1018,1019,1020,1023],{"name":957,"slug":958,"type":16},{"name":11,"slug":8,"type":16},{"name":1021,"slug":1022,"type":16},"OpenAPI","openapi",{"name":1024,"slug":1025,"type":16},"Technical Writing","technical-writing","2026-07-12T08:17:39.603232",{"slug":1028,"name":1028,"fn":1029,"description":1030,"org":1031,"tags":1032,"stars":966,"repoUrl":967,"updatedAt":1037},"generate-sdk-locally","generate and test Azure SDKs locally","Generate, build, and test Azure SDKs locally from TypeSpec with automatic customization. WHEN: \"generate SDK locally\", \"build SDK\", \"run SDK tests\", \"run CI checks\", \"validate package\", \"run checks\", \"update changelog\", \"fix SDK build errors\", \"fix breaking changes\", \"resolve SDK generation errors\", \"customize TypeSpec\", \"rename SDK client\", \"rename SDK model\", \"hide operation from SDK\", \"fix analyzer errors\", \"resolve customization drift\", \"create subclient\", \"update metadata\", \"update version\". DO NOT USE FOR: publishing to package registries, CI pipeline configuration, API design review. INVOKES: azsdk_verify_setup, azsdk_package_generate_code, azsdk_package_build_code, azsdk_package_run_check, azsdk_package_run_tests, azsdk_customized_code_update, azsdk_package_update_changelog_content, azsdk_package_update_metadata, azsdk_package_update_version.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1033,1034,1035,1036],{"name":11,"slug":8,"type":16},{"name":1007,"slug":1008,"type":16},{"name":978,"slug":979,"type":16},{"name":981,"slug":982,"type":16},"2026-07-12T08:17:37.08523",{"slug":1039,"name":1039,"fn":1040,"description":1041,"org":1042,"tags":1043,"stars":966,"repoUrl":967,"updatedAt":1051},"markdown-token-optimizer","optimize markdown files for token efficiency","Analyze markdown files for token efficiency and reduce context-window bloat. **UTILITY SKILL**. DO NOT USE FOR: code optimization, general file editing, non-markdown files. TRIGGERS: optimize markdown, reduce tokens, token count, token bloat, too many tokens, make concise, shrink file, file too large, optimize for AI, token efficiency, verbose markdown, reduce file size. INVOKES: waza CLI.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1044,1047,1050],{"name":1045,"slug":1046,"type":16},"LLM","llm",{"name":1048,"slug":1049,"type":16},"Performance","performance",{"name":1024,"slug":1025,"type":16},"2026-07-12T08:17:42.080413",{"slug":1053,"name":1053,"fn":1054,"description":1055,"org":1056,"tags":1057,"stars":966,"repoUrl":967,"updatedAt":1062},"pipeline-troubleshooting","troubleshoot Azure SDK CI pipelines","Diagnose and resolve failures in Azure SDK CI and generation pipelines. **UTILITY SKILL**. USE FOR: \"pipeline failed\", \"build failure\", \"CI check failing\", \"SDK generation error\", \"reproduce pipeline locally\", \"debug SDK pipeline\". DO NOT USE FOR: local build issues without pipeline context, API design review, SDK publishing. INVOKES: azure-sdk-mcp:azsdk_analyze_pipeline, azure-sdk-mcp:azsdk_package_build_code, azure-sdk-mcp:azsdk_package_run_check.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1058,1059,1060,1061],{"name":11,"slug":8,"type":16},{"name":1007,"slug":1008,"type":16},{"name":25,"slug":26,"type":16},{"name":978,"slug":979,"type":16},"2026-07-12T08:17:40.821512",{"slug":1064,"name":1064,"fn":1065,"description":1066,"org":1067,"tags":1068,"stars":966,"repoUrl":967,"updatedAt":1075},"sensei","improve skill frontmatter compliance","**WORKFLOW SKILL** — Iteratively improve skill frontmatter compliance using the Ralph loop pattern. WHEN: \"run sensei\", \"sensei help\", \"improve skill\", \"fix frontmatter\", \"skill compliance\", \"frontmatter audit\", \"score skill\", \"check skill tokens\". INVOKES: token counting tools, test runners, git commands. FOR SINGLE OPERATIONS: use token CLI directly for counts\u002Fchecks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1069,1070,1071,1074],{"name":11,"slug":8,"type":16},{"name":920,"slug":921,"type":16},{"name":1072,"slug":1073,"type":16},"Process Optimization","process-optimization",{"name":1024,"slug":1025,"type":16},"2026-07-12T08:17:32.970921",{"slug":1077,"name":1077,"fn":1078,"description":1079,"org":1080,"tags":1081,"stars":966,"repoUrl":967,"updatedAt":1087},"skill-authoring","author agent skills for agentskills.io","Write Agent Skills that comply with the agentskills.io specification. WHEN: \"create a skill\", \"new skill\", \"write a skill\", \"skill template\", \"skill structure\", \"review skill\", \"skill PR\", \"skill compliance\", \"SKILL.md format\", \"skill frontmatter\", \"skill best practices\". DO NOT USE FOR: improving existing skills (use sensei), general documentation. INVOKES: waza CLI.