[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70P0WMV5XT0EEC0N445PW07":3,"skill-same:01M70P0WMV5XT0EEC0N445PW07":78},{"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":6,"sourceHtmlUrl":16,"categories":17,"keywords":34,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M70P0WMV5XT0EEC0N445PW07","writing-skills",null,"How to write SKILL.md files that trigger reliably and teach effectively. Use when creating, improving, or reviewing Claude Code skills.","shengdabai\u002FTony-Claude-Code-Skills","shengdabai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F116417419?v=4","01M70F6D2WY5PQV5A92BKYJQEW","Tony Sheng","01M70F6D3GAAAYZ5H4CC1G8VXM",3,"MIT","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fxiaolai\u002Fnlpm\u002Fskills\u002Fnlpm\u002Fwriting-skills\u002FSKILL.md",[18,23,26,31],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":32,"categoryName":33,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000036","内容创作者",[35,36,37,38,39,40,41,42,43,44,45,46,47],"writing","writing skills","trigger","how to","files","claude code skills","use","when","code","how","write","write skill","teach","2026-11-10 10:12:30",false,"---\nname: writing-skills\ndescription: \"How to write SKILL.md files that trigger reliably and teach effectively. Use when creating, improving, or reviewing Claude Code skills.\"\nversion: 0.1.0\n---\n\n# Writing Skills\n\n> Scope: covers SKILL.md authoring. For agent writing, see [[writing-agents]]. For plugin architecture, see [[writing-plugins]].\n\n## 1. The Description is Everything\n\nThe `description` field determines when Claude loads this skill. It is not a summary -- it is a **trigger mechanism**.\n\n**Bad** (score 55):\n```yaml\ndescription: \"Helpful skill for React development\"\n```\n\n**Good** (score 95):\n```yaml\ndescription: \"Use when building React components, debugging re-renders, optimizing performance with useMemo\u002FuseCallback, or fixing hook dependency arrays\"\n```\n\n### Description Checklist\n\n| Criterion | Test |\n|-----------|------|\n| 3+ trigger phrases | Count distinct action phrases separated by commas |\n| Action-oriented | Starts with \"Use when...\" or \"How to...\" |\n| Includes tool\u002Fframework name | The technology name appears explicitly |\n| Matches real queries | Would a user's actual question contain any of your trigger words? |\n\n### Trigger Phrase Construction\n\nMap real user queries to trigger phrases:\n\n| User says | Trigger phrase to include |\n|-----------|--------------------------|\n| \"My component re-renders too much\" | \"debugging re-renders\" |\n| \"How do I memoize this?\" | \"optimizing performance with useMemo\u002FuseCallback\" |\n| \"My useEffect runs in a loop\" | \"fixing hook dependency arrays\" |\n| \"I need a new component for...\" | \"building React components\" |\n\n**Rule**: if you can't list 3 real user queries that match your description, rewrite it.\n\n## 2. Body Structure\n\n### Section Order\n\n1. **Scope note** (if related skills exist) -- tells Claude when to use THIS skill vs another\n2. **Most commonly needed patterns** -- what users ask about 80% of the time\n3. **Decision matrices** -- when to use A vs B (tables)\n4. **Worked examples** -- before\u002Fafter with scores\n5. **Common mistakes** -- anti-patterns to avoid\n6. **References** -- links to deep dives\n\n### Heading Rules\n\n- H1 (`#`): skill title only (one per file)\n- H2 (`##`): major sections (numbered: `## 1. Section Name`)\n- H3 (`###`): subsections within a major section\n- Never skip heading levels (no H2 followed directly by H4)\n\n### Code Examples\n\nEvery code example must show the **problem**, then the **solution**:\n\n```markdown\n### Bad (breaks on concurrent requests)\n` ` `python\nglobal_state = {}  # shared mutable state\n` ` `\n\n### Good (request-scoped)\n` ` `python\ndef handler(request):\n    state = {}  # local to this request\n` ` `\n```\n\n**Rules for code examples:**\n- Runnable, not pseudocode\n- Contextual -- show enough surrounding code to understand placement\n- Annotated -- comment the critical line, not every line\n\n## 3. Progressive Disclosure\n\nKeep SKILL.md under 