[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-google-deepmind-workflow-skill-creator":3,"mdc-5n2jps-key":33,"related-org-google-deepmind-workflow-skill-creator":1602,"related-repo-google-deepmind-workflow-skill-creator":1774},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":28,"sourceUrl":31,"mdContent":32},"workflow-skill-creator","distill workflows into reusable agent skills","Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say \"make this a skill\", \"create a skill from what we just did\", \"package this workflow\" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"google-deepmind","Google DeepMind","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fgoogle-deepmind.png",[12,16,19],{"name":13,"slug":14,"type":15},"Automation","automation","tag",{"name":17,"slug":18,"type":15},"Process Documentation","process-documentation",{"name":20,"slug":21,"type":15},"Agents","agents",2333,"https:\u002F\u002Fgithub.com\u002Fgoogle-deepmind\u002Fscience-skills","2026-07-12T07:52:04.311992",null,234,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools.","https:\u002F\u002Fgithub.com\u002Fgoogle-deepmind\u002Fscience-skills\u002Ftree\u002FHEAD\u002Fskills\u002Fworkflow_skill_creator","---\nname: workflow-skill-creator\ndescription: >\n  Distills a completed user workflow or interaction into a reusable agent\n  skill. Use when the user asks to turn their workflow, interaction, or\n  multi-step process into a skill, or when they say \"make this a skill\",\n  \"create a skill from what we just did\", \"package this workflow\" or similar.\n  Do not use for creating skills from scratch without an existing workflow\n  (use a generic skill-creator for that).\n---\n\n# Workflow-to-Skill Distiller\n\nTurns a completed workflow into a reusable agent skill. Specifically, this skill\nextracts patterns from an interaction or workflow that **already happened** and\npackages them.\n\n> [!CAUTION] **You MUST complete Phase 1 (Brainstorming) before writing any code\n> or SKILL.md content.** Skipping brainstorming produces skills that are either\n> too rigid or too vague. The brainstorming conversation is the most important\n> part of this process.\n\n## Phase 1: Brainstorming (MANDATORY)\n\nHave an **iterative back-and-forth conversation** with the user. Do NOT ask all\nquestions at once. Pick 2-3 relevant questions per round from the bank below,\nrefine your understanding, and ask follow-ups.\n\n### Round 1: Understand the Workflow\n\nStart by summarizing what you observed from the workflow, then ask:\n\n1.  \"Here's my understanding of the workflow: [summary]. Is this accurate? What\n    would you change?\"\n2.  \"What are the expected inputs and outputs for this workflow?\"\n3.  \"How often do you expect to run this workflow? Is it recurring or one-off?\"\n\n### Round 2: Flexibility and Error Handling\n\nFor each step identified in the workflow, determine its rigidity:\n\n1.  \"For [step X], if the primary approach fails (e.g., API down, no results),\n    should the agent: (a) ask you for guidance, (b) try alternative approaches\n    automatically, or (c) fail loudly with an error?\"\n2.  \"Are there any steps where the exact method matters (e.g., must use a\n    specific database), vs. steps where any reasonable approach is fine?\"\n3.  \"Should the skill handle edge cases silently or surface them to the user?\"\n\n### Round 3: Dependencies and Resources\n\nBefore asking these questions, check which of your installed skills overlap with\nthe workflow. If an existing skill from the science bundle covers a step, the\nnew skill **MUST** reference it — do not offer a self-contained option.\n\n1.  \"I noticed the workflow uses functionality covered by [existing skill X,\n    skill Y]. The new skill will reference these rather than reimplementing\n    them. Are there any other tools or skills you'd like me to incorporate?\"\n2.  \"Are there any API rate limits I should be aware of for services used in\n    this workflow that aren't already covered by an existing skill?\"\n3.  \"Are there specific files that provide important scientific context for\n    creating this skill? For example: API documentation, reference papers,\n    example datasets, or domain-specific notes. If so, please share them and I\n    will incorporate their content into the skill's reference materials.\"\n\n### Round 4: Scope and Shape\n\n1.  \"Our workflow covered [X, Y, Z]. Should I distill all of these into the\n    skill, or is there additional functionality that's important to include?\n    Conversely, should any of these be left out?\"\n2.  Determine whether the skill needs any code. If any step involves calling an\n    API, processing data, reading\u002Fwriting files, or computing results, the skill\n    **needs code** and you should default to the CLI pattern. Only use a\n    text-only instruction skill when every step is purely about reasoning,\n    coordinating existing tools, or following a written protocol with no\n    programmatic work at all. Confirm your assessment with the user in plain\n    language:\n    -   If code is needed: \"Some of these steps involve [fetching data from an\n        API \u002F processing files \u002F computing results], so I'll create a helper\n        script that the agent can run for you. The script will have simple\n        commands like `search`, `fetch`, `analyze`, etc. — you won't need to\n        write any code yourself. Does that sound right?\"\n    -   If no code is needed: \"This workflow is entirely about following a set\n        of steps and using existing tools — no new code is needed. I'll write it\n        as a set of clear instructions the agent follows. Does that sound\n        right?\"\n3.  If a helper script will be created: \"I'm thinking the script should have\n    these commands: [proposed commands in plain English, e.g. 'search for\n    proteins', 'fetch results', 'compare sequences']. What would you add or\n    change?\"\n4.  \"What should the skill be called? Proposed name: `[suggestion]`.\"\n\n### Round 5: Testing (Optional)\n\n1.  \"Can you provide a sample query and expected answer that I can use to verify\n    the skill works as intended? For example: 'If I ask [question], the skill\n    should produce [answer].' This is optional but helps me validate the skill\n    during development.\"\n\n### Brainstorming Completion Criteria\n\nYou are ready to move to Phase 2 when you can confidently answer ALL of:\n\n-   [ ] What is the workflow's purpose and scope?\n-   [ ] What are the inputs and outputs?\n-   [ ] Which steps are strict vs. flexible?\n-   [ ] Which existing skills should be referenced?\n-   [ ] What new scripts (if any) are needed?\n-   [ ] What rate limits apply?\n-   [ ] How should errors be handled?\n-   [ ] Does the workflow need any code? (If yes → CLI pattern; if no →\n    instruction-only)\n-   [ ] Where should the skill be installed? (local, global, or custom path)\n-   [ ] Is there a sample query\u002Fanswer for validation?\n\n## Phase 2: Skill Design\n\nProduce a **design document** (as an artifact \u002F implementation plan) and present\nit to the user for approval. The document must include:\n\n1.  **Skill name and description** (following YAML frontmatter rules: name ≤64\n    chars, lowercase + hyphens; description ≤1024 chars).\n2.  **Directory structure** showing all planned files and the **install\n    location** (local, global, or custom — see Rule 7).\n3.  **Existing skills referenced** with rationale for each.\n4.  **New scripts** (if any) with proposed subcommands and arguments.\n5.  **Rate limiting strategy** for any APIs not covered by existing skills.\n6.  **Error handling strategy** per step.\n\n**Wait for explicit user approval before proceeding to Phase 3.**\n\n## Phase 3: Implementation\n\n### Guiding Principles\n\nGeneral guidelines for skill implementation:\n\n-   Use `uv run`, never `python` or `python3`.\n-   Prefer stdlib libraries that come with a default Python 3 installation\n    (`urllib` preferred); Avoid libraries that require extra installation if\n    possible.\n-   Rate limits must be documented and respected in code. Prefer\n    **file-lock–based rate limiting** so that concurrent sub-agents sharing the\n    same machine collectively respect the limit. See other skills in the Science\n    Skills bundle for the canonical cross-process–safe implementation.\n-   Skill output must be \u003C500 lines or redirected to a file. Long output files\n    should be processed programmatically to extract relevant fields.\n-   Hyphens are recommended for the skill name and YAML `name:` field.