[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CBWK00VM0DP6YWXK8KSW10":3,"skill-same:01M6CBWK00VM0DP6YWXK8KSW10":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":49,"install":50,"resources":62},"01M6CBWK00VM0DP6YWXK8KSW10","skill-discovery",null,"Search all Claude Code skill\u002Fplugin marketplaces, curated collections, and GitHub for skills matching a use case. Compares findings to installed inventory, ranks by adoption, and handles install + symlink + agent wiring. Use PROACTIVELY when any agent is missing skills, when the user asks \"find a skill for X\", \"is there a skill for Y\", \"search for Z\", or when you notice a capability gap that an existing skill might fill. Also use when setting up a new specialist agent that needs domain skills.","ray-manaloto\u002Fmacos-development-environment","ray-manaloto","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F227192835?v=4","01M6CBR7J13ZA01X5YB1A1QRJP","01M6CBR7P0S3NS8ZV81JYNST14",1,"MIT","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-discovery\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35],"discovery","skill discovery","github","plugin","code","search","adoption","inventory","find","user","install","use","up","2026-11-10 10:12:30",false,"---\nname: skill-discovery\ndescription: Search all Claude Code skill\u002Fplugin marketplaces, curated collections, and GitHub for skills matching a use case. Compares findings to installed inventory, ranks by adoption, and handles install + symlink + agent wiring. Use PROACTIVELY when any agent is missing skills, when the user asks \"find a skill for X\", \"is there a skill for Y\", \"search for Z\", or when you notice a capability gap that an existing skill might fill. Also use when setting up a new specialist agent that needs domain skills.\nuser-invocable: true\nargument-hint: \u003Cuse-case-or-query>\n---\n\n# Skill Discovery\n\nSearch across all Claude Code skill sources, compare to what's installed, and install the best match — or identify gaps where a custom skill is needed.\n\n## Quick Start\n\n```bash\n# Unified search across all sources (skills.sh + GitHub + SkillsMP)\nuv run mde-py research skill-discover \u003Cquery>\n\n# JSON output for programmatic use\nuv run mde-py research skill-discover \u003Cquery> --json\n\n# Via mise task\nmise run mde:research:skill-discover -- \u003Cquery>\n```\n\n## The Discovery Pipeline\n\n```\n1. INVENTORY — Check what's already installed locally\n2. SEARCH — Query working sources (skills.sh, skillkit, GitHub)\n3. COMPARE — Rank results by adoption and relevance\n4. DECIDE — Install best match, or identify gap for custom skill\n5. INSTALL — skills add + symlink + agent wiring\n6. VERIFY — Confirm skill file exists and agent references it\n```\n\n## Step 1: Check Local Inventory First\n\nBefore searching externally, check what's already installed. This avoids duplicates and may reveal the skill already exists.\n\n```bash\n# Search installed project + user skills by keyword\nfind .claude\u002Fskills .agents\u002Fskills -name \"SKILL.md\" 2>\u002Fdev\u002Fnull \\\n  | xargs grep -li \"\u003Cquery>\" 2>\u002Fdev\u002Fnull\n\n# Count total installed skills\nskillfish list 2>&1 | tail -3\n\n# Search installed plugins\nclaude plugins list 2>&1 | grep -i \"\u003Cquery>\"\n```\n\n## Step 2: Search External Sources\n\nRun all agent-accessible tools in parallel, then guide the user for interactive\u002Fweb tools.\n\n### Agent-Accessible Search Tools (run these via Bash)\n\n```bash\n# 1. skills.sh — BEST source. 22K+ skills with install-count rankings.\n#    Fastest, most reliable, has adoption metrics as quality signal.