[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CGJS86EZAYVP24CNG8HJ6S":3,"skill-same:01M6CGJS86EZAYVP24CNG8HJ6S":95},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":16,"sourceHtmlUrl":17,"categories":18,"keywords":24,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":55,"updatedAt":56,"install":57,"resources":70},"01M6CGJS86EZAYVP24CNG8HJ6S","skill-creator",null,"Create or update Pi skills (SKILL.md plus optional scripts, references, or assets). Use when someone asks to design a new Pi skill, refine an existing one, or structure skills for Pi discovery or packaging.","Dicklesworthstone\u002Fpi_agent_rust","Dicklesworthstone","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F35050222?v=4","01M6CG26AR942CSVMN1M5E3DSE","Jeff Emanuel","01M6CG26EPP71PSHW1VDS71121",1992,"MIT","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fnpm\u002Fpi-extensions\u002Fextending-pi\u002Fskill-creator\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fnpm\u002Fpi-extensions\u002Fextending-pi\u002Fskill-creator\u002FSKILL.md",[19],{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"skill creator","creator","new","design","when","Existing","for","scripts","structure","refine","references","use","packaging","pi","assets","discovery","update","create","2026-11-10 10:12:30",false,"---\nname: skill-creator\ndescription: Create or update Pi skills (SKILL.md plus optional scripts, references, or assets). Use when someone asks to design a new Pi skill, refine an existing one, or structure skills for Pi discovery or packaging.\n---\n\n# Skill Creator\n\nProvide guidance for creating effective Pi skills.\n\n## Principles\n\n- **Conciseness**: the agent is already very capable - only domain-specific knowledge, workflows, and tooling it can't infer earn their token cost.\n- **Progressive disclosure**: Pi loads skills in tiers - frontmatter (always in context), body (on trigger), bundled resources (on demand) - so splitting content across them keeps context lean.\n- **Activation**: Pi decides whether to load a skill based solely on the frontmatter `description`. \"When to use\" information in the body comes too late.\n- **Context over directives**: the agent makes better decisions when it understands why. For tasks requiring judgment, context like \"X helps Y because Z\" is more robust than instructions like \"You MUST do X\".\n\n## Pi Agent Skills format\n\n- Required frontmatter: `name`, `description`. Directory name must equal `name`.\n- Name rules: 1–64 chars, lowercase letters\u002Fdigits\u002Fhyphens, no leading\u002Ftrailing\u002Fconsecutive hyphens.\n- Optional frontmatter: `license`, `compatibility`, `metadata` (arbitrary key-value pairs for tooling), `allowed-tools` (restrict which tools the skill may invoke).\n- `disable-model-invocation`: when set, Pi won't auto-trigger the skill; the user must invoke it explicitly with `\u002Fskill:name`.\n- Paths are relative to the skill directory; `{baseDir}` placeholders are not supported.\n- Skill locations: `~\u002F.pi\u002Fagent\u002Fskills\u002F`, `.pi\u002Fskills\u002F`, `skills\u002F` in a package, settings `skills`, or `--skill \u003Cpath>`.\n\n## Recommended structure\n\n```\npi-skill\u002F\n├── SKILL.md\n├── README.md         # Optional: human summary + installation\n├── scripts\u002F          # Optional executables\n├── references\u002F       # Optional docs loaded on demand\n└── assets\u002F           # Optional templates\u002Fassets\n```\n\n## Workflow\n\n### 1) Clarify use cases\n\n2-4 concrete example requests usually suffice to scope triggers and functionality.\n\n### 2) Plan reusable resources\n\nFor each example, decide if you need:\n- **scripts\u002F** for deterministic tasks\n- **references\u002F** for long docs or schemas\n- **assets\u002F** for templates or boilerplate\n\n### 3) Create the skeleton\n\nA skill needs a directory containing a SKILL.md. Only add resource sub-directories that are actually needed.\n\n```bash\nmkdir -p ~\u002F.pi\u002Fagent\u002Fskills\u002Fmy-skill\ntouch ~\u002F.pi\u002Fagent\u002Fskills\u002Fmy-skill\u002FSKILL.md\n```\n\n### 4) Optional: Write README.md (humans + installation)\n\nIf you plan to share the skill with humans, a README.md helps discovery and installation. If you have a README, installation info can live there to save space in SKILL.md.\n\n```markdown\n# My Skill\n\nShort summary for humans discovering the skill.