500 lines. Use the file system for depth:\n\n```\nskills\u002Fmy-domain\u002Fmy-skill\u002F\n  SKILL.md          # core patterns (\u003C 500 lines)\n  references\u002F       # deep dives, edge cases, full API docs\n    advanced.md\n    api-reference.md\n  examples\u002F         # working code samples\n    basic-setup.ts\n    advanced-config.ts\n  scripts\u002F          # utility scripts\n    validate.sh\n```\n\n### When to Extract to references\u002F\n\n| Content type | Keep in SKILL.md? | Extract to references\u002F? |\n|-------------|-------------------|------------------------|\n| Top 5 patterns everyone needs | Yes | No |\n| Full API reference (50+ entries) | No | Yes |\n| Edge cases (\u003C 5% of users) | No | Yes |\n| Configuration matrix (20+ options) | No | Yes |\n| Quick decision table (\u003C 10 rows) | Yes | No |\n\n## 4. Worked Example: Improving a Skill\n\n### Before (score 55\u002F100)\n\n```yaml\n---\nname: docker-helper\ndescription: \"Information about Docker\"\nversion: 0.1.0\n---\n```\n\n```markdown\n# Docker Helper\n\nDocker is a containerization platform. Here are some useful commands.\n\n## Commands\n- `docker build` - builds an image\n- `docker run` - runs a container\n- `docker ps` - lists containers\n\n## Dockerfile\nA Dockerfile contains instructions for building an image.\n\n## Docker Compose\nDocker Compose is for multi-container applications.\n```\n\n**Problems:**\n- Description is a label, not a trigger mechanism (0 trigger phrases)\n- Body teaches theory Claude already knows from training\n- No code examples showing problem\u002Fsolution\n- No decision matrices\n- No scope note\n\n### After (score 92\u002F100)\n\n```yaml\n---\nname: docker-helper\ndescription: \"Use when writing Dockerfiles, debugging container networking, optimizing image size with multi-stage builds, or configuring Docker Compose services. Covers build cache, volume mounts, health checks, and compose profiles.\"\nversion: 0.1.0\n---\n```\n\n```markdown\n# Docker Helper\n\n> Scope: covers Docker CLI, Dockerfiles, and Compose. For Kubernetes deployment, see [[k8s-deploy]].\n\n## 1. Image Size Optimization\n\n### Before (1.2 GB)\n` ` `dockerfile\nFROM node:20\nCOPY . .\nRUN npm install\nRUN npm run build\nCMD [\"node\", \"dist\u002Findex.js\"]\n` ` `\n\n### After (148 MB -- 88% smaller)\n` ` `dockerfile\nFROM node:20-slim AS build\nWORKDIR \u002Fapp\nCOPY package*.json .\u002F\nRUN npm ci --only=production\nCOPY . .\nRUN npm run build\n\nFROM node:20-slim\nWORKDIR \u002Fapp\nCOPY --from=build \u002Fapp\u002Fdist .\u002Fdist\nCOPY --from=build \u002Fapp\u002Fnode_modules .\u002Fnode_modules\nCMD [\"node\", \"dist\u002Findex.js\"]\n` ` `\n\nKey changes: multi-stage build, slim base, copy only production artifacts.\n\n## 2. Base Image Selection\n\n| Use case | Base image | Size |\n|----------|-----------|------|\n| Node.js production | node:20-slim | 180 MB |\n| Node.js minimal | node:20-alpine | 130 MB |\n| Python production | python:3.12-slim | 150 MB |\n| Static files only | nginx:alpine | 40 MB |\n| From scratch (Go\u002FRust) | scratch | \u003C 20 MB |\n```\n\n**Changes made:**\n1. Description: 0 trigger phrases -> 8 trigger phrases (+37 points)\n2. Scope note added (+5 points)\n3. Replaced theory with problem\u002Fsolution examples (+25 points)\n4. Added decision matrix (+10 points)\n5. Removed content Claude knows from training (-15 lines, +5 points for conciseness)\n\n## 5. Common Mistakes\n\n| Mistake | Why it hurts | Fix |\n|---------|-------------|-----|\n| Description is a feature list | Claude can't match user queries to the skill | Rewrite as trigger phrases starting with \"Use when...\" |\n| Body teaches theory | Wastes tokens on content Claude already knows | Show patterns and decisions, not definitions |\n| Over 500 lines | Bloats context window, penalized by linters | Extract to references\u002F, keep core patterns only |\n| No scope note | Claude doesn't know when to use THIS skill vs a related one | Add scope note referencing related skills |\n| Pseudocode examples | Not actionable, can't be copy-pasted | Use runnable code with enough context |\n| Every section has equal weight | Buries the most useful content | Lead with the 80% patterns, push edge cases to references\u002F |\n\n## 6. Quality Checklist\n\nBefore shipping a skill, verify:\n\n- [ ] Description has 3+ specific trigger phrases\n- [ ] Description starts with \"Use when...