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1082,1083,1086],{"name":964,"slug":965,"type":16},{"name":1084,"slug":1085,"type":16},"Plugin Development","plugin-development",{"name":1024,"slug":1025,"type":16},"2026-07-12T08:17:35.873862",109,{"items":1090,"total":31},[1091,1099,1112,1125,1135,1145,1158],{"slug":4,"name":4,"fn":5,"description":6,"org":1092,"tags":1093,"stars":27,"repoUrl":28,"updatedAt":29},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1094,1095,1096,1097,1098],{"name":22,"slug":23,"type":16},{"name":11,"slug":8,"type":16},{"name":25,"slug":26,"type":16},{"name":19,"slug":20,"type":16},{"name":14,"slug":15,"type":16},{"slug":1100,"name":1100,"fn":1101,"description":1102,"org":1103,"tags":1104,"stars":27,"repoUrl":28,"updatedAt":1111},"agentops-config","configure AgentOps release-readiness gates","Generate or update agentops.yaml (flat 1.0 schema) for AgentOps release-readiness gates. Trigger on \"configure agentops\", \"agentops.yaml\", \"set up evaluation\", \"what should I evaluate\". Infer the agent target and dataset from the codebase; ask only when nothing can be found.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1105,1106,1107,1110],{"name":22,"slug":23,"type":16},{"name":11,"slug":8,"type":16},{"name":1108,"slug":1109,"type":16},"Configuration","configuration",{"name":19,"slug":20,"type":16},"2026-07-12T08:19:06.790378",{"slug":1113,"name":1113,"fn":1114,"description":1115,"org":1116,"tags":1117,"stars":27,"repoUrl":28,"updatedAt":1124},"agentops-dataset","create datasets for AgentOps release readiness","Create or extend a small JSONL dataset for AgentOps release-readiness gates. Trigger on \"create dataset\", \"generate test data\", \"JSONL\", \"more eval rows\". Infer the agent's domain from the codebase and produce realistic rows; never fabricate data when the domain is unclear.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1118,1119,1120,1123],{"name":22,"slug":23,"type":16},{"name":11,"slug":8,"type":16},{"name":1121,"slug":1122,"type":16},"Datasets","datasets",{"name":19,"slug":20,"type":16},"2026-07-12T08:19:08.00408",{"slug":1126,"name":1126,"fn":1127,"description":1128,"org":1129,"tags":1130,"stars":27,"repoUrl":28,"updatedAt":1134},"agentops-eval","run release-readiness evaluations for agents","Run AgentOps release-readiness evaluations against Foundry prompt agents, Foundry hosted endpoints, HTTP\u002FJSON agents, or raw model deployments. Trigger on phrases like \"run eval\", \"evaluate my agent\", \"benchmark\", \"agentops eval\", \"compare runs\", \"can we ship\". Uses the flat agentops.yaml schema.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1131,1132,1133],{"name":22,"slug":23,"type":16},{"name":11,"slug":8,"type":16},{"name":19,"slug":20,"type":16},"2026-07-15T06:02:50.097169",{"slug":520,"name":520,"fn":1136,"description":1137,"org":1138,"tags":1139,"stars":27,"repoUrl":28,"updatedAt":1144},"draft governance evidence for AI agents","Scaffold ASSERT and Red Team runners for the release gate, and draft reviewable governance evidence for ASSERT, Agent Control Specification (ACS), Guided Guardrail readiness, and red-team planning. Trigger on \"ASSERT\", \"ACS\", \"agent control\", \"guardrail\", \"red team\", \"governance\", \"release evidence\", \"scaffold assert\", \"set up red team\", \"add safety gate\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1140,1141,1142,1143],{"name":22,"slug":23,"type":16},{"name":11,"slug":8,"type":16},{"name":920,"slug":921,"type":16},{"name":923,"slug":924,"type":16},"2026-07-12T08:19:04.026045",{"slug":1146,"name":1146,"fn":1147,"description":1148,"org":1149,"tags":1150,"stars":27,"repoUrl":28,"updatedAt":1157},"agentops-report","generate and explain AgentOps release-gate reports","Read, regenerate, and explain AgentOps release-gate reports. Trigger on \"show report\", \"explain scores\", \"regenerate report\", \"what do these metrics mean\", \"where is the proof\". Operates on results.json and report.md produced by `agentops eval run`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1151,1152,1153,1154],{"name":22,"slug":23,"type":16},{"name":11,"slug":8,"type":16},{"name":14,"slug":15,"type":16},{"name":1155,"slug":1156,"type":16},"Reporting","reporting","2026-07-12T08:19:09.241071",{"slug":1159,"name":1159,"fn":1160,"description":1161,"org":1162,"tags":1163,"stars":27,"repoUrl":28,"updatedAt":1170},"agentops-workflow","configure AgentOps release readiness workflows","Set up AgentOps release-readiness workflows: PR eval gates, Doctor\u002Fevidence artifacts, and safe deploy handoffs to azd or Foundry prompt-agent tooling. Trigger on CI, CD, pipeline, workflow, GitHub Actions, Azure DevOps, ADO, PR gate, deploy, environments, GitFlow, release branch, promote to prod, DevOps, can we ship.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1164,1165,1166,1167],{"name":11,"slug":8,"type":16},{"name":1007,"slug":1008,"type":16},{"name":939,"slug":940,"type":16},{"name":1168,"slug":1169,"type":16},"GitHub Actions","github-actions","2026-07-15T06:02:51.371749"]