\n\n## Installation\n`pi install git:github.com\u002Forg\u002Fmy-skill`\n```\n\n### 5) Write frontmatter\n\nUse only the fields you need.\n\n```markdown\n---\nname: my-skill\ndescription: What it does + when to use it.\n---\n```\n\nIf you need to hide auto-invocation, set:\n\n```yaml\ndisable-model-invocation: true\n```\n\n### 6) Write the body\n\n- Imperative phrasing works well for procedural instructions; context framing works better for guidance (see Principles).\n- ~500 lines is a practical ceiling for SKILL.md; beyond that, split content into references.\n- The agent won't know a reference file exists unless SKILL.md says when to read it.\n\n### 7) Add resources\n\nSKILL.md is the agent's interface to the skill — usage examples and input\u002Foutput descriptions let it call scripts without needing to understand internals.\n\n- **scripts\u002F**: usage examples in SKILL.md inform the agent how to call them; scripts should be executable.\n- **references\u002F**: a table of contents helps the agent navigate files longer than ~100 lines. References work best one level deep from SKILL.md, and each fact should live in one place (SKILL.md or a reference, not both).\n- **assets\u002F**: templates, boilerplate, or data used in final output — typically not loaded into context.\n\n### 8) Validate and test\n\n- Run the validator script:\n\n```bash\nscripts\u002Fvalidate_skill.py \u002Fpath\u002Fto\u002Fmy-skill\n```\n\n- Load only the skill to spot warnings:\n\n```bash\npi --no-skills --skill \u002Fpath\u002Fto\u002Fmy-skill\n```\n\n- Invoke it explicitly:\n\n```bash\n\u002Fskill:my-skill\n```\n\n- After edits, use `\u002Freload`.\n\n### 9) Publish (optional)\n\nTo share beyond a single machine, publish as a Pi package (package.json-based, not a .skill archive).\n\n- Add `package.json` with a `pi` manifest (or rely on the conventional `skills\u002F` directory).\n- Add `\"keywords\": [\"pi-package\"]` for discoverability.\n- Publish to npm or host in git; install with `pi install \u003Csource>` and enable via `pi config` if needed.\n\n```json\n{\n  \"name\": \"my-pi-skills\",\n  \"keywords\": [\"pi-package\"],\n  \"pi\": { \"skills\": [\".\u002Fskills\"] }\n}\n```\n","# Skill Creator\n\nProvide guidance for creating effective Pi skills.\n\n## Principles\n\n- **Conciseness**: the agent is already very capable - only domain-specific knowledge, workflows, and tooling it can't infer earn their token cost.\n- **Progressive disclosure**: Pi loads skills in tiers - frontmatter (always in context), body (on trigger), bundled resources (on demand) - so splitting content across them keeps context lean.\n- **Activation**: Pi decides whether to load a skill based solely on the frontmatter `description`. \"When to use\" information in the body comes too late.\n- **Context over directives**: the agent makes better decisions when it understands why. For tasks requiring judgment, context like \"X helps Y because Z\" is more robust than instructions like \"You MUST do X\".\n\n## Pi Agent Skills format\n\n- Required frontmatter: `name`, `description`. Directory name must equal `name`.\n- Name rules: 1–64 chars, lowercase letters\u002Fdigits\u002Fhyphens, no leading\u002Ftrailing\u002Fconsecutive hyphens.\n- Optional frontmatter: `license`, `compatibility`, `metadata` (arbitrary key-value pairs for tooling), `allowed-tools` (restrict which tools the skill may invoke).\n- `disable-model-invocation`: when set, Pi won't auto-trigger the skill; the user must invoke it explicitly with `\u002Fskill:name`.\n- Paths are relative to the skill directory; `{baseDir}` placeholders are not supported.\n- Skill locations: `~\u002F.pi\u002Fagent\u002Fskills\u002F`, `.pi\u002Fskills\u002F`, `skills\u002F` in a package, settings `skills`, or `--skill \u003Cpath>`.\n\n## Recommended structure\n\n```\npi-skill\u002F\n├── SKILL.md\n├── README.md         # Optional: human summary + installation\n├── scripts\u002F          # Optional executables\n├── references\u002F       # Optional docs loaded on demand\n└── assets\u002F           # Optional templates\u002Fassets\n```\n\n## Workflow\n\n### 1) Clarify use cases\n\n2-4 concrete example requests usually suffice to scope triggers and functionality.