\" or \"How to...\"\n- [ ] Scope note present (if related skills exist)\n- [ ] H2 sections numbered, H3 subsections under them\n- [ ] Code examples show problem then solution\n- [ ] Decision tables for A-vs-B choices\n- [ ] Total lines \u003C 500\n- [ ] No content Claude already knows from training\n- [ ] At least one worked example with before\u002Fafter\n","# Writing Skills\n\n> Scope: covers SKILL.md authoring. For agent writing, see [[writing-agents]]. For plugin architecture, see [[writing-plugins]].\n\n## 1. The Description is Everything\n\nThe `description` field determines when Claude loads this skill. It is not a summary -- it is a **trigger mechanism**.\n\n**Bad** (score 55):\n```yaml\ndescription: \"Helpful skill for React development\"\n```\n\n**Good** (score 95):\n```yaml\ndescription: \"Use when building React components, debugging re-renders, optimizing performance with useMemo\u002FuseCallback, or fixing hook dependency arrays\"\n```\n\n### Description Checklist\n\n| Criterion | Test |\n|-----------|------|\n| 3+ trigger phrases | Count distinct action phrases separated by commas |\n| Action-oriented | Starts with \"Use when...\" or \"How to...\" |\n| Includes tool\u002Fframework name | The technology name appears explicitly |\n| Matches real queries | Would a user's actual question contain any of your trigger words? |\n\n### Trigger Phrase Construction\n\nMap real user queries to trigger phrases:\n\n| User says | Trigger phrase to include |\n|-----------|--------------------------|\n| \"My component re-renders too much\" | \"debugging re-renders\" |\n| \"How do I memoize this?\" | \"optimizing performance with useMemo\u002FuseCallback\" |\n| \"My useEffect runs in a loop\" | \"fixing hook dependency arrays\" |\n| \"I need a new component for...\" | \"building React components\" |\n\n**Rule**: if you can't list 3 real user queries that match your description, rewrite it.\n\n## 2. Body Structure\n\n### Section Order\n\n1. **Scope note** (if related skills exist) -- tells Claude when to use THIS skill vs another\n2. **Most commonly needed patterns** -- what users ask about 80% of the time\n3. **Decision matrices** -- when to use A vs B (tables)\n4. **Worked examples** -- before\u002Fafter with scores\n5. **Common mistakes** -- anti-patterns to avoid\n6. **References** -- links to deep dives\n\n### Heading Rules\n\n- H1 (`#`): skill title only (one per file)\n- H2 (`##`): major sections (numbered: `## 1. Section Name`)\n- H3 (`###`): subsections within a major section\n- Never skip heading levels (no H2 followed directly by H4)\n\n### Code Examples\n\nEvery code example must show the **problem**, then the **solution**:\n\n```markdown\n### Bad (breaks on concurrent requests)\n` ` `python\nglobal_state = {}  # shared mutable state\n` ` `\n\n### Good (request-scoped)\n` ` `python\ndef handler(request):\n    state = {}  # local to this request\n` ` `\n```\n\n**Rules for code examples:**\n- Runnable, not pseudocode\n- Contextual -- show enough surrounding code to understand placement\n- Annotated -- comment the critical line, not every line\n\n## 3. Progressive Disclosure\n\nKeep SKILL.md under 500 lines. Use the file system for depth:\n\n```\nskills\u002Fmy-domain\u002Fmy-skill\u002F\n  SKILL.md          # core patterns (\u003C 500 lines)\n  references\u002F       # deep dives, edge cases, full API docs\n    advanced.md\n    api-reference.md\n  examples\u002F         # working code samples\n    basic-setup.ts\n    advanced-config.ts\n  scripts\u002F          # utility scripts\n    validate.sh\n```\n\n### When to Extract to references\u002F\n\n| Content type | Keep in SKILL.md? | Extract to references\u002F? |\n|-------------|-------------------|------------------------|\n| Top 5 patterns everyone needs | Yes | No |\n| Full API reference (50+ entries) | No | Yes |\n| Edge cases (\u003C 5% of users) | No | Yes |\n| Configuration matrix (20+ options) | No | Yes |\n| Quick decision table (\u003C 10 rows) | Yes | No |\n\n## 4. Worked Example: Improving a Skill\n\n### Before (score 55\u002F100)\n\n```yaml\n---\nname: docker-helper\ndescription: \"Information about Docker\"\nversion: 0.1.0\n---\n```\n\n```markdown\n# Docker Helper\n\nDocker is a containerization platform. Here are some useful commands.