\n\n### Rule 1: Reuse Existing Skills\n\nWhen the workflow uses functionality covered by an existing installed skill, the\nnew SKILL.md **MUST** reference it by name rather than reimplementing. Include a\n**Dependencies** section in the SKILL.md listing required skills with a brief\nrationale for each.\n\n### Rule 2: Rate Limiting for New APIs\n\nFor any API interaction **not** covered by an existing skill, the generated CLI\nscript **MUST** implement rate limiting. Before writing any rate-limiting code,\n**look up the API's official rate-limit guidelines**: check any documentation\nthe user provided during brainstorming, then search the API's public\ndocumentation online. If no documented rate limit can be found, **default to 1\nrequest per second**. The rate limiting pattern is built directly into the CLI\ntemplate at `references\u002Fcli_script_template.py` — see the `RateLimitError` class\nand the `_request` method of the API client.\n\nKey requirements:\n\n-   Use `time.monotonic()` for timing (not `time.time()`).\n-   Calculate delay from documented rate limits.\n-   Implement retry with exponential backoff for transient errors (5xx).\n-   Raise a dedicated `RateLimitError` when HTTP 429 is received.\n-   Log retry attempts to stderr so the agent can observe progress.\n-   Include the URL and rate-limit value in error messages.\n-   On non-retriable HTTP errors (e.g. 400, 403, 404), read and include the\n    response body in the error message — not just the status code. API response\n    bodies contain actionable details (e.g., \"Invalid parameter\") that enable\n    the agent to self-correct.\n\n### Rule 3: CLI Script Pattern (Default When Code Is Needed)\n\n**This is the default choice.** If **any** step in the workflow involves API\ncalls, data processing, file I\u002FO, computation, or any other programmatic work,\nproduce a multi-command CLI script using `argparse` with subcommands. Follow the\ntemplate in `references\u002Fcli_script_template.py`.\n\nKey requirements:\n\n-   Each major workflow step becomes a subcommand.\n-   All subcommands accept `--output` for writing results to a file.\n-   Use `json.dump` with `indent=2` for JSON output.\n-   Print a success message with the output file path.\n-   Exit with code 1 on errors.\n-   Make arguments like `--limit` **required** (no silent defaults). This forces\n    the agent to specify the value explicitly, preventing it from assuming it\n    retrieved \"all\" results when it was silently capped.\n\n### Rule 4: Default to File Output\n\nAll scripts and workflows **MUST** write output to files, not stdout. Stdout\nshould only contain short status messages (e.g., \"Success! Data written to:\nresults.json\"). This is critical because:\n\n-   API responses can be very large and will truncate in terminal output.\n-   File output is token-efficient — the agent reads only the fields it needs\n    using `jp` or Python one-liners.\n-   Large stdout output wastes context window space.\n\n### Rule 5: Instruction-Only Pattern (Only When No Code Is Needed)\n\nUse this pattern **only** when the workflow requires **zero** programmatic work\n— i.e., every step is purely about orchestration, reasoning, multi-skill\ncoordination, or following a written protocol. If any step needs code (API\ncalls, data processing, file I\u002FO, etc.), use the CLI pattern from Rule 3\ninstead. Produce a SKILL.md with a structured workflow section:\n\n```markdown\n## Workflow\n\n### 1. Step Name\n- Description of what to do\n- Which skill to use and how\n\n### 2. Next Step\n...\n```\n\n### Rule 6: SKILL.md Structure\n\nEvery generated SKILL.md must follow this structure:\n\n```markdown\n---\nname: {skill-name}\ndescription: >-\n  {description}\n---\n\n# {Skill Title}\n\n## Overview\n{Brief description of what the skill does.}\n\n## Dependencies\n{List of required skills, if any.}\n\n## Quick Start\n{Minimal example to get started.}\n\n## Utility Scripts (if CLI-based)\n{Document each subcommand with examples.}\n\n## Workflow (if instruction-only)\n{Numbered steps with clear instructions.}\n\n## Rate Limiting (if applicable)\n{Document rate limits and how they are enforced.}\n\n## Common Mistakes\n{List 2-3 common pitfalls.}\n```\n\n### Rule 7: Skill Placement\n\nSkills can be installed **locally** (project-specific, per-workspace) or\n**globally** (available across all projects). Ask the user if they want to\ninstall locally, globally, or use a custom install path.\n\nSkill paths by agent CLI (local paths relative to project root):\n\n-   **Claude Code**: local `.claude\u002Fskills\u002F`, global `~\u002F.claude\u002Fskills\u002F`\n-   **Codex**: local `.agents\u002Fskills\u002F`, global `~\u002F.agents\u002Fskills\u002F`\n-   **Antigravity 2.0**: local `.agents\u002Fskills\u002F`, global\n    `~\u002F.gemini\u002Fconfig\u002Fskills\u002F`\n-   **Gemini CLI**: local `.gemini\u002Fskills\u002F`, global `~\u002F.gemini\u002Fskills\u002F`\n-   **OpenCode**: local `.opencode\u002Fskills\u002F`, global `~\u002F.config\u002Fopencode\u002Fskills\u002F`\n\nFor other CLIs, find out local and global skill paths by yourself.\n\n## Phase 4: Validation\n\nAfter implementation is complete:\n\n1.  **Test the skill manually** by invoking the agent with a natural-language\n    prompt that should trigger the new skill.\n\n2.  **If a sample query\u002Fanswer was provided** during brainstorming, run it\n    through the skill and verify the output matches expectations.\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,47,61,83,90,102,109,114,141,147,152,177,183,195,220,226,323,329,351,357,362,461,467,479,549,557,563,569,574,649,655,673,679,735,740,800,806,837,841,911,917,928,954,960,979,1088,1094,1099,1412,1418,1437,1442,1557,1562,1568,1573,1596],{"type":39,"tag":40,"props":41,"children":43},"element","h1",{"id":42},"workflow-to-skill-distiller",[44],{"type":45,"value":46},"text","Workflow-to-Skill Distiller",{"type":39,"tag":48,"props":49,"children":50},"p",{},[51,53,59],{"type":45,"value":52},"Turns a completed workflow into a reusable agent skill. Specifically, this skill\nextracts patterns from an interaction or workflow that ",{"type":39,"tag":54,"props":55,"children":56},"strong",{},[57],{"type":45,"value":58},"already happened",{"type":45,"value":60}," and\npackages them.",{"type":39,"tag":62,"props":63,"children":64},"blockquote",{},[65],{"type":39,"tag":48,"props":66,"children":67},{},[68,74,76,81],{"type":39,"tag":69,"props":70,"children":71},"span",{},[72],{"type":45,"value":73},"!CAUTION",{"type":45,"value":75}," ",{"type":39,"tag":54,"props":77,"children":78},{},[79],{"type":45,"value":80},"You MUST complete Phase 1 (Brainstorming) before writing any code\nor SKILL.md content.",{"type":45,"value":82}," Skipping brainstorming produces skills that are either\ntoo rigid or too vague. The brainstorming conversation is the most important\npart of this process.",{"type":39,"tag":84,"props":85,"children":87},"h2",{"id":86},"phase-1-brainstorming-mandatory",[88],{"type":45,"value":89},"Phase 1: Brainstorming (MANDATORY)",{"type":39,"tag":48,"props":91,"children":92},{},[93,95,100],{"type":45,"value":94},"Have an ",{"type":39,"tag":54,"props":96,"children":97},{},[98],{"type":45,"value":99},"iterative back-and-forth conversation",{"type":45,"value":101}," with the user. Do NOT ask all\nquestions at once. Pick 2-3 relevant questions per round from the bank below,\nrefine your understanding, and ask follow-ups.",{"type":39,"tag":103,"props":104,"children":106},"h3",{"id":105},"round-1-understand-the-workflow",[107],{"type":45,"value":108},"Round 1: Understand the Workflow",{"type":39,"tag":48,"props":110,"children":111},{},[112],{"type":45,"value":113},"Start by summarizing what you observed from the workflow, then ask:",{"type":39,"tag":115,"props":116,"children":117},"ol",{},[118,131,136],{"type":39,"tag":119,"props":120,"children":121},"li",{},[122,124,129],{"type":45,"value":123},"\"Here's my understanding of the workflow: ",{"type":39,"tag":69,"props":125,"children":126},{},[127],{"type":45,"value":128},"summary",{"type":45,"value":130},". Is this accurate? What\nwould you change?\"",{"type":39,"tag":119,"props":132,"children":133},{},[134],{"type":45,"value":135},"\"What are the expected inputs and outputs for this workflow?\"",{"type":39,"tag":119,"props":137,"children":138},{},[139],{"type":45,"value":140},"\"How often do you expect to run this workflow? Is it recurring or one-off?