[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C5KYXZSAVSWN5Y87JSGEQE":3,"skill-same:01M6C5KYXZSAVSWN5Y87JSGEQE":80},{"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":23,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M6C5KYXZSAVSWN5Y87JSGEQE","skill-discovery",null,"Scan and catalog all available skills, agents, commands, hooks, and rules in the project. Use this skill whenever someone asks 'what skills are available', 'list agents', 'show me the registry', 'update the skill catalog', 'what can I use', 'what tools do I have', or any question about discovering, listing, or inventorying the project's AI capabilities. Also trigger when generating prompts that need to know what skills exist, or when setting up a new session and wanting to confirm available tooling.","CoralShades\u002Facm-ai","CoralShades","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F220297585?v=4","01M6C5211QSJHZ8HXSDDWCR507","Coral Shades AI Agency","01M6C52161FNQDRQ0FRR8DAA9D",0,"MIT","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskill-discovery\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"skill discovery","discovery","list","prompts","tooling","hooks","up","use","catalog","session","update","question","Rules","show me","new session","Tools","capabilities","registry","2026-11-10 10:12:30",false,"---\nname: skill-discovery\ndescription: \"Scan and catalog all available skills, agents, commands, hooks, and rules in the project. Use this skill whenever someone asks 'what skills are available', 'list agents', 'show me the registry', 'update the skill catalog', 'what can I use', 'what tools do I have', or any question about discovering, listing, or inventorying the project's AI capabilities. Also trigger when generating prompts that need to know what skills exist, or when setting up a new session and wanting to confirm available tooling.\"\n---\n\n# Skill Discovery\n\nScan and catalog all available skills, agents, commands, hooks, and rules in the project. Produces a structured `skills-registry.json` and presents a formatted summary.\n\n## Steps\n\n### Step 1: Run the Scanner\n\nExecute the registry scanner script from the repo root:\n\n```bash\ncd \"D:\u002Failocal\u002Facm-ai\" && bash .claude\u002Fskills\u002Fskill-discovery\u002Fscripts\u002Fscan_registry.sh\n```\n\nThis generates `skills-registry.json` at the repo root with a full inventory of all capabilities.\n\n### Step 2: Read the Generated Registry\n\nRead the generated file:\n\n```\nD:\u002Failocal\u002Facm-ai\u002Fskills-registry.json\n```\n\n### Step 3: Present a Formatted Summary\n\nPresent the results grouped by type. Use this format:\n\n```\n## Skills Registry Summary\nScanned at: \u003Cscanned_at>\n\n### Skills (\u003Ccount> total)\n| Name | Description | Location | Platforms |\n|------|-------------|----------|-----------|\n| pydantic-models-py | Create Pydantic models... | .claude\u002Fskills\u002F... | claude-code |\n| ...  | ...          | ...      | ...       |\n\n### Commands (\u003Ccount> total)\n| Name | Description |\n|------|-------------|\n| start | Start development services |\n| ...  | ...         |\n\n### Hooks (\u003Ccount> total)\n| Name | Trigger |\n|------|---------|\n| pre-tool-use.sh | PreToolUse |\n| ...             | ...        |\n\n### Rule Categories (from CLAUDE.md)\n- Project Overview\n- Essential Commands\n- Architecture\n- ...\n```\n\n### Step 4: Filter if Requested\n\nIf the user asks to filter (e.g., \"show me debugging skills\", \"list only frontend skills\"):\n\n- Filter `skills` array by matching keywords against `name` and `description` fields\n- Present the filtered subset using the same table format\n- Note how many skills were hidden: \"Showing 3 of 12 skills (filtered by 'debug')\"\n\n## Quick Reference\n\nThe following skills are available in this project (populated after first scan):\n\n| Name | One-line Description |\n|------|---------------------|\n| `pydantic-models-py` | Create Pydantic v2 models following multi-model pattern |\n| `acm-observability` | ACM-AI 6-tool observability stack reference |\n| `systematic-debugging` | Structured debugging process before proposing fixes |\n| `dispatching-parallel-agents` | Dispatch 2+ independent tasks in parallel |\n| `subagent-driven-development` | Execute plans via focused sub-agents |\n| `planning-with-files` | Persistent markdown-based planning for session continuity |\n| `verification-before-completion` | Verify work before claiming completion |\n| `skill-discovery` | This skill — scan and catalog all AI capabilities |\n\n> Run the scanner to get the full up-to-date list including all installed skills.