\nskills find \"\u003Cquery>\" 2>&1 | head -30\n\n# 2. skillkit — 15K+ skills, cross-platform (13+ AI tools).\n#    Slower (downloads 19MB on first run), but finds results skills.sh misses.\nskillkit search \"\u003Cquery>\" 2>&1 | head -30\n\n# 3. GitHub code search — deepest, finds niche\u002Fpersonal skills.\n#    Searches ALL public SKILL.md files on GitHub.\ngh search code \"\u003Cquery>\" --filename \"SKILL.md\" --limit 15 2>&1\n```\n\n### User-Interactive Search Tools (user runs these in their terminal)\n\nThese tools have interactive TUIs that require a real terminal. Ask the user to run them via the `!` prefix (which runs in their shell session):\n\n```\n# 4. skills-installer — 203+ results for popular queries, interactive TUI selector.\n#    Searches all public GitHub skills via agentskills.io index.\n! skills-installer search \"\u003Cquery>\"\n\n# 5. skill.fish browser — 31-33K skills, visual search.\n#    User opens https:\u002F\u002Fskill.fish in browser and searches there.\n```\n\nTell the user: \"I can search skills.sh, skillkit, and GitHub automatically, but skills-installer and skill.fish need your terminal. Run `! skills-installer search '\u003Cquery>'` to search the agentskills.io index (203+ results for terraform, 33 for chezmoi).\"\n\n### API-Key-Required Sources (setup needed first)\n\n```bash\n# 6. SkillsMP API — 546K+ skills, largest catalog.\n#    Requires API key: sign up at https:\u002F\u002Fskillsmp.com\u002Fdocs\u002Fapi\n#    Set SKILLSMP_API_KEY env var, then use skillsmp-mcp-lite MCP server.\ncurl -s -H \"Authorization: Bearer $SKILLSMP_API_KEY\" \\\n  \"https:\u002F\u002Fskillsmp.com\u002Fapi\u002Fv1\u002Fskills\u002Fsearch?q=\u003Cquery>\" 2>&1 | head -50\n```\n\n### Skillfish (installer only, search broken upstream)\n\n`skillfish search` returns empty results — the backend API at mcpmarket.com returns 403. But `skillfish add`, `skillfish list`, `skillfish install` (from skillfish.json manifest), and `skillfish bundle` all work. Use it for installing\u002Fmanaging, not searching.\n\n```bash\n# List all installed skills across all agents\nskillfish list 2>&1 | tail -5\n\n# Install a specific skill from a known repo\nskillfish add \u003Cowner\u002Frepo\u002Fskill-name> 2>&1\n```\n\n### GitHub Collection Search (curated quality)\n\nFor high-quality skills from known collections, search their repos directly:\n\n```bash\nfor repo in wshobson\u002Fagents VoltAgent\u002Fawesome-claude-code-subagents \\\n  affaan-m\u002Feverything-claude-code ComposioHQ\u002Fawesome-claude-skills \\\n  anthropics\u002Fskills BehiSecc\u002Fawesome-claude-skills \\\n  travisvn\u002Fawesome-claude-skills; do\n  echo \"=== $repo ===\"\n  gh api \"repos\u002F$repo\u002Fgit\u002Ftrees\u002Fmain\" --jq '.tree[].path' 2>\u002Fdev\u002Fnull \\\n    | grep -i \"\u003Cquery>\" | head -5\ndone\n```\n\n## Step 3: Compare and Rank\n\nBuild a comparison table from all search results:\n\n| Skill | Source | Installs\u002FStars | Already Installed? | Author |\n|-------|--------|---------------|-------------------|--------|\n| name | skills.sh \u002F GitHub | count | YES\u002FNO | ecosystem fit? |\n\n**Ranking criteria (in priority order):**\n1. **Relevance** — Does it actually solve the use case? Read the SKILL.md content.\n2. **Adoption** — Install count from skills.sh is the best quality signal\n3. **Ecosystem fit** — Same author as other installed skills? (terrylica has both chezmoi + mise)\n4. **Recency** — When was it last updated?