\"",{"type":39,"tag":103,"props":142,"children":144},{"id":143},"round-2-flexibility-and-error-handling",[145],{"type":45,"value":146},"Round 2: Flexibility and Error Handling",{"type":39,"tag":48,"props":148,"children":149},{},[150],{"type":45,"value":151},"For each step identified in the workflow, determine its rigidity:",{"type":39,"tag":115,"props":153,"children":154},{},[155,167,172],{"type":39,"tag":119,"props":156,"children":157},{},[158,160,165],{"type":45,"value":159},"\"For ",{"type":39,"tag":69,"props":161,"children":162},{},[163],{"type":45,"value":164},"step X",{"type":45,"value":166},", if the primary approach fails (e.g., API down, no results),\nshould the agent: (a) ask you for guidance, (b) try alternative approaches\nautomatically, or (c) fail loudly with an error?\"",{"type":39,"tag":119,"props":168,"children":169},{},[170],{"type":45,"value":171},"\"Are there any steps where the exact method matters (e.g., must use a\nspecific database), vs. steps where any reasonable approach is fine?\"",{"type":39,"tag":119,"props":173,"children":174},{},[175],{"type":45,"value":176},"\"Should the skill handle edge cases silently or surface them to the user?\"",{"type":39,"tag":103,"props":178,"children":180},{"id":179},"round-3-dependencies-and-resources",[181],{"type":45,"value":182},"Round 3: Dependencies and Resources",{"type":39,"tag":48,"props":184,"children":185},{},[186,188,193],{"type":45,"value":187},"Before asking these questions, check which of your installed skills overlap with\nthe workflow. If an existing skill from the science bundle covers a step, the\nnew skill ",{"type":39,"tag":54,"props":189,"children":190},{},[191],{"type":45,"value":192},"MUST",{"type":45,"value":194}," reference it — do not offer a self-contained option.",{"type":39,"tag":115,"props":196,"children":197},{},[198,210,215],{"type":39,"tag":119,"props":199,"children":200},{},[201,203,208],{"type":45,"value":202},"\"I noticed the workflow uses functionality covered by ",{"type":39,"tag":69,"props":204,"children":205},{},[206],{"type":45,"value":207},"existing skill X,\nskill Y",{"type":45,"value":209},". The new skill will reference these rather than reimplementing\nthem. Are there any other tools or skills you'd like me to incorporate?\"",{"type":39,"tag":119,"props":211,"children":212},{},[213],{"type":45,"value":214},"\"Are there any API rate limits I should be aware of for services used in\nthis workflow that aren't already covered by an existing skill?\"",{"type":39,"tag":119,"props":216,"children":217},{},[218],{"type":45,"value":219},"\"Are there specific files that provide important scientific context for\ncreating this skill? For example: API documentation, reference papers,\nexample datasets, or domain-specific notes. If so, please share them and I\nwill incorporate their content into the skill's reference materials.\"",{"type":39,"tag":103,"props":221,"children":223},{"id":222},"round-4-scope-and-shape",[224],{"type":45,"value":225},"Round 4: Scope and Shape",{"type":39,"tag":115,"props":227,"children":228},{},[229,241,298,310],{"type":39,"tag":119,"props":230,"children":231},{},[232,234,239],{"type":45,"value":233},"\"Our workflow covered ",{"type":39,"tag":69,"props":235,"children":236},{},[237],{"type":45,"value":238},"X, Y, Z",{"type":45,"value":240},". Should I distill all of these into the\nskill, or is there additional functionality that's important to include?\nConversely, should any of these be left out?\"",{"type":39,"tag":119,"props":242,"children":243},{},[244,246,251,253],{"type":45,"value":245},"Determine whether the skill needs any code. If any step involves calling an\nAPI, processing data, reading\u002Fwriting files, or computing results, the skill\n",{"type":39,"tag":54,"props":247,"children":248},{},[249],{"type":45,"value":250},"needs code",{"type":45,"value":252}," and you should default to the CLI pattern. Only use a\ntext-only instruction skill when every step is purely about reasoning,\ncoordinating existing tools, or following a written protocol with no\nprogrammatic work at all. Confirm your assessment with the user in plain\nlanguage:\n",{"type":39,"tag":254,"props":255,"children":256},"ul",{},[257,293],{"type":39,"tag":119,"props":258,"children":259},{},[260,262,267,269,276,278,284,285,291],{"type":45,"value":261},"If code is needed: \"Some of these steps involve ",{"type":39,"tag":69,"props":263,"children":264},{},[265],{"type":45,"value":266},"fetching data from an\nAPI \u002F processing files \u002F computing results",{"type":45,"value":268},", so I'll create a helper\nscript that the agent can run for you. The script will have simple\ncommands like ",{"type":39,"tag":270,"props":271,"children":273},"code",{"className":272},[],[274],{"type":45,"value":275},"search",{"type":45,"value":277},", ",{"type":39,"tag":270,"props":279,"children":281},{"className":280},[],[282],{"type":45,"value":283},"fetch",{"type":45,"value":277},{"type":39,"tag":270,"props":286,"children":288},{"className":287},[],[289],{"type":45,"value":290},"analyze",{"type":45,"value":292},", etc. — you won't need to\nwrite any code yourself. Does that sound right?\"",{"type":39,"tag":119,"props":294,"children":295},{},[296],{"type":45,"value":297},"If no code is needed: \"This workflow is entirely about following a set\nof steps and using existing tools — no new code is needed. I'll write it\nas a set of clear instructions the agent follows. Does that sound\nright?\"",{"type":39,"tag":119,"props":299,"children":300},{},[301,303,308],{"type":45,"value":302},"If a helper script will be created: \"I'm thinking the script should have\nthese commands: ",{"type":39,"tag":69,"props":304,"children":305},{},[306],{"type":45,"value":307},"proposed commands in plain English, e.g. 'search for\nproteins', 'fetch results', 'compare sequences'",{"type":45,"value":309},". What would you add or\nchange?\"",{"type":39,"tag":119,"props":311,"children":312},{},[313,315,321],{"type":45,"value":314},"\"What should the skill be called? Proposed name: ",{"type":39,"tag":270,"props":316,"children":318},{"className":317},[],[319],{"type":45,"value":320},"[suggestion]",{"type":45,"value":322},".\"",{"type":39,"tag":103,"props":324,"children":326},{"id":325},"round-5-testing-optional",[327],{"type":45,"value":328},"Round 5: Testing (Optional)",{"type":39,"tag":115,"props":330,"children":331},{},[332],{"type":39,"tag":119,"props":333,"children":334},{},[335,337,342,344,349],{"type":45,"value":336},"\"Can you provide a sample query and expected answer that I can use to verify\nthe skill works as intended? For example: 'If I ask ",{"type":39,"tag":69,"props":338,"children":339},{},[340],{"type":45,"value":341},"question",{"type":45,"value":343},", the skill\nshould produce ",{"type":39,"tag":69,"props":345,"children":346},{},[347],{"type":45,"value":348},"answer",{"type":45,"value":350},".' This is optional but helps me validate the skill\nduring development.\"",{"type":39,"tag":103,"props":352,"children":354},{"id":353},"brainstorming-completion-criteria",[355],{"type":45,"value":356},"Brainstorming Completion Criteria",{"type":39,"tag":48,"props":358,"children":359},{},[360],{"type":45,"value":361},"You are ready to move to Phase 2 when you can confidently answer ALL of:",{"type":39,"tag":254,"props":363,"children":366},{"className":364},[365],"contains-task-list",[367,380,389,398,407,416,425,434,443,452],{"type":39,"tag":119,"props":368,"children":371},{"className":369},[370],"task-list-item",[372,378],{"type":39,"tag":373,"props":374,"children":377},"input",{"disabled":375,"type":376},true,"checkbox",[],{"type":45,"value":379}," What is the workflow's purpose and scope?",{"type":39,"tag":119,"props":381,"children":383},{"className":382},[370],[384,387],{"type":39,"tag":373,"props":385,"children":386},{"disabled":375,"type":376},[],{"type":45,"value":388}," What are the inputs and outputs?",{"type":39,"tag":119,"props":390,"children":392},{"className":391},[370],[393,396],{"type":39,"tag":373,"props":394,"children":395},{"disabled":375,"type":376},[],{"type":45,"value":397}," Which steps are strict vs. flexible?",{"type":39,"tag":119,"props":399,"children":401},{"className":400},[370],[402,405],{"type":39,"tag":373,"props":403,"children":404},{"disabled":375,"type":376},[],{"type":45,"value":406}," Which existing skills should be referenced?",{"type":39,"tag":119,"props":408,"children":410},{"className":409},[370],[411,414],{"type":39,"tag":373,"props":412,"children":413},{"disabled":375,"type":376},[],{"type":45,"value":415}," What new scripts (if any) are needed?",{"type":39,"tag":119,"props":417,"children":419},{"className":418},[370],[420,423],{"type":39,"tag":373,"props":421,"children":422},{"disabled":375,"type":376},[],{"type":45,"value":424}," What