\n\n### 2) Plan reusable resources\n\nFor each example, decide if you need:\n- **scripts\u002F** for deterministic tasks\n- **references\u002F** for long docs or schemas\n- **assets\u002F** for templates or boilerplate\n\n### 3) Create the skeleton\n\nA skill needs a directory containing a SKILL.md. Only add resource sub-directories that are actually needed.\n\n```bash\nmkdir -p ~\u002F.pi\u002Fagent\u002Fskills\u002Fmy-skill\ntouch ~\u002F.pi\u002Fagent\u002Fskills\u002Fmy-skill\u002FSKILL.md\n```\n\n### 4) Optional: Write README.md (humans + installation)\n\nIf you plan to share the skill with humans, a README.md helps discovery and installation. If you have a README, installation info can live there to save space in SKILL.md.\n\n```markdown\n# My Skill\n\nShort summary for humans discovering the skill.\n\n## Installation\n`pi install git:github.com\u002Forg\u002Fmy-skill`\n```\n\n### 5) Write frontmatter\n\nUse only the fields you need.\n\n```markdown\n---\nname: my-skill\ndescription: What it does + when to use it.\n---\n```\n\nIf you need to hide auto-invocation, set:\n\n```yaml\ndisable-model-invocation: true\n```\n\n### 6) Write the body\n\n- Imperative phrasing works well for procedural instructions; context framing works better for guidance (see Principles).\n- ~500 lines is a practical ceiling for SKILL.md; beyond that, split content into references.\n- The agent won't know a reference file exists unless SKILL.md says when to read it.\n\n### 7) Add resources\n\nSKILL.md is the agent's interface to the skill — usage examples and input\u002Foutput descriptions let it call scripts without needing to understand internals.\n\n- **scripts\u002F**: usage examples in SKILL.md inform the agent how to call them; scripts should be executable.\n- **references\u002F**: a table of contents helps the agent navigate files longer than ~100 lines. References work best one level deep from SKILL.md, and each fact should live in one place (SKILL.md or a reference, not both).\n- **assets\u002F**: templates, boilerplate, or data used in final output — typically not loaded into context.\n\n### 8) Validate and test\n\n- Run the validator script:\n\n```bash\nscripts\u002Fvalidate_skill.py \u002Fpath\u002Fto\u002Fmy-skill\n```\n\n- Load only the skill to spot warnings:\n\n```bash\npi --no-skills --skill \u002Fpath\u002Fto\u002Fmy-skill\n```\n\n- Invoke it explicitly:\n\n```bash\n\u002Fskill:my-skill\n```\n\n- After edits, use `\u002Freload`.\n\n### 9) Publish (optional)\n\nTo share beyond a single machine, publish as a Pi package (package.json-based, not a .skill archive).\n\n- Add `package.json` with a `pi` manifest (or rely on the conventional `skills\u002F` directory).\n- Add `\"keywords\": [\"pi-package\"]` for discoverability.\n- Publish to npm or host in git; install with `pi install \u003Csource>` and enable via `pi config` if needed.\n\n```json\n{\n  \"name\": \"my-pi-skills\",\n  \"keywords\": [\"pi-package\"],\n  \"pi\": { \"skills\": [\".\u002Fskills\"] }\n}\n```\n",{"name":5,"description":7},"main","7439377908fdee98c9bb5863391212b95453de95","tests\u002Fext_conformance\u002Fartifacts\u002Fnpm\u002Fpi-extensions\u002Fextending-pi\u002Fskill-creator",233,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust","https:\u002F\u002Fgithub.com\u002FDicklesworthstone","https:\u002F\u002Fwww.jeffreyemanuel.com\u002F","Building in NY","2026-11-15 01:54:15",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add Dicklesworthstone\u002Fpi_agent_rust --skill skill-creator",{"tool":63,"command":64},"bunx","bunx skills add Dicklesworthstone\u002Fpi_agent_rust --skill skill-creator",{"tool":66,"command":67},"pnpm","pnpm dlx skills add Dicklesworthstone\u002Fpi_agent_rust --skill skill-creator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fnpm\u002Fpi-extensions\u002Fextending-pi\u002Fskill-creator\u002FSKILL.md",true,[71,77,81,85,89],{"path":72,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":75,"sourceHtmlUrl":76},"CHANGELOG.md","REFERENCE","参考文档",688,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fnpm\u002Fpi-extensions\u002Fextending-pi\u002Fskill-creator\u002FCHANGELOG.md",{"path":78,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":16},"LICENSE","许可证",1071,{"path":82,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":83,"sourceHtmlUrl":84},"package.json",597,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fnpm\u002Fpi-extensions\u002Fextending-pi\u002Fskill-creator\u002Fpackage.json",{"path":86,"resourceType":73,"resourceTypeDesc":74,"sizeBytes":87,"sourceHtmlUrl":88},"README