\n5. **Not a duplicate** — Check it isn't already installed under a different name\n\n## Step 4: Decide\n\n**A. Strong match found** → Install (Step 5)\n\n**B. Partial match** → Install best available + note gaps for a custom companion skill\n\n**C. No match** → Report: \"No existing skill covers this. Closest are [X, Y]. Recommend creating a custom skill covering [gaps].\"\n\n## Step 5: Install\n\n```bash\n# Install from skills.sh\nskills add \u003Cowner\u002Frepo> --skill \u003Cname> --yes 2>&1\n\n# Verify it landed in .agents\u002Fskills\u002F\nls .agents\u002Fskills\u002F\u003Cname>\u002FSKILL.md 2>\u002Fdev\u002Fnull\n\n# Symlink to .claude\u002Fskills\u002F if not auto-linked\nif [ ! -e \".claude\u002Fskills\u002F\u003Cname>\" ]; then\n  ln -s \"..\u002F..\u002F.agents\u002Fskills\u002F\u003Cname>\" \".claude\u002Fskills\u002F\u003Cname>\"\nfi\necho \"Symlink: $(ls -la .claude\u002Fskills\u002F\u003Cname>)\"\n```\n\n### Wire to Agent (if target agent specified)\n\n```bash\n# Read current skills field\ngrep \"^skills:\" .claude\u002Fagents\u002F\u003Cagent-name>.md\n\n# Add the new skill to the YAML list (edit the frontmatter)\n# Example: skills: [existing-skill] → skills: [existing-skill, new-skill]\n```\n\n## Step 6: Verify\n\n```bash\n# 1. Skill file exists\nhead -5 .claude\u002Fskills\u002F\u003Cname>\u002FSKILL.md\n\n# 2. Agent references it (if wired)\ngrep \"^skills:\" .claude\u002Fagents\u002F\u003Cagent-name>.md\n\n# 3. Skill resolves through symlink\ntest -f \".claude\u002Fskills\u002F\u003Cname>\u002FSKILL.md\" && echo \"RESOLVES\" || echo \"BROKEN SYMLINK\"\n```\n\n## High-Adoption Skill Authors\n\nTrack these authors — they produce consistently popular, quality skills:\n\n| Author | Ecosystem | Top Skills (installs) |\n|--------|----------|----------------------|\n| terrylica\u002Fcc-skills | DevOps + dotfiles (20 plugins) | mise-tasks (114), chezmoi-workflows (85) |\n| samhvw8\u002Fdotfiles | mise specialist | mise-expert (98) |\n| bobmatnyc\u002Fclaude-mpm-skills | Package management | homebrew-formula-maintenance (84) |\n| hashicorp\u002Fagent-skills | Terraform (official) | terraform-style-guide (2K), terraform-test (1.2K) |\n| github\u002Fawesome-copilot | Azure\u002Fcloud | terraform-azurerm (7.3K) |\n\n## Web Marketplaces (manual search only)\n\nThese have large catalogs but no working CLI. Use a browser or MCP when available:\n\n| Marketplace | URL | Catalog Size |\n|------------|-----|-------------|\n| SkillsMP | https:\u002F\u002Fskillsmp.com | 546K+ (API key required) |\n| LobeHub | https:\u002F\u002Flobehub.com\u002Fskills | 229K+ |\n| Skill.Fish | https:\u002F\u002Fskill.fish | 31-33K |\n| awesomeclaude.ai | https:\u002F\u002Fawesomeclaude.ai\u002Fawesome-claude-skills | Curated directory |\n| ClawHub | https:\u002F\u002Fclawhub.ai | NEW, vector search |\n\nFor the full source registry with URLs, sizes, and search commands, see `references\u002Fsources.md`.\n\n## Project-Specific Policies\n\n- **Library-first**: Always search before building custom skills\n- **Mise-first**: If a skill needs a CLI tool, install via mise not npm -g\n- **Chezmoi pipeline**: Tool installs flow through chezmoi templates\n- **Source catalog**: Log every URL discovered to `docs\u002Fresearch\u002Fsource-catalog.md`\n- **Provenance**: Write findings to `docs\u002Fresearch\u002Ftrail\u002Ffindings\u002Ffinding-\u003Cslug>.yaml`\n","# Skill Discovery\n\nSearch across all Claude Code skill sources, compare to what's installed, and install the best match — or identify gaps where a custom skill is needed.