rate limits apply?",{"type":39,"tag":119,"props":426,"children":428},{"className":427},[370],[429,432],{"type":39,"tag":373,"props":430,"children":431},{"disabled":375,"type":376},[],{"type":45,"value":433}," How should errors be handled?",{"type":39,"tag":119,"props":435,"children":437},{"className":436},[370],[438,441],{"type":39,"tag":373,"props":439,"children":440},{"disabled":375,"type":376},[],{"type":45,"value":442}," Does the workflow need any code? (If yes → CLI pattern; if no →\ninstruction-only)",{"type":39,"tag":119,"props":444,"children":446},{"className":445},[370],[447,450],{"type":39,"tag":373,"props":448,"children":449},{"disabled":375,"type":376},[],{"type":45,"value":451}," Where should the skill be installed? (local, global, or custom path)",{"type":39,"tag":119,"props":453,"children":455},{"className":454},[370],[456,459],{"type":39,"tag":373,"props":457,"children":458},{"disabled":375,"type":376},[],{"type":45,"value":460}," Is there a sample query\u002Fanswer for validation?",{"type":39,"tag":84,"props":462,"children":464},{"id":463},"phase-2-skill-design",[465],{"type":45,"value":466},"Phase 2: Skill Design",{"type":39,"tag":48,"props":468,"children":469},{},[470,472,477],{"type":45,"value":471},"Produce a ",{"type":39,"tag":54,"props":473,"children":474},{},[475],{"type":45,"value":476},"design document",{"type":45,"value":478}," (as an artifact \u002F implementation plan) and present\nit to the user for approval. The document must include:",{"type":39,"tag":115,"props":480,"children":481},{},[482,492,509,519,529,539],{"type":39,"tag":119,"props":483,"children":484},{},[485,490],{"type":39,"tag":54,"props":486,"children":487},{},[488],{"type":45,"value":489},"Skill name and description",{"type":45,"value":491}," (following YAML frontmatter rules: name ≤64\nchars, lowercase + hyphens; description ≤1024 chars).",{"type":39,"tag":119,"props":493,"children":494},{},[495,500,502,507],{"type":39,"tag":54,"props":496,"children":497},{},[498],{"type":45,"value":499},"Directory structure",{"type":45,"value":501}," showing all planned files and the ",{"type":39,"tag":54,"props":503,"children":504},{},[505],{"type":45,"value":506},"install\nlocation",{"type":45,"value":508}," (local, global, or custom — see Rule 7).",{"type":39,"tag":119,"props":510,"children":511},{},[512,517],{"type":39,"tag":54,"props":513,"children":514},{},[515],{"type":45,"value":516},"Existing skills referenced",{"type":45,"value":518}," with rationale for each.",{"type":39,"tag":119,"props":520,"children":521},{},[522,527],{"type":39,"tag":54,"props":523,"children":524},{},[525],{"type":45,"value":526},"New scripts",{"type":45,"value":528}," (if any) with proposed subcommands and arguments.",{"type":39,"tag":119,"props":530,"children":531},{},[532,537],{"type":39,"tag":54,"props":533,"children":534},{},[535],{"type":45,"value":536},"Rate limiting strategy",{"type":45,"value":538}," for any APIs not covered by existing skills.",{"type":39,"tag":119,"props":540,"children":541},{},[542,547],{"type":39,"tag":54,"props":543,"children":544},{},[545],{"type":45,"value":546},"Error handling strategy",{"type":45,"value":548}," per step.",{"type":39,"tag":48,"props":550,"children":551},{},[552],{"type":39,"tag":54,"props":553,"children":554},{},[555],{"type":45,"value":556},"Wait for explicit user approval before proceeding to Phase 3.",{"type":39,"tag":84,"props":558,"children":560},{"id":559},"phase-3-implementation",[561],{"type":45,"value":562},"Phase 3: Implementation",{"type":39,"tag":103,"props":564,"children":566},{"id":565},"guiding-principles",[567],{"type":45,"value":568},"Guiding Principles",{"type":39,"tag":48,"props":570,"children":571},{},[572],{"type":45,"value":573},"General guidelines for skill implementation:",{"type":39,"tag":254,"props":575,"children":576},{},[577,606,619,631,636],{"type":39,"tag":119,"props":578,"children":579},{},[580,582,588,590,596,598,604],{"type":45,"value":581},"Use ",{"type":39,"tag":270,"props":583,"children":585},{"className":584},[],[586],{"type":45,"value":587},"uv run",{"type":45,"value":589},", never ",{"type":39,"tag":270,"props":591,"children":593},{"className":592},[],[594],{"type":45,"value":595},"python",{"type":45,"value":597}," or ",{"type":39,"tag":270,"props":599,"children":601},{"className":600},[],[602],{"type":45,"value":603},"python3",{"type":45,"value":605},".",{"type":39,"tag":119,"props":607,"children":608},{},[609,611,617],{"type":45,"value":610},"Prefer stdlib libraries that come with a default Python 3 installation\n(",{"type":39,"tag":270,"props":612,"children":614},{"className":613},[],[615],{"type":45,"value":616},"urllib",{"type":45,"value":618}," preferred); Avoid libraries that require extra installation if\npossible.",{"type":39,"tag":119,"props":620,"children":621},{},[622,624,629],{"type":45,"value":623},"Rate limits must be documented and respected in code. Prefer\n",{"type":39,"tag":54,"props":625,"children":626},{},[627],{"type":45,"value":628},"file-lock–based rate limiting",{"type":45,"value":630}," so that concurrent sub-agents sharing the\nsame machine collectively respect the limit. See other skills in the Science\nSkills bundle for the canonical cross-process–safe implementation.",{"type":39,"tag":119,"props":632,"children":633},{},[634],{"type":45,"value":635},"Skill output must be \u003C500 lines or redirected to a file. Long output files\nshould be processed programmatically to extract relevant fields.",{"type":39,"tag":119,"props":637,"children":638},{},[639,641,647],{"type":45,"value":640},"Hyphens are recommended for the skill name and YAML ",{"type":39,"tag":270,"props":642,"children":644},{"className":643},[],[645],{"type":45,"value":646},"name:",{"type":45,"value":648}," field.",{"type":39,"tag":103,"props":650,"children":652},{"id":651},"rule-1-reuse-existing-skills",[653],{"type":45,"value":654},"Rule 1: Reuse Existing Skills",{"type":39,"tag":48,"props":656,"children":657},{},[658,660,664,666,671],{"type":45,"value":659},"When the workflow uses functionality covered by an existing installed skill, the\nnew SKILL.md ",{"type":39,"tag":54,"props":661,"children":662},{},[663],{"type":45,"value":192},{"type":45,"value":665}," reference it by name rather than reimplementing. Include a\n",{"type":39,"tag":54,"props":667,"children":668},{},[669],{"type":45,"value":670},"Dependencies",{"type":45,"value":672}," section in the SKILL.md listing required skills with a brief\nrationale for each.",{"type":39,"tag":103,"props":674,"children":676},{"id":675},"rule-2-rate-limiting-for-new-apis",[677],{"type":45,"value":678},"Rule 2: Rate Limiting for New APIs",{"type":39,"tag":48,"props":680,"children":681},{},[682,684,689,691,695,697,702,704,709,711,717,719,725,727,733],{"type":45,"value":683},"For any API interaction ",{"type":39,"tag":54,"props":685,"children":686},{},[687],{"type":45,"value":688},"not",{"type":45,"value":690}," covered by an existing skill, the generated CLI\nscript ",{"type":39,"tag":54,"props":692,"children":693},{},[694],{"type":45,"value":192},{"type":45,"value":696}," implement rate limiting. Before writing any rate-limiting code,\n",{"type":39,"tag":54,"props":698,"children":699},{},[700],{"type":45,"value":701},"look up the API's official rate-limit guidelines",{"type":45,"value":703},": check any documentation\nthe user provided during brainstorming, then search the API's public\ndocumentation online. If no documented rate limit can be found, ",{"type":39,"tag":54,"props":705,"children":706},{},[707],{"type":45,"value":708},"default to 1\nrequest per second",{"type":45,"value":710},". The rate limiting pattern is built directly into the CLI\ntemplate at ",{"type":39,"tag":270,"props":712,"children":714},{"className":713},[],[715],{"type":45,"value":716},"references\u002Fcli_script_template.py",{"type":45,"value":718}," — see the ",{"type":39,"tag":270,"props":720,"children":722},{"className":721},[],[723],{"type":45,"value":724},"RateLimitError",{"type":45,"value":726}," class\nand the ",{"type":39,"tag":270,"props":728,"children":730},{"className":729},[],[731],{"type":45,"value":732},"_request",{"type":45,"value":734}," method of the API client.",{"type":39,"tag":48,"props":736,"children":737},{},[738],{"type":45,"value":739},"Key requirements:",{"type":39,"tag":254,"props":741,"children":742},{},[743,763,768,773,785,790,795],{"type":39,"tag":119,"props":744,"children":745},{},[746,747,753,755,761],{"type":45,"value":581},{"type":39,"tag":270,"props":748,"children":750},{"className":749},[],[751],{"type":45,"value":752},"time.monotonic()",{"type":45,"value":754}," for