.md",166,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fnpm\u002Fpi-extensions\u002Fextending-pi\u002Fskill-creator\u002FREADME.md",{"path":90,"resourceType":91,"resourceTypeDesc":92,"sizeBytes":93,"sourceHtmlUrl":94},"scripts\u002Fvalidate_skill.py","SCRIPT","脚本",6501,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fnpm\u002Fpi-extensions\u002Fextending-pi\u002Fskill-creator\u002Fscripts\u002Fvalidate_skill.py",[96,128,162,185,211,229],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":107,"publishedAt":127},"01M6FCR7G5A005P364Z6ZWCJDP","theme-factory","Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors\u002Ffonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fcreative-design\u002Ftheme-factory\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fcreative-design\u002Ftheme-factory\u002FSKILL.md",[104],{"categoryNo":105,"categoryName":106,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000015","视觉设计",[108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126],"theme factory","factory","theme","docs","toolkit","generate","artifacts","SET","fly","slides","landing","html","styling","artifact","pages","themes","with","you","fonts","2026-11-11 15:11:14",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":132,"sourceHtmlUrl":133,"categories":134,"keywords":138,"publishedAt":43},"01M6FEGPPK0ZTKCCM0R3E3KS33","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[135],{"categoryNo":136,"categoryName":137,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000009","前端开发",[139,140,114,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,36,119,156,157,158,159,31,160,161],"web artifacts builder","web","artifacts builder","builder","frontend","css","components","react","component","routing","state management","state","shadcn","file","ui","Tools","Tailwind","single-file","simple","ui components","multi","jsx","suite",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":166,"sourceHtmlUrl":167,"categories":168,"keywords":173,"publishedAt":43},"01M6FEE9VTK1W4GY21AKREJXRG","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[169,172],{"categoryNo":170,"categoryName":171,"taxonomyType":22,"taxonomyTypeDesc":23},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":136,"categoryName":137,"taxonomyType":22,"taxonomyTypeDesc":23},[174,175,176,143,177,178,140,179,112,180,153,181,182,183,184,124,31],"testing","webapp testing","webapp","screenshots","playwright","debugging","browser","logs","applications","behavior","local",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":189,"sourceHtmlUrl":190,"categories":191,"keywords":192,"publishedAt":43},"01M6FE20F7ZTQBFWKF4MPJ2SBX","neuropixels-analysis","Neuropixels neural recording analysis. Load SpikeGLX\u002FOpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen\u002FIBL curation, AI-assisted visual analysis, for Neuropixels 1.0\u002F2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FSKILL.md",[],[193,194,195,196,197,198,199,200,36,201,202,203,204,205,206,207,124,208,209,210,31,29],"analysis","neuropixels analysis","spike","metrics","data","open","quality","user","recordings","Neural","motion","visual","quality metrics","unit","sorting","curation","recording","load",{"skillNo":212,"name":5,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":100,"licenseFileUrl":214,"sourceHtmlUrl":215,"categories":216,"keywords":218,"publishedAt":43},"01M6FDP0PDK6F1GGX395C7625Z","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fskill-creator\u002FSKILL.md",[217],{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},[25,26,219,42,41,220,221,222,223,224,225,226,227,228,124,31,30,29,27],"workflows","capabilities","knowledge","tool","integrations","specialized","guide","new skill","existing skill","users",{"skillNo":230,"name":231,"nameZh":6,"description":232,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":233,"sourceHtmlUrl":234,"categories":235,"keywords":237,"publishedAt":43},"01M6FDM8Y7VK7NYG9SM7QPA3PW","notebooklm","Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fnotebooklm\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fnotebooklm\u002FSKILL.md",[236],{"categoryNo":20,"categoryName":21,"taxonomyType":22,"taxonomyTypeDesc":23},[231,238,239,240,241,242,243,180,244,245,36,246,247,248,249,31,250],"google","browser automation","gemini","automation","auth","code","library","management","only","document","query","Citation","source"]