\n\n## Quick Start\n\n```bash\n# Unified search across all sources (skills.sh + GitHub + SkillsMP)\nuv run mde-py research skill-discover \u003Cquery>\n\n# JSON output for programmatic use\nuv run mde-py research skill-discover \u003Cquery> --json\n\n# Via mise task\nmise run mde:research:skill-discover -- \u003Cquery>\n```\n\n## The Discovery Pipeline\n\n```\n1. INVENTORY — Check what's already installed locally\n2. SEARCH — Query working sources (skills.sh, skillkit, GitHub)\n3. COMPARE — Rank results by adoption and relevance\n4. DECIDE — Install best match, or identify gap for custom skill\n5. INSTALL — skills add + symlink + agent wiring\n6. VERIFY — Confirm skill file exists and agent references it\n```\n\n## Step 1: Check Local Inventory First\n\nBefore searching externally, check what's already installed. This avoids duplicates and may reveal the skill already exists.\n\n```bash\n# Search installed project + user skills by keyword\nfind .claude\u002Fskills .agents\u002Fskills -name \"SKILL.md\" 2>\u002Fdev\u002Fnull \\\n  | xargs grep -li \"\u003Cquery>\" 2>\u002Fdev\u002Fnull\n\n# Count total installed skills\nskillfish list 2>&1 | tail -3\n\n# Search installed plugins\nclaude plugins list 2>&1 | grep -i \"\u003Cquery>\"\n```\n\n## Step 2: Search External Sources\n\nRun all agent-accessible tools in parallel, then guide the user for interactive\u002Fweb tools.\n\n### Agent-Accessible Search Tools (run these via Bash)\n\n```bash\n# 1. skills.sh — BEST source. 22K+ skills with install-count rankings.\n#    Fastest, most reliable, has adoption metrics as quality signal.\nskills find \"\u003Cquery>\" 2>&1 | head -30\n\n# 2. skillkit — 15K+ skills, cross-platform (13+ AI tools).\n#    Slower (downloads 19MB on first run), but finds results skills.sh misses.\nskillkit search \"\u003Cquery>\" 2>&1 | head -30\n\n# 3. GitHub code search — deepest, finds niche\u002Fpersonal skills.\n#    Searches ALL public SKILL.md files on GitHub.\ngh search code \"\u003Cquery>\" --filename \"SKILL.md\" --limit 15 2>&1\n```\n\n### User-Interactive Search Tools (user runs these in their terminal)\n\nThese tools have interactive TUIs that require a real terminal. Ask the user to run them via the `!` prefix (which runs in their shell session):\n\n```\n# 4. skills-installer — 203+ results for popular queries, interactive TUI selector.\n#    Searches all public GitHub skills via agentskills.io index.\n! skills-installer search \"\u003Cquery>\"\n\n# 5. skill.fish browser — 31-33K skills, visual search.\n#    User opens https:\u002F\u002Fskill.fish in browser and searches there.\n```\n\nTell the user: \"I can search skills.sh, skillkit, and GitHub automatically, but skills-installer and skill.fish need your terminal. Run `! skills-installer search '\u003Cquery>'` to search the agentskills.io index (203+ results for terraform, 33 for chezmoi).\"\n\n### API-Key-Required Sources (setup needed first)\n\n```bash\n# 6. SkillsMP API — 546K+ skills, largest catalog.\n#    Requires API key: sign up at https:\u002F\u002Fskillsmp.com\u002Fdocs\u002Fapi\n#    Set SKILLSMP_API_KEY env var, then use skillsmp-mcp-lite MCP server.\ncurl -s -H \"Authorization: Bearer $SKILLSMP_API_KEY\" \\\n  \"https:\u002F\u002Fskillsmp.com\u002Fapi\u002Fv1\u002Fskills\u002Fsearch?q=\u003Cquery>\" 2>&1 | head -50\n```\n\n### Skillfish (installer only, search broken upstream)\n\n`skillfish search` returns empty results — the backend API at mcpmarket.com returns 403. But `skillfish add`, `skillfish list`, `skillfish install` (from skillfish.json manifest), and `skillfish bundle` all work. Use it for installing\u002Fmanaging, not searching.