timing (not ",{"type":39,"tag":270,"props":756,"children":758},{"className":757},[],[759],{"type":45,"value":760},"time.time()",{"type":45,"value":762},").",{"type":39,"tag":119,"props":764,"children":765},{},[766],{"type":45,"value":767},"Calculate delay from documented rate limits.",{"type":39,"tag":119,"props":769,"children":770},{},[771],{"type":45,"value":772},"Implement retry with exponential backoff for transient errors (5xx).",{"type":39,"tag":119,"props":774,"children":775},{},[776,778,783],{"type":45,"value":777},"Raise a dedicated ",{"type":39,"tag":270,"props":779,"children":781},{"className":780},[],[782],{"type":45,"value":724},{"type":45,"value":784}," when HTTP 429 is received.",{"type":39,"tag":119,"props":786,"children":787},{},[788],{"type":45,"value":789},"Log retry attempts to stderr so the agent can observe progress.",{"type":39,"tag":119,"props":791,"children":792},{},[793],{"type":45,"value":794},"Include the URL and rate-limit value in error messages.",{"type":39,"tag":119,"props":796,"children":797},{},[798],{"type":45,"value":799},"On non-retriable HTTP errors (e.g. 400, 403, 404), read and include the\nresponse body in the error message — not just the status code. API response\nbodies contain actionable details (e.g., \"Invalid parameter\") that enable\nthe agent to self-correct.",{"type":39,"tag":103,"props":801,"children":803},{"id":802},"rule-3-cli-script-pattern-default-when-code-is-needed",[804],{"type":45,"value":805},"Rule 3: CLI Script Pattern (Default When Code Is Needed)",{"type":39,"tag":48,"props":807,"children":808},{},[809,814,816,821,823,829,831,836],{"type":39,"tag":54,"props":810,"children":811},{},[812],{"type":45,"value":813},"This is the default choice.",{"type":45,"value":815}," If ",{"type":39,"tag":54,"props":817,"children":818},{},[819],{"type":45,"value":820},"any",{"type":45,"value":822}," step in the workflow involves API\ncalls, data processing, file I\u002FO, computation, or any other programmatic work,\nproduce a multi-command CLI script using ",{"type":39,"tag":270,"props":824,"children":826},{"className":825},[],[827],{"type":45,"value":828},"argparse",{"type":45,"value":830}," with subcommands. Follow the\ntemplate in ",{"type":39,"tag":270,"props":832,"children":834},{"className":833},[],[835],{"type":45,"value":716},{"type":45,"value":605},{"type":39,"tag":48,"props":838,"children":839},{},[840],{"type":45,"value":739},{"type":39,"tag":254,"props":842,"children":843},{},[844,849,862,882,887,892],{"type":39,"tag":119,"props":845,"children":846},{},[847],{"type":45,"value":848},"Each major workflow step becomes a subcommand.",{"type":39,"tag":119,"props":850,"children":851},{},[852,854,860],{"type":45,"value":853},"All subcommands accept ",{"type":39,"tag":270,"props":855,"children":857},{"className":856},[],[858],{"type":45,"value":859},"--output",{"type":45,"value":861}," for writing results to a file.",{"type":39,"tag":119,"props":863,"children":864},{},[865,866,872,874,880],{"type":45,"value":581},{"type":39,"tag":270,"props":867,"children":869},{"className":868},[],[870],{"type":45,"value":871},"json.dump",{"type":45,"value":873}," with ",{"type":39,"tag":270,"props":875,"children":877},{"className":876},[],[878],{"type":45,"value":879},"indent=2",{"type":45,"value":881}," for JSON output.",{"type":39,"tag":119,"props":883,"children":884},{},[885],{"type":45,"value":886},"Print a success message with the output file path.",{"type":39,"tag":119,"props":888,"children":889},{},[890],{"type":45,"value":891},"Exit with code 1 on errors.",{"type":39,"tag":119,"props":893,"children":894},{},[895,897,903,904,909],{"type":45,"value":896},"Make arguments like ",{"type":39,"tag":270,"props":898,"children":900},{"className":899},[],[901],{"type":45,"value":902},"--limit",{"type":45,"value":75},{"type":39,"tag":54,"props":905,"children":906},{},[907],{"type":45,"value":908},"required",{"type":45,"value":910}," (no silent defaults). This forces\nthe agent to specify the value explicitly, preventing it from assuming it\nretrieved \"all\" results when it was silently capped.",{"type":39,"tag":103,"props":912,"children":914},{"id":913},"rule-4-default-to-file-output",[915],{"type":45,"value":916},"Rule 4: Default to File Output",{"type":39,"tag":48,"props":918,"children":919},{},[920,922,926],{"type":45,"value":921},"All scripts and workflows ",{"type":39,"tag":54,"props":923,"children":924},{},[925],{"type":45,"value":192},{"type":45,"value":927}," write output to files, not stdout. Stdout\nshould only contain short status messages (e.g., \"Success! Data written to:\nresults.json\"). This is critical because:",{"type":39,"tag":254,"props":929,"children":930},{},[931,936,949],{"type":39,"tag":119,"props":932,"children":933},{},[934],{"type":45,"value":935},"API responses can be very large and will truncate in terminal output.",{"type":39,"tag":119,"props":937,"children":938},{},[939,941,947],{"type":45,"value":940},"File output is token-efficient — the agent reads only the fields it needs\nusing ",{"type":39,"tag":270,"props":942,"children":944},{"className":943},[],[945],{"type":45,"value":946},"jp",{"type":45,"value":948}," or Python one-liners.",{"type":39,"tag":119,"props":950,"children":951},{},[952],{"type":45,"value":953},"Large stdout output wastes context window space.",{"type":39,"tag":103,"props":955,"children":957},{"id":956},"rule-5-instruction-only-pattern-only-when-no-code-is-needed",[958],{"type":45,"value":959},"Rule 5: Instruction-Only Pattern (Only When No Code Is Needed)",{"type":39,"tag":48,"props":961,"children":962},{},[963,965,970,972,977],{"type":45,"value":964},"Use this pattern ",{"type":39,"tag":54,"props":966,"children":967},{},[968],{"type":45,"value":969},"only",{"type":45,"value":971}," when the workflow requires ",{"type":39,"tag":54,"props":973,"children":974},{},[975],{"type":45,"value":976},"zero",{"type":45,"value":978}," programmatic work\n— i.e., every step is purely about orchestration, reasoning, multi-skill\ncoordination, or following a written protocol. If any step needs code (API\ncalls, data processing, file I\u002FO, etc.), use the CLI pattern from Rule 3\ninstead. Produce a SKILL.md with a structured workflow section:",{"type":39,"tag":980,"props":981,"children":986},"pre",{"className":982,"code":983,"language":984,"meta":985,"style":985},"language-markdown shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","## Workflow\n\n### 1. Step Name\n- Description of what to do\n- Which skill to use and how\n\n### 2. Next Step\n...\n","markdown","",[987],{"type":39,"tag":270,"props":988,"children":989},{"__ignoreMap":985},[990,1007,1016,1030,1045,1058,1066,1079],{"type":39,"tag":69,"props":991,"children":994},{"class":992,"line":993},"line",1,[995,1001],{"type":39,"tag":69,"props":996,"children":998},{"style":997},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[999],{"type":45,"value":1000},"## ",{"type":39,"tag":69,"props":1002,"children":1004},{"style":1003},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[1005],{"type":45,"value":1006},"Workflow\n",{"type":39,"tag":69,"props":1008,"children":1010},{"class":992,"line":1009},2,[1011],{"type":39,"tag":69,"props":1012,"children":1013},{"emptyLinePlaceholder":375},[1014],{"type":45,"value":1015},"\n",{"type":39,"tag":69,"props":1017,"children":1019},{"class":992,"line":1018},3,[1020,1025],{"type":39,"tag":69,"props":1021,"children":1022},{"style":997},[1023],{"type":45,"value":1024},"### ",{"type":39,"tag":69,"props":1026,"children":1027},{"style":1003},[1028],{"type":45,"value":1029},"1. Step Name\n",{"type":39,"tag":69,"props":1031,"children":1033},{"class":992,"line":1032},4,[1034,1039],{"type":39,"tag":69,"props":1035,"children":1036},{"style":997},[1037],{"type":45,"value":1038},"-",{"type":39,"tag":69,"props":1040,"children":1042},{"style":1041},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[1043],{"type":45,"value":1044}," Description of what to do\n",{"type":39,"tag":69,"props":1046,"children":1048},{"class":992,"line":1047},5,[1049,1053],{"type":39,"tag":69,"props":1050,"children":1051},{"style":997},[1052],{"type":45,"value":1038},{"type":39,"tag":69,"props":1054,"children":1055},{"style":1041},[1056],{"type":45,"value":1057}," Which skill to use and how\n",{"type":39,"tag":69,"props":1059,"children":1061},{"class":992,"line":1060},6,[1062],{"type":39,"tag":69,"props":1063,"children":1064},{"emptyLinePlaceholder":375},[1065],{"type":45,"value":1015},{"type":39,"tag":69,"props":1067,"children":1069},{"class":992,"line":1068},7,[1070,1074],{"type":39,"tag":69,"props":1071,"children":1072},{"style":997},[1073],{"type":45,"value":1024},{"type":39,"tag":69,"props":1075,"children":1076},{"style":1003},[1077],{"type":45,"value":1078},"2. Next Step\n",{"type":39,"tag":69,"props":1080,"children":1082},{"class":992,"line":1081},8,[1083],{"type":39,"tag":69,"props":1084,"children":1085},{"style":1041},[1086],{"type":45,"value":1087},"...