\n\n## Commands\n- `docker build` - builds an image\n- `docker run` - runs a container\n- `docker ps` - lists containers\n\n## Dockerfile\nA Dockerfile contains instructions for building an image.\n\n## Docker Compose\nDocker Compose is for multi-container applications.\n```\n\n**Problems:**\n- Description is a label, not a trigger mechanism (0 trigger phrases)\n- Body teaches theory Claude already knows from training\n- No code examples showing problem\u002Fsolution\n- No decision matrices\n- No scope note\n\n### After (score 92\u002F100)\n\n```yaml\n---\nname: docker-helper\ndescription: \"Use when writing Dockerfiles, debugging container networking, optimizing image size with multi-stage builds, or configuring Docker Compose services. Covers build cache, volume mounts, health checks, and compose profiles.\"\nversion: 0.1.0\n---\n```\n\n```markdown\n# Docker Helper\n\n> Scope: covers Docker CLI, Dockerfiles, and Compose. For Kubernetes deployment, see [[k8s-deploy]].\n\n## 1. Image Size Optimization\n\n### Before (1.2 GB)\n` ` `dockerfile\nFROM node:20\nCOPY . .\nRUN npm install\nRUN npm run build\nCMD [\"node\", \"dist\u002Findex.js\"]\n` ` `\n\n### After (148 MB -- 88% smaller)\n` ` `dockerfile\nFROM node:20-slim AS build\nWORKDIR \u002Fapp\nCOPY package*.json .\u002F\nRUN npm ci --only=production\nCOPY . .\nRUN npm run build\n\nFROM node:20-slim\nWORKDIR \u002Fapp\nCOPY --from=build \u002Fapp\u002Fdist .\u002Fdist\nCOPY --from=build \u002Fapp\u002Fnode_modules .\u002Fnode_modules\nCMD [\"node\", \"dist\u002Findex.js\"]\n` ` `\n\nKey changes: multi-stage build, slim base, copy only production artifacts.\n\n## 2. Base Image Selection\n\n| Use case | Base image | Size |\n|----------|-----------|------|\n| Node.js production | node:20-slim | 180 MB |\n| Node.js minimal | node:20-alpine | 130 MB |\n| Python production | python:3.12-slim | 150 MB |\n| Static files only | nginx:alpine | 40 MB |\n| From scratch (Go\u002FRust) | scratch | \u003C 20 MB |\n```\n\n**Changes made:**\n1. Description: 0 trigger phrases -> 8 trigger phrases (+37 points)\n2. Scope note added (+5 points)\n3. Replaced theory with problem\u002Fsolution examples (+25 points)\n4. Added decision matrix (+10 points)\n5. Removed content Claude knows from training (-15 lines, +5 points for conciseness)\n\n## 5. Common Mistakes\n\n| Mistake | Why it hurts | Fix |\n|---------|-------------|-----|\n| Description is a feature list | Claude can't match user queries to the skill | Rewrite as trigger phrases starting with \"Use when...\" |\n| Body teaches theory | Wastes tokens on content Claude already knows | Show patterns and decisions, not definitions |\n| Over 500 lines | Bloats context window, penalized by linters | Extract to references\u002F, keep core patterns only |\n| No scope note | Claude doesn't know when to use THIS skill vs a related one | Add scope note referencing related skills |\n| Pseudocode examples | Not actionable, can't be copy-pasted | Use runnable code with enough context |\n| Every section has equal weight | Buries the most useful content | Lead with the 80% patterns, push edge cases to references\u002F |\n\n## 6. Quality Checklist\n\nBefore shipping a skill, verify:\n\n- [ ] Description has 3+ specific trigger phrases\n- [ ] Description starts with \"Use when...\" or \"How to...