\n\n```bash\n# List all installed skills across all agents\nskillfish list 2>&1 | tail -5\n\n# Install a specific skill from a known repo\nskillfish add \u003Cowner\u002Frepo\u002Fskill-name> 2>&1\n```\n\n### GitHub Collection Search (curated quality)\n\nFor high-quality skills from known collections, search their repos directly:\n\n```bash\nfor repo in wshobson\u002Fagents VoltAgent\u002Fawesome-claude-code-subagents \\\n  affaan-m\u002Feverything-claude-code ComposioHQ\u002Fawesome-claude-skills \\\n  anthropics\u002Fskills BehiSecc\u002Fawesome-claude-skills \\\n  travisvn\u002Fawesome-claude-skills; do\n  echo \"=== $repo ===\"\n  gh api \"repos\u002F$repo\u002Fgit\u002Ftrees\u002Fmain\" --jq '.tree[].path' 2>\u002Fdev\u002Fnull \\\n    | grep -i \"\u003Cquery>\" | head -5\ndone\n```\n\n## Step 3: Compare and Rank\n\nBuild a comparison table from all search results:\n\n| Skill | Source | Installs\u002FStars | Already Installed? | Author |\n|-------|--------|---------------|-------------------|--------|\n| name | skills.sh \u002F GitHub | count | YES\u002FNO | ecosystem fit? |\n\n**Ranking criteria (in priority order):**\n1. **Relevance** — Does it actually solve the use case? Read the SKILL.md content.\n2. **Adoption** — Install count from skills.sh is the best quality signal\n3. **Ecosystem fit** — Same author as other installed skills? (terrylica has both chezmoi + mise)\n4. **Recency** — When was it last updated?\n5. **Not a duplicate** — Check it isn't already installed under a different name\n\n## Step 4: Decide\n\n**A. Strong match found** → Install (Step 5)\n\n**B. Partial match** → Install best available + note gaps for a custom companion skill\n\n**C. No match** → Report: \"No existing skill covers this. Closest are [X, Y]. Recommend creating a custom skill covering [gaps].\"\n\n## Step 5: Install\n\n```bash\n# Install from skills.sh\nskills add \u003Cowner\u002Frepo> --skill \u003Cname> --yes 2>&1\n\n# Verify it landed in .agents\u002Fskills\u002F\nls .agents\u002Fskills\u002F\u003Cname>\u002FSKILL.md 2>\u002Fdev\u002Fnull\n\n# Symlink to .claude\u002Fskills\u002F if not auto-linked\nif [ ! -e \".claude\u002Fskills\u002F\u003Cname>\" ]; then\n  ln -s \"..\u002F..\u002F.agents\u002Fskills\u002F\u003Cname>\" \".claude\u002Fskills\u002F\u003Cname>\"\nfi\necho \"Symlink: $(ls -la .claude\u002Fskills\u002F\u003Cname>)\"\n```\n\n### Wire to Agent (if target agent specified)\n\n```bash\n# Read current skills field\ngrep \"^skills:\" .claude\u002Fagents\u002F\u003Cagent-name>.md\n\n# Add the new skill to the YAML list (edit the frontmatter)\n# Example: skills: [existing-skill] → skills: [existing-skill, new-skill]\n```\n\n## Step 6: Verify\n\n```bash\n# 1. Skill file exists\nhead -5 .claude\u002Fskills\u002F\u003Cname>\u002FSKILL.md\n\n# 2. Agent references it (if wired)\ngrep \"^skills:\" .claude\u002Fagents\u002F\u003Cagent-name>.md\n\n# 3. Skill resolves through symlink\ntest -f \".claude\u002Fskills\u002F\u003Cname>\u002FSKILL.md\" && echo \"RESOLVES\" || echo \"BROKEN SYMLINK\"\n```\n\n## High-Adoption Skill Authors\n\nTrack these authors — they produce consistently popular, quality skills:\n\n| Author | Ecosystem | Top Skills (installs) |\n|--------|----------|----------------------|\n| terrylica\u002Fcc-skills | DevOps + dotfiles (20 plugins) | mise-tasks (114), chezmoi-workflows (85) |\n| samhvw8\u002Fdotfiles | mise specialist | mise-expert (98) |\n| bobmatnyc\u002Fclaude-mpm-skills | Package management | homebrew-formula-maintenance (84) |\n| hashicorp\u002Fagent-skills | Terraform (official) | terraform-style-guide (2K), terraform-test (1.2K) |\n| github\u002Fawesome-copilot | Azure\u002Fcloud | terraform-azurerm (7.3K) |\n\n## Web Marketplaces (manual search only)\n\nThese have large catalogs but no working CLI. Use a browser or MCP when available:\n\n| Marketplace | URL | Catalog Size |\n|------------|-----|-------------|\n| SkillsMP | https:\u002F\u002Fskillsmp.com | 546K+ (API key required) |\n| LobeHub | https:\u002F\u002Flobehub.com\u002Fskills | 229K+ |\n| Skill.Fish | https:\u002F\u002Fskill.fish | 31-33K |\n| awesomeclaude.ai | https:\u002F\u002Fawesomeclaude.ai\u002Fawesome-claude-skills | Curated directory |\n| ClawHub | https:\u002F\u002Fclawhub.ai | NEW, vector search |\n\nFor the full source registry with URLs, sizes, and search commands, see `references\u002Fsources.md`.\n\n## Project-Specific Policies\n\n- **Library-first**: Always search before building custom skills\n- **Mise-first**: If a skill needs a CLI tool, install via mise not npm -g\n- **Chezmoi pipeline**: Tool installs flow through chezmoi templates\n- **Source catalog**: Log every URL discovered to `docs\u002Fresearch\u002Fsource-catalog.md`\n- **Provenance**: Write findings to `docs\u002Fresearch\u002Ftrail\u002Ffindings\u002Ffinding-\u003Cslug>.yaml`\n",{"name":5,"description":7,"argument-hint":41,"user-invocable":42},"\u003Cuse-case-or-query>",true,"main","716b17df3ef6719d88aeac180015008b7ddfff6f",".agents\u002Fskills\u002Fskill-discovery",0,"https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment","https:\u002F\u002Fgithub.com\u002Fray-manaloto","2026-08-03 16:55:50",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":42},[52,55,58],{"tool":53,"command":54},"npx","npx skills add ray-manaloto\u002Fmacos-development-environment --skill skill-discovery",{"tool":56,"command":57},"bunx","bunx skills add ray-manaloto\u002Fmacos-development-environment --skill skill-discovery",{"tool":59,"command":60},"pnpm","pnpm dlx skills add ray-manaloto\u002Fmacos-development-environment --skill skill-discovery","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-discovery\u002FSKILL.md",[63,69,73],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fsources.md","REFERENCE","参考文档",6093,"https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-discovery\u002Freferences\u002Fsources.md",{"path":70,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":71,"sourceHtmlUrl":72},"SOURCE.md",198,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdefi\u002Fgovernance-x-dao\u002FSOURCE.md",{"path":74,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":75,"sourceHtmlUrl":76},"TRUST.auto.yaml",2217,"https:\u002F\u002Fgithub.com\u002Fjiayaoqijia\u002Fcryptoskill\u002Fblob\u002Fmain\u002Fskills\u002Fdefi\u002Fgovernance-x-dao\u002FTRUST.auto.yaml",[78,94,109,128,148,162],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":85,"publishedAt":36},"01M6CC8DXNJ39YWERYTWCGGCGG","next-workflow-step","Use this skill when the user wants to transition to the next workflow step, wrap up a session cleanly, prepare a handoff, or says things like \"next step\", \"continue the workflow\", \"wrap up\", \"hand off\", \"move to the next phase\", \"what's next in embrace\", or \"prepare for \u002Fclear\". Also triggers when the current octo:embrace phase appears complete and no explicit next action is set.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fworkflow-toolkit\u002Fskills\u002Fnext-workflow-step\u002FSKILL.md",[84],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[86,87,35,34,88,32,89,90,91,92,93],"next workflow step","workflow","session","wrap up","continue","handoff","prepare","SET",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":36},"01M6CC8BRZBQHEBXGMKPDM422P","source-discovery","This skill should be used when the user asks to \"find sources\", \"discover URLs\", \"catalog a source\", \"classify a URL\", \"search for libraries\", \"check what exists\", or mentions source discovery, URL cataloging, source classification, or research source management.