\n",{"type":39,"tag":103,"props":1089,"children":1091},{"id":1090},"rule-6-skillmd-structure",[1092],{"type":45,"value":1093},"Rule 6: SKILL.md Structure",{"type":39,"tag":48,"props":1095,"children":1096},{},[1097],{"type":45,"value":1098},"Every generated SKILL.md must follow this structure:",{"type":39,"tag":980,"props":1100,"children":1102},{"className":982,"code":1101,"language":984,"meta":985,"style":985},"---\nname: {skill-name}\ndescription: >-\n  {description}\n---\n\n# {Skill Title}\n\n## Overview\n{Brief description of what the skill does.}\n\n## Dependencies\n{List of required skills, if any.}\n\n## Quick Start\n{Minimal example to get started.}\n\n## Utility Scripts (if CLI-based)\n{Document each subcommand with examples.}\n\n## Workflow (if instruction-only)\n{Numbered steps with clear instructions.}\n\n## Rate Limiting (if applicable)\n{Document rate limits and how they are enforced.}\n\n## Common Mistakes\n{List 2-3 common pitfalls.}\n",[1103],{"type":39,"tag":270,"props":1104,"children":1105},{"__ignoreMap":985},[1106,1114,1144,1168,1176,1183,1190,1203,1210,1223,1232,1240,1253,1262,1270,1283,1292,1300,1313,1322,1330,1343,1352,1360,1373,1382,1390,1403],{"type":39,"tag":69,"props":1107,"children":1108},{"class":992,"line":993},[1109],{"type":39,"tag":69,"props":1110,"children":1111},{"style":997},[1112],{"type":45,"value":1113},"---\n",{"type":39,"tag":69,"props":1115,"children":1116},{"class":992,"line":1009},[1117,1123,1128,1133,1139],{"type":39,"tag":69,"props":1118,"children":1120},{"style":1119},"--shiki-light:#E53935;--shiki-default:#F07178;--shiki-dark:#F07178",[1121],{"type":45,"value":1122},"name",{"type":39,"tag":69,"props":1124,"children":1125},{"style":997},[1126],{"type":45,"value":1127},":",{"type":39,"tag":69,"props":1129,"children":1130},{"style":997},[1131],{"type":45,"value":1132}," {",{"type":39,"tag":69,"props":1134,"children":1136},{"style":1135},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[1137],{"type":45,"value":1138},"skill-name",{"type":39,"tag":69,"props":1140,"children":1141},{"style":997},[1142],{"type":45,"value":1143},"}\n",{"type":39,"tag":69,"props":1145,"children":1146},{"class":992,"line":1018},[1147,1152,1156,1162],{"type":39,"tag":69,"props":1148,"children":1149},{"style":1119},[1150],{"type":45,"value":1151},"description",{"type":39,"tag":69,"props":1153,"children":1154},{"style":997},[1155],{"type":45,"value":1127},{"type":39,"tag":69,"props":1157,"children":1159},{"style":1158},"--shiki-light:#39ADB5;--shiki-light-font-style:italic;--shiki-default:#89DDFF;--shiki-default-font-style:italic;--shiki-dark:#89DDFF;--shiki-dark-font-style:italic",[1160],{"type":45,"value":1161}," >",{"type":39,"tag":69,"props":1163,"children":1165},{"style":1164},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[1166],{"type":45,"value":1167},"-\n",{"type":39,"tag":69,"props":1169,"children":1170},{"class":992,"line":1032},[1171],{"type":39,"tag":69,"props":1172,"children":1173},{"style":1135},[1174],{"type":45,"value":1175},"  {description}\n",{"type":39,"tag":69,"props":1177,"children":1178},{"class":992,"line":1047},[1179],{"type":39,"tag":69,"props":1180,"children":1181},{"style":997},[1182],{"type":45,"value":1113},{"type":39,"tag":69,"props":1184,"children":1185},{"class":992,"line":1060},[1186],{"type":39,"tag":69,"props":1187,"children":1188},{"emptyLinePlaceholder":375},[1189],{"type":45,"value":1015},{"type":39,"tag":69,"props":1191,"children":1192},{"class":992,"line":1068},[1193,1198],{"type":39,"tag":69,"props":1194,"children":1195},{"style":997},[1196],{"type":45,"value":1197},"# ",{"type":39,"tag":69,"props":1199,"children":1200},{"style":1003},[1201],{"type":45,"value":1202},"{Skill Title}\n",{"type":39,"tag":69,"props":1204,"children":1205},{"class":992,"line":1081},[1206],{"type":39,"tag":69,"props":1207,"children":1208},{"emptyLinePlaceholder":375},[1209],{"type":45,"value":1015},{"type":39,"tag":69,"props":1211,"children":1213},{"class":992,"line":1212},9,[1214,1218],{"type":39,"tag":69,"props":1215,"children":1216},{"style":997},[1217],{"type":45,"value":1000},{"type":39,"tag":69,"props":1219,"children":1220},{"style":1003},[1221],{"type":45,"value":1222},"Overview\n",{"type":39,"tag":69,"props":1224,"children":1226},{"class":992,"line":1225},10,[1227],{"type":39,"tag":69,"props":1228,"children":1229},{"style":1041},[1230],{"type":45,"value":1231},"{Brief description of what the skill does.}\n",{"type":39,"tag":69,"props":1233,"children":1235},{"class":992,"line":1234},11,[1236],{"type":39,"tag":69,"props":1237,"children":1238},{"emptyLinePlaceholder":375},[1239],{"type":45,"value":1015},{"type":39,"tag":69,"props":1241,"children":1243},{"class":992,"line":1242},12,[1244,1248],{"type":39,"tag":69,"props":1245,"children":1246},{"style":997},[1247],{"type":45,"value":1000},{"type":39,"tag":69,"props":1249,"children":1250},{"style":1003},[1251],{"type":45,"value":1252},"Dependencies\n",{"type":39,"tag":69,"props":1254,"children":1256},{"class":992,"line":1255},13,[1257],{"type":39,"tag":69,"props":1258,"children":1259},{"style":1041},[1260],{"type":45,"value":1261},"{List of required skills, if any.}\n",{"type":39,"tag":69,"props":1263,"children":1265},{"class":992,"line":1264},14,[1266],{"type":39,"tag":69,"props":1267,"children":1268},{"emptyLinePlaceholder":375},[1269],{"type":45,"value":1015},{"type":39,"tag":69,"props":1271,"children":1273},{"class":992,"line":1272},15,[1274,1278],{"type":39,"tag":69,"props":1275,"children":1276},{"style":997},[1277],{"type":45,"value":1000},{"type":39,"tag":69,"props":1279,"children":1280},{"style":1003},[1281],{"type":45,"value":1282},"Quick Start\n",{"type":39,"tag":69,"props":1284,"children":1286},{"class":992,"line":1285},16,[1287],{"type":39,"tag":69,"props":1288,"children":1289},{"style":1041},[1290],{"type":45,"value":1291},"{Minimal example to get started.}\n",{"type":39,"tag":69,"props":1293,"children":1295},{"class":992,"line":1294},17,[1296],{"type":39,"tag":69,"props":1297,"children":1298},{"emptyLinePlaceholder":375},[1299],{"type":45,"value":1015},{"type":39,"tag":69,"props":1301,"children":1303},{"class":992,"line":1302},18,[1304,1308],{"type":39,"tag":69,"props":1305,"children":1306},{"style":997},[1307],{"type":45,"value":1000},{"type":39,"tag":69,"props":1309,"children":1310},{"style":1003},[1311],{"type":45,"value":1312},"Utility Scripts (if CLI-based)\n",{"type":39,"tag":69,"props":1314,"children":1316},{"class":992,"line":1315},19,[1317],{"type":39,"tag":69,"props":1318,"children":1319},{"style":1041},[1320],{"type":45,"value":1321},"{Document each subcommand with examples.}\n",{"type":39,"tag":69,"props":1323,"children":1325},{"class":992,"line":1324},20,[1326],{"type":39,"tag":69,"props":1327,"children":1328},{"emptyLinePlaceholder":375},[1329],{"type":45,"value":1015},{"type":39,"tag":69,"props":1331,"children":1333},{"class":992,"line":1332},21,[1334,1338],{"type":39,"tag":69,"props":1335,"children":1336},{"style":997},[1337],{"type":45,"value":1000},{"type":39,"tag":69,"props":1339,"children":1340},{"style":1003},[1341],{"type":45,"value":1342},"Workflow (if instruction-only)\n",{"type":39,"tag":69,"props":1344,"children":1346},{"class":992,"line":1345},22,[1347],{"type":39,"tag":69,"props":1348,"children":1349},{"style":1041},[1350],{"type":45,"value":1351},"{Numbered steps with clear instructions.}\n",{"type":39,"tag":69,"props":1353,"children":1355},{"class":992,"line":1354},23,[1356],{"type":39,"tag":69,"props":1357,"children":1358},{"emptyLinePlaceholder":375},[1359],{"type":45,"value":1015},{"type":39,"tag":69,"props":1361,"children":1363},{"class":992,"line":1362},24,[1364,1368],{"type":39,"tag":69,"props":1365,"children":1366},{"style":997},[1367],{"type":45,"value":1000},{"type":39,"tag":69,"props":1369,"children":1370},{"style":1003},[1371],{"type":45,"value":1372},"Rate Limiting (if applicable)\n",{"type":39,"tag":69,"props":1374,"children":1376},{"class":992,"line":1375},25,[1377],{"type":39,"tag":69,"props":1378,"children":1379},{"style":1041},[1380],{"type":45,"value":1381},"{Document rate limits and how they are enforced.