\n\n## Notes\n\n- Skills can live in `.claude\u002Fskills\u002F` (Claude Code) or `.agents\u002Fskills\u002F` (agent platform) or both\n- Skills with `also_at` entries appear in multiple registries — they are the same skill\n- The registry is regenerated on each scan; commit `skills-registry.json` to track changes over time\n- Hooks are found in `.claude\u002Fhooks\u002F` — they run automatically based on trigger type\n- Commands are in `commands\u002F` (surreal-commands worker handlers, not slash commands)\n","# Skill Discovery\n\nScan and catalog all available skills, agents, commands, hooks, and rules in the project. Produces a structured `skills-registry.json` and presents a formatted summary.\n\n## Steps\n\n### Step 1: Run the Scanner\n\nExecute the registry scanner script from the repo root:\n\n```bash\ncd \"D:\u002Failocal\u002Facm-ai\" && bash .claude\u002Fskills\u002Fskill-discovery\u002Fscripts\u002Fscan_registry.sh\n```\n\nThis generates `skills-registry.json` at the repo root with a full inventory of all capabilities.\n\n### Step 2: Read the Generated Registry\n\nRead the generated file:\n\n```\nD:\u002Failocal\u002Facm-ai\u002Fskills-registry.json\n```\n\n### Step 3: Present a Formatted Summary\n\nPresent the results grouped by type. Use this format:\n\n```\n## Skills Registry Summary\nScanned at: \u003Cscanned_at>\n\n### Skills (\u003Ccount> total)\n| Name | Description | Location | Platforms |\n|------|-------------|----------|-----------|\n| pydantic-models-py | Create Pydantic models... | .claude\u002Fskills\u002F... | claude-code |\n| ...  | ...          | ...      | ...       |\n\n### Commands (\u003Ccount> total)\n| Name | Description |\n|------|-------------|\n| start | Start development services |\n| ...  | ...         |\n\n### Hooks (\u003Ccount> total)\n| Name | Trigger |\n|------|---------|\n| pre-tool-use.sh | PreToolUse |\n| ...             | ...        |\n\n### Rule Categories (from CLAUDE.md)\n- Project Overview\n- Essential Commands\n- Architecture\n- ...\n```\n\n### Step 4: Filter if Requested\n\nIf the user asks to filter (e.g., \"show me debugging skills\", \"list only frontend skills\"):\n\n- Filter `skills` array by matching keywords against `name` and `description` fields\n- Present the filtered subset using the same table format\n- Note how many skills were hidden: \"Showing 3 of 12 skills (filtered by 'debug')\"\n\n## Quick Reference\n\nThe following skills are available in this project (populated after first scan):\n\n| Name | One-line Description |\n|------|---------------------|\n| `pydantic-models-py` | Create Pydantic v2 models following multi-model pattern |\n| `acm-observability` | ACM-AI 6-tool observability stack reference |\n| `systematic-debugging` | Structured debugging process before proposing fixes |\n| `dispatching-parallel-agents` | Dispatch 2+ independent tasks in parallel |\n| `subagent-driven-development` | Execute plans via focused sub-agents |\n| `planning-with-files` | Persistent markdown-based planning for session continuity |\n| `verification-before-completion` | Verify work before claiming completion |\n| `skill-discovery` | This skill — scan and catalog all AI capabilities |\n\n> Run the scanner to get the full up-to-date list including all installed skills.