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fresearch-review-toolkit\u002Fskills\u002Fsource-discovery\u002FSKILL.md",[],[23,101,102,103,28,104,31,105,106,32,107,108],"source discovery","research","libraries","classification","check","management","catalog","find sources",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":36},"01M6CC89CGJP69A0PS22G2H1FV","review-synthesis","This skill should be used when the user asks to \"summarize review findings\", \"prioritize fixes\", \"rank review issues\", \"combine reviewer feedback\", \"create action items from review\", or mentions review synthesis, finding prioritization, severity ranking, or review result summarization.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fresearch-review-toolkit\u002Fskills\u002Freview-synthesis\u002FSKILL.md",[],[116,117,118,119,120,121,122,32,123,124,125,126,127],"review","review synthesis","Synthesis","prioritize","create action","feedback","reviewer","summarize","prioritization","create","issues","severity",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":137,"publishedAt":36},"01M6CC872EZ9GRJY0HRCG0RT2M","research-scoring","This skill should be used when the user asks to \"score research\", \"check research quality\", \"evaluate coverage\", \"measure improvement\", \"assess research completeness\", or mentions research scoring, quality metrics, coverage gaps, improvement baseline, or research pipeline status.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fresearch-review-toolkit\u002Fskills\u002Fresearch-scoring\u002FSKILL.md",[134],{"categoryNo":135,"categoryName":136,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[138,102,139,140,141,142,143,144,105,32,145,146,147],"research scoring","status","coverage gaps","metrics","pipeline","baseline","quality","coverage","pipeline status","research quality",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":36},"01M6CC852HSDS1FE4EJAT0RHGR","notebooklm-integration","This skill should be used when the user asks to \"ingest into NotebookLM\", \"query NotebookLM\", \"add sources to notebook\", \"cross-source synthesis\", \"check stale sources\", or mentions NotebookLM, notebook integration, source ingestion, or knowledge consolidation.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fresearch-review-toolkit\u002Fskills\u002Fnotebooklm-integration\u002FSKILL.md",[],[155,156,157,158,105,32,159,160,161,118],"notebooklm integration","notebooklm","integration","knowledge","ingestion","ingest","stale",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":169,"publishedAt":36},"01M6CC82Z4V3205KCJWQZPS2VG","evidence-synthesis","This skill should be used when the user asks to \"synthesize findings\", \"combine research\", \"cross-reference sources\", \"summarize evidence\", \"write a deep review\", or mentions evidence synthesis, finding consolidation, cross-source analysis, or research summarization.","https:\u002F\u002Fgithub.com\u002Fray-manaloto\u002Fmacos-development-environment\u002Fblob\u002Fmain\u002Frsm-subagents\u002Fplugins\u002Fresearch-review-toolkit\u002Fskills\u002Fevidence-synthesis\u002FSKILL.md",[168],{"categoryNo":135,"categoryName":136,"taxonomyType":20,"taxonomyTypeDesc":21},[170,118,171,123,102,172,173,174,32,175,116],"evidence synthesis","evidence","deep review","analysis","write","reference"]