}\n",{"type":39,"tag":69,"props":1383,"children":1385},{"class":992,"line":1384},26,[1386],{"type":39,"tag":69,"props":1387,"children":1388},{"emptyLinePlaceholder":375},[1389],{"type":45,"value":1015},{"type":39,"tag":69,"props":1391,"children":1393},{"class":992,"line":1392},27,[1394,1398],{"type":39,"tag":69,"props":1395,"children":1396},{"style":997},[1397],{"type":45,"value":1000},{"type":39,"tag":69,"props":1399,"children":1400},{"style":1003},[1401],{"type":45,"value":1402},"Common Mistakes\n",{"type":39,"tag":69,"props":1404,"children":1406},{"class":992,"line":1405},28,[1407],{"type":39,"tag":69,"props":1408,"children":1409},{"style":1041},[1410],{"type":45,"value":1411},"{List 2-3 common pitfalls.}\n",{"type":39,"tag":103,"props":1413,"children":1415},{"id":1414},"rule-7-skill-placement",[1416],{"type":45,"value":1417},"Rule 7: Skill Placement",{"type":39,"tag":48,"props":1419,"children":1420},{},[1421,1423,1428,1430,1435],{"type":45,"value":1422},"Skills can be installed ",{"type":39,"tag":54,"props":1424,"children":1425},{},[1426],{"type":45,"value":1427},"locally",{"type":45,"value":1429}," (project-specific, per-workspace) or\n",{"type":39,"tag":54,"props":1431,"children":1432},{},[1433],{"type":45,"value":1434},"globally",{"type":45,"value":1436}," (available across all projects). Ask the user if they want to\ninstall locally, globally, or use a custom install path.",{"type":39,"tag":48,"props":1438,"children":1439},{},[1440],{"type":45,"value":1441},"Skill paths by agent CLI (local paths relative to project root):",{"type":39,"tag":254,"props":1443,"children":1444},{},[1445,1469,1491,1513,1535],{"type":39,"tag":119,"props":1446,"children":1447},{},[1448,1453,1455,1461,1463],{"type":39,"tag":54,"props":1449,"children":1450},{},[1451],{"type":45,"value":1452},"Claude Code",{"type":45,"value":1454},": local ",{"type":39,"tag":270,"props":1456,"children":1458},{"className":1457},[],[1459],{"type":45,"value":1460},".claude\u002Fskills\u002F",{"type":45,"value":1462},", global ",{"type":39,"tag":270,"props":1464,"children":1466},{"className":1465},[],[1467],{"type":45,"value":1468},"~\u002F.claude\u002Fskills\u002F",{"type":39,"tag":119,"props":1470,"children":1471},{},[1472,1477,1478,1484,1485],{"type":39,"tag":54,"props":1473,"children":1474},{},[1475],{"type":45,"value":1476},"Codex",{"type":45,"value":1454},{"type":39,"tag":270,"props":1479,"children":1481},{"className":1480},[],[1482],{"type":45,"value":1483},".agents\u002Fskills\u002F",{"type":45,"value":1462},{"type":39,"tag":270,"props":1486,"children":1488},{"className":1487},[],[1489],{"type":45,"value":1490},"~\u002F.agents\u002Fskills\u002F",{"type":39,"tag":119,"props":1492,"children":1493},{},[1494,1499,1500,1505,1507],{"type":39,"tag":54,"props":1495,"children":1496},{},[1497],{"type":45,"value":1498},"Antigravity 2.0",{"type":45,"value":1454},{"type":39,"tag":270,"props":1501,"children":1503},{"className":1502},[],[1504],{"type":45,"value":1483},{"type":45,"value":1506},", global\n",{"type":39,"tag":270,"props":1508,"children":1510},{"className":1509},[],[1511],{"type":45,"value":1512},"~\u002F.gemini\u002Fconfig\u002Fskills\u002F",{"type":39,"tag":119,"props":1514,"children":1515},{},[1516,1521,1522,1528,1529],{"type":39,"tag":54,"props":1517,"children":1518},{},[1519],{"type":45,"value":1520},"Gemini CLI",{"type":45,"value":1454},{"type":39,"tag":270,"props":1523,"children":1525},{"className":1524},[],[1526],{"type":45,"value":1527},".gemini\u002Fskills\u002F",{"type":45,"value":1462},{"type":39,"tag":270,"props":1530,"children":1532},{"className":1531},[],[1533],{"type":45,"value":1534},"~\u002F.gemini\u002Fskills\u002F",{"type":39,"tag":119,"props":1536,"children":1537},{},[1538,1543,1544,1550,1551],{"type":39,"tag":54,"props":1539,"children":1540},{},[1541],{"type":45,"value":1542},"OpenCode",{"type":45,"value":1454},{"type":39,"tag":270,"props":1545,"children":1547},{"className":1546},[],[1548],{"type":45,"value":1549},".opencode\u002Fskills\u002F",{"type":45,"value":1462},{"type":39,"tag":270,"props":1552,"children":1554},{"className":1553},[],[1555],{"type":45,"value":1556},"~\u002F.config\u002Fopencode\u002Fskills\u002F",{"type":39,"tag":48,"props":1558,"children":1559},{},[1560],{"type":45,"value":1561},"For other CLIs, find out local and global skill paths by yourself.",{"type":39,"tag":84,"props":1563,"children":1565},{"id":1564},"phase-4-validation",[1566],{"type":45,"value":1567},"Phase 4: Validation",{"type":39,"tag":48,"props":1569,"children":1570},{},[1571],{"type":45,"value":1572},"After implementation is complete:",{"type":39,"tag":115,"props":1574,"children":1575},{},[1576,1586],{"type":39,"tag":119,"props":1577,"children":1578},{},[1579,1584],{"type":39,"tag":54,"props":1580,"children":1581},{},[1582],{"type":45,"value":1583},"Test the skill manually",{"type":45,"value":1585}," by invoking the agent with a natural-language\nprompt that should trigger the new skill.",{"type":39,"tag":119,"props":1587,"children":1588},{},[1589,1594],{"type":39,"tag":54,"props":1590,"children":1591},{},[1592],{"type":45,"value":1593},"If a sample query\u002Fanswer was provided",{"type":45,"value":1595}," during brainstorming, run it\nthrough the skill and verify the output matches expectations.",{"type":39,"tag":1597,"props":1598,"children":1599},"style",{},[1600],{"type":45,"value":1601},"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":1603,"total":1773},[1604,1623,1638,1658,1670,1685,1701,1714,1726,1741,1752,1762],{"slug":1605,"name":1605,"fn":1606,"description":1607,"org":1608,"tags":1609,"stars":22,"repoUrl":23,"updatedAt":1622},"alphafold-database-fetch-and-analyze","retrieve and analyze AlphaFold protein structures","Retrieve and analyze AlphaFold predicted structures for a protein. Use when the user provides a specific UniProt Accession ID and wants structural confidence metrics (pLDDT), domain boundary analysis, or disorder assessment. Do not use if the user only has a protein name, gene name, or amino acid sequence — ask for a UniProt ID first.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1610,1613,1616,1619],{"name":1611,"slug":1612,"type":15},"Bioinformatics","bioinformatics",{"name":1614,"slug":1615,"type":15},"Genomics","genomics",{"name":1617,"slug":1618,"type":15},"Life Sciences","life-sciences",{"name":1620,"slug":1621,"type":15},"Research","research","2026-07-12T07:51:51.827211",{"slug":1624,"name":1624,"fn":1625,"description":1626,"org":1627,"tags":1628,"stars":22,"repoUrl":23,"updatedAt":1637},"alphagenome-single-variant-analysis","analyze genetic variant effects with AlphaGenome","Analyzes genetic variant effects on gene expression (RNA-seq), chromatin accessibility (DNASE), histone marks (ChIP), and transcription factors using the AlphaGenome API. Use when the user asks about non-coding variant effects, pathogenicity, clinical significance, disease associations, functional effects, gene expression changes, splicing disruption, or regulatory effects in promoters and enhancers. Also use for resolving biological terms to tissue\u002Fcell-type ontologies (UBERON\u002FCL) or analyzing variants in chr:pos:ref>alt format.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1629,1630,1633,1634],{"name":1611,"slug":1612,"type":15},{"name":1631,"slug":1632,"type":15},"Genetics","genetics",{"name":1620,"slug":1621,"type":15},{"name":1635,"slug":1636,"type":15},"RNA-seq","rna-seq","2026-07-12T07:51:39.494803",{"slug":1639,"name":1639,"fn":1640,"description":1641,"org":1642,"tags":1643,"stars":22,"repoUrl":23,"updatedAt":1657},"chembl-database","query ChEMBL database for bioactive molecules","Query the ChEMBL database for bioactive molecules, drug targets, bioactivity data, approved drugs, and chemical structures. Use when the user asks about compounds, targets, IC50\u002FKi values, drug mechanisms, or structure searches.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1644,1647,1650,1653,1656],{"name":1645,"slug":1646,"type":15},"ChEMBL","chembl",{"name":1648,"slug":1649,"type":15},"Chemistry","chemistry",{"name":1651,"slug":1652,"type":15},"Database","database",{"name":1654,"slug":1655,"type":15},"Pharmacology","pharmacology",{"name":1620,"slug":1621,"type":15},"2026-07-12T07:51:35.544306",{"slug":1659,"name":1659,"fn":1660,"description":1661,"org":1662,"tags":1663,"stars":22,"repoUrl":23,"updatedAt":1669},"clinical-trials-database","query clinical trial data","Query ClinicalTrials.gov via APIv2. Use when you want to search for trials by condition, drug, location, status, or phase; retrieve trial details by NCT ID; check eligibility\u002Finclusion criteria; count trials across conditions or time periods; identify a sponsor's trial portfolio; find recruiting trials for patient matching.