\n\n## Notes\n\n- Skills can live in `.claude\u002Fskills\u002F` (Claude Code) or `.agents\u002Fskills\u002F` (agent platform) or both\n- Skills with `also_at` entries appear in multiple registries — they are the same skill\n- The registry is regenerated on each scan; commit `skills-registry.json` to track changes over time\n- Hooks are found in `.claude\u002Fhooks\u002F` — they run automatically based on trigger type\n- Commands are in `commands\u002F` (surreal-commands worker handlers, not slash commands)\n",{"name":5,"description":7},"main","1ca81b0a7de199942400f965edd4d7544077ac5d",".claude\u002Fskills\u002Fskill-discovery","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai","https:\u002F\u002Fgithub.com\u002FCoralShades","coralshades.com.au","2026-04-18 00:45:07",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add CoralShades\u002Facm-ai --skill skill-discovery",{"tool":60,"command":61},"bunx","bunx skills add CoralShades\u002Facm-ai --skill skill-discovery",{"tool":63,"command":64},"pnpm","pnpm dlx skills add CoralShades\u002Facm-ai --skill skill-discovery","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskill-discovery\u002FSKILL.md",true,[68,74],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fregistry-schema.md","REFERENCE","参考文档",5908,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskill-discovery\u002Freferences\u002Fregistry-schema.md",{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"scripts\u002Fscan_registry.sh","SCRIPT","脚本",10157,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fskill-discovery\u002Fscripts\u002Fscan_registry.sh",[81,102,115,131,153,163],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":90,"publishedAt":42},"01M6C63HKXA890HHV47WBAX0TB","uncodixfy","Prevents generic AI\u002FCodex UI patterns when generating frontend code. Use this skill whenever generating HTML, CSS, React, Vue, Svelte, or any frontend UI code to enforce clean, human-designed aesthetics inspired by Linear, Raycast, Stripe, and GitHub instead of typical AI-generated UI.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Funcodixfy\u002FSKILL.md",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[83,91,92,93,94,95,96,97,98,99,100,31,101],"github","frontend","css","codex","react","code","linear","ui","vue","generated","html",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":106,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":42},"01M6C63FJ2GEBBGZ5XSMV40KXB","runpodctl","Runpod CLI to manage your GPU workloads.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Frunpodctl\u002FSKILL.md",[],[104,110,111,112,113,114],"macos","cli","linux","gpu","Bash",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":42},"01M6C63DPAV46TFVQ01SFYPJ7X","langgraph-persistence","INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-persistence\u002FSKILL.md",[],[122,123,124,125,126,127,128,129,130],"langgraph persistence","langgraph","persistence","travel","history","scoping","remember","state","configure",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":142,"publishedAt":42},"01M6C63BNS9CQEBTB8RNSSBFPA","langgraph-human-in-the-loop","INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval\u002Fvalidation workflows, and the 4-tier error handling strategy.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-human-in-the-loop\u002FSKILL.md",[137],{"categoryNo":138,"categoryName":139,"taxonomyType":140,"taxonomyTypeDesc":141},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[143,144,123,145,146,147,148,149,150,151,152],"langgraph human in the loop","loop","workflows","error handling","validation","human-in-the-loop","command","strategy","approval","resume",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":42},"01M6C639GVYZFX3NFPV5FBDR4F","langgraph-fundamentals","INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-fundamentals\u002FSKILL.md",[],[160,123,146,129,161,162,149,96],"langgraph fundamentals","streaming","writing",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":169,"publishedAt":42},"01M6C6375N34YX2GZ3SD3R7XR2","langchain-rag","INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flangchain-rag\u002FSKILL.md",[],[170,171,172,173,174,175,176,177,178,179],"rag","langchain rag","langchain","embeddings","vector","openai","chroma","faiss","vector stores","system"]