\"\n- [ ] Scope note present (if related skills exist)\n- [ ] H2 sections numbered, H3 subsections under them\n- [ ] Code examples show problem then solution\n- [ ] Decision tables for A-vs-B choices\n- [ ] Total lines \u003C 500\n- [ ] No content Claude already knows from training\n- [ ] At least one worked example with before\u002Fafter\n",{"name":5,"version":53,"description":7},"0.1.0","main","7850740bd837adb32f0a109ab2af82482196c6f2","skills\u002Fxiaolai\u002Fnlpm\u002Fskills\u002Fnlpm\u002Fwriting-skills",1,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills","https:\u002F\u002Fzturnsgo.com","https:\u002F\u002Fgithub.com\u002Fshengdabai","https:\u002F\u002Fzturnsgo.com\u002F","AI × education creator — producer, not consumer. Taught 6,000+ learners; shipping learning tools & daily essays with Claude Code, practicing @xiaolai's way 🥋","2026-11-01 21:28:23",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add shengdabai\u002FTony-Claude-Code-Skills --skill writing-skills",{"tool":70,"command":71},"bunx","bunx skills add shengdabai\u002FTony-Claude-Code-Skills --skill writing-skills",{"tool":73,"command":74},"pnpm","pnpm dlx skills add shengdabai\u002FTony-Claude-Code-Skills --skill writing-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fxiaolai\u002Fnlpm\u002Fskills\u002Fnlpm\u002Fwriting-skills\u002FSKILL.md",true,[],[79,88,96,104,112,120],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":83,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":87},"01M73H7XKBHE1ETQDZT94MF9HH","seedance-prompt-en","Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fseedance-prompt-en\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fseedance-prompt-en\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":87},"01M73GRE9998Q1DZWC71N41JWG","onepage-pdf","Convert an HTML page into a single continuous-page PDF (one tall page, no pagination breaks), preserving desktop layout, backgrounds and selectable text. Use when the user asks to turn an HTML file\u002Freport\u002Fproposal into a \"single-page PDF\", \"long PDF\", \"不分页 PDF\", \"单页 PDF\", \"长图式 PDF\", or complains that an HTML-to-PDF export breaks into pages or cuts content. Supports optional string redaction with leak verification.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fonepage-pdf\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fonepage-pdf\u002FSKILL.md",[],[],{"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":15,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":87},"01M73GQG1KZDADVPV3MHAT1J5A","native-feel-cross-platform-desktop","Use when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a native app to its users — fast launch, native windowing, native input handling, native materials. Trigger words include \"cross-platform desktop\", \"Electron alternative\", \"Tauri vs native\", \"WebView wrapper\", \"near-native performance\", \"Raycast architecture\", \"WebKit\u002FWebView2 quirks\", \"WKWebView\", \"system tray app\", \"global hotkey app\", \"launcher app\". Do NOT trigger this skill for pure web apps, pure mobile apps, or for greenfield projects that have no native-feel requirement.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fnative-feel-cross-platform-desktop\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fnative-feel-cross-platform-desktop\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":108,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":87},"01M73G87PDNSMKG2FHWCYER6N8","gstack","Router for the gstack skill suite. (gstack)","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fgstack\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fgstack\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":116,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":87},"01M73G3EAQWKCM8DB8D0N0QSVG","fireworks-tech-graph","Use when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent\u002Fmemory, or concept map - and export as SVG+PNG. Trigger on: \"画图\" \"帮我画\" \"生成图\" \"做个图\" \"架构图\" \"流程图\" \"可视化一下\" \"出图\" \"generate diagram\" \"draw diagram\" \"visualize\" or any system\u002Fflow description the user wants illustrated.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Ffireworks-tech-graph\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Ffireworks-tech-graph\u002FSKILL.md",[],[],{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":87},"01M73G086AXAH9DW1H5G5N3CPB","dbs-video-extract","接收抖音、小红书、微信视频号等短视频链接或分享文案，查询作品／账号数据并提取语音文字稿，按作者和标题归档为 Markdown。用户希望完整解析短视频、取得数据或文字稿时使用；运行前检查 TikHub 与轻抖使用凭证，缺少时用新手能理解的方式引导购买和安全配置。","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fdbs-video-extract\u002FSKILL.md",[],[]]