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1664,1667,1668],{"name":1665,"slug":1666,"type":15},"Clinical Trials","clinical-trials",{"name":1617,"slug":1618,"type":15},{"name":1620,"slug":1621,"type":15},"2026-07-12T07:52:06.846705",{"slug":1671,"name":1671,"fn":1672,"description":1673,"org":1674,"tags":1675,"stars":22,"repoUrl":23,"updatedAt":1684},"clinvar-database","retrieve clinical significance from ClinVar database","Use when needing clinical significance, pathogenicity classifications (e.g., Pathogenic, Benign, VUS), clinical evidence rationales, or finding \"hard positive\" benchmark controls for human genomic variants.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1676,1679,1680,1683],{"name":1677,"slug":1678,"type":15},"ClinVar","clinvar",{"name":1631,"slug":1632,"type":15},{"name":1681,"slug":1682,"type":15},"Healthcare","healthcare",{"name":1620,"slug":1621,"type":15},"2026-07-12T07:51:36.86094",{"slug":1686,"name":1686,"fn":1687,"description":1688,"org":1689,"tags":1690,"stars":22,"repoUrl":23,"updatedAt":1700},"credentials","manage and verify API credentials safely","Instructions for handling API keys and credentials safely, verifying their presence, and prompting the user to add them if missing using a safe protocol.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1691,1694,1697],{"name":1692,"slug":1693,"type":15},"Compliance","compliance",{"name":1695,"slug":1696,"type":15},"Operations","operations",{"name":1698,"slug":1699,"type":15},"Security","security","2026-07-12T07:52:17.355491",{"slug":1702,"name":1702,"fn":1703,"description":1704,"org":1705,"tags":1706,"stars":22,"repoUrl":23,"updatedAt":1713},"dbsnp-database","search genetic variants in dbSNP database","Use when you want to look up, map, and search for short genetic variants (SNPs, indels) in NCBI's dbSNP database. Resolves between rsIDs, genomic coordinates in VCF format, and HGVS strings. For an rsID, returns variant type, gene associations, clinical significance, allele frequencies, and genomic coordinates (GRCh38).\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1707,1708,1709,1712],{"name":1611,"slug":1612,"type":15},{"name":1631,"slug":1632,"type":15},{"name":1710,"slug":1711,"type":15},"NCBI","ncbi",{"name":1620,"slug":1621,"type":15},"2026-07-12T07:51:33.054229",{"slug":1715,"name":1715,"fn":1716,"description":1717,"org":1718,"tags":1719,"stars":22,"repoUrl":23,"updatedAt":1725},"embl-ebi-ols","search biomedical ontologies in EMBL-EBI OLS","Query and search the EMBL-EBI Ontology Lookup Service (OLS) for biomedical ontology terms, definitions, and hierarchies across 250+ ontologies (e.g., GO, DOID, HP). Use when the user asks to search for terms, retrieve details, navigate hierarchies (parents, children, ancestors), look up properties and individuals, get autocomplete suggestions, or access ontology metadata and statistics.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1720,1721,1724],{"name":1611,"slug":1612,"type":15},{"name":1722,"slug":1723,"type":15},"Ontology","ontology",{"name":1620,"slug":1621,"type":15},"2026-07-12T07:51:59.368324",{"slug":1727,"name":1727,"fn":1728,"description":1729,"org":1730,"tags":1731,"stars":22,"repoUrl":23,"updatedAt":1740},"encode-ccres-database","query ENCODE regulatory and experimental data","Query the ENCODE Registry of cis-Regulatory Elements (cCREs) via the SCREEN GraphQL API, or make custom queries to the ENCODE Portal REST API for experiments and files (ChIP-seq peaks, etc.). Use when you want to query regulatory annotations or raw experimental data across human cell types.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1732,1733,1736,1737],{"name":1611,"slug":1612,"type":15},{"name":1734,"slug":1735,"type":15},"GraphQL","graphql",{"name":1620,"slug":1621,"type":15},{"name":1738,"slug":1739,"type":15},"REST API","rest-api","2026-07-12T07:52:10.597139",{"slug":1742,"name":1742,"fn":1743,"description":1744,"org":1745,"tags":1746,"stars":22,"repoUrl":23,"updatedAt":1751},"ensembl-database","query genomic and protein data from Ensembl","Query the Ensembl database to resolve gene, transcript, and protein IDs, fetch genomic or protein sequences, retrieve gene structures (exons), and get variant consequence and effect predictions (VEP). Use this skill as a primary ID translator, genomic sequence database and variant effect prediction tool.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1747,1748,1749,1750],{"name":1611,"slug":1612,"type":15},{"name":1631,"slug":1632,"type":15},{"name":1617,"slug":1618,"type":15},{"name":1620,"slug":1621,"type":15},"2026-07-12T07:51:41.645835",{"slug":1753,"name":1753,"fn":1754,"description":1755,"org":1756,"tags":1757,"stars":22,"repoUrl":23,"updatedAt":1761},"foldseek-structural-search","perform 3D protein structural searches","Performs 3D structural searches of proteins against various databases (PDB, AlphaFold, CATH, MGnify, etc.) using the Foldseek API. Use ONLY when the user provides a physical 3D coordinate file (.cif, .mmcif, or .pdb) and wants to find structurally similar proteins. Do NOT use if the user only provides a protein sequence, gene name, or UniProt ID.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1758,1759,1760],{"name":1611,"slug":1612,"type":15},{"name":1617,"slug":1618,"type":15},{"name":1620,"slug":1621,"type":15},"2026-07-12T07:52:09.354992",{"slug":1763,"name":1763,"fn":1764,"description":1765,"org":1766,"tags":1767,"stars":22,"repoUrl":23,"updatedAt":1772},"gnomad-database","query genetic variant data from gnomAD","Query the Genome Aggregation Database (gnomAD). Use when determining the rarity or allele frequency of specific genetic variants, retrieving gene constraint metrics (pLI, LOEUF) to assess loss-of-function intolerance, finding variants in a genomic region or gene, or querying structural variants. Don't use for analyzing individual patient genomes, tracking somatic mutations in cancer (use COSMIC), or requesting raw sequencing reads (use ENA).\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1768,1769,1770,1771],{"name":1611,"slug":1612,"type":15},{"name":1631,"slug":1632,"type":15},{"name":1617,"slug":1618,"type":15},{"name":1620,"slug":1621,"type":15},"2026-07-12T07:51:38.213009",38,{"items":1775,"total":1773},[1776,1783,1790,1798,1804,1811,1817],{"slug":1605,"name":1605,"fn":1606,"description":1607,"org":1777,"tags":1778,"stars":22,"repoUrl":23,"updatedAt":1622},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1779,1780,1781,1782],{"name":1611,"slug":1612,"type":15},{"name":1614,"slug":1615,"type":15},{"name":1617,"slug":1618,"type":15},{"name":1620,"slug":1621,"type":15},{"slug":1624,"name":1624,"fn":1625,"description":1626,"org":1784,"tags":1785,"stars":22,"repoUrl":23,"updatedAt":1637},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1786,1787,1788,1789],{"name":1611,"slug":1612,"type":15},{"name":1631,"slug":1632,"type":15},{"name":1620,"slug":1621,"type":15},{"name":1635,"slug":1636,"type":15},{"slug":1639,"name":1639,"fn":1640,"description":1641,"org":1791,"tags":1792,"stars":22,"repoUrl":23,"updatedAt":1657},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1793,1794,1795,1796,1797],{"name":1645,"slug":1646,"type":15},{"name":1648,"slug":1649,"type":15},{"name":1651,"slug":1652,"type":15},{"name":1654,"slug":1655,"type":15},{"name":1620,"slug":1621,"type":15},{"slug":1659,"name":1659,"fn":1660,"description":1661,"org":1799,"tags":1800,"stars":22,"repoUrl":23,"updatedAt":1669},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1801,1802,1803],{"name":1665,"slug":1666,"type":15},{"name":1617,"slug":1618,"type":15},{"name":1620,"slug":1621,"type":15},{"slug":1671,"name":1671,"fn":1672,"description":1673,"org":1805,"tags":1806,"stars":22,"repoUrl":23,"updatedAt":1684},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1807,1808,1809,1810],{"name":1677,"slug":1678,"type":15},{"name":1631,"slug":1632,"type":15},{"name":1681,"slug":1682,"type":15},{"name":1620,"slug":1621,"type":15},{"slug":1686,"name":1686,"fn":1687,"description":1688,"org":1812,"tags":1813,"stars":22,"repoUrl":23,"updatedAt":1700},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1814,1815,1816],{"name":1692,"slug":1693,"type":15},{"name":1695,"slug":1696,"type":15},{"name":1698,"slug":1699,"type":15},{"slug":1702,"name":1702,"fn":1703,"description":1704,"org":1818,"tags":1819,"stars":22,"repoUrl":23,"updatedAt":1713},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1820,1821,1822,1823],{"name":1611,"slug":1612,"type":15},{"name":1631,"slug":1632,"type":15},{"name":1710,"slug":1711,"type":15},{"name":1620,"slug":1621,"type":15}]