[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C2WYN48449Q7FDFJBDCGM5":3,"skill-same:01M6C2WYN48449Q7FDFJBDCGM5":69},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":44,"install":45,"resources":58},"01M6C2WYN48449Q7FDFJBDCGM5","ai-universe-second-opinion-workflow",null,"Complete workflow for using AI Universe MCP \u002Fsecondo command","jleechanorg\u002Fjleechan-skills","jleechanorg","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F221404966?v=4","01M6C1VJ99XG950X1DWPEBCBGX","01M6C1VJDK5YVDNT3362RT5WSB",6,"MIT","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills_archive\u002Flegacy-pre-2026-08-27\u002Fpackages\u002Fai-universe-second-opinion-workflow\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],"workflow","second opinion","ai universe second opinion workflow","second","MCP","command","project","complete","usage","for","2026-11-10 10:12:30",false,"---\ndescription: Complete workflow for using AI Universe MCP \u002Fsecondo command\ntype: usage\nscope: project\n---\n\n# AI Universe Second Opinion Workflow\n\n**Quick start:** Use `\u002Fsecondo` or the HTTPie helper script to gather multi-model analysis (Cerebras, Gemini, Perplexity, GPT-4o + synthesis).\n\n---\n\n## Activation cues\n- Requests to run or debug the AI Universe \"second opinion\" workflow.\n- Follow-ups after failed `\u002Fsecondo` runs or HTTPie 401\u002F5xx errors.\n- Planning sessions that need step-by-step instructions for MCP calls.\n- Questions about cost, rate limits, or interpreting multi-model output.\n\n## Prerequisites & authentication\n1. **Verify auth-cli.mjs installation**:\n   ```bash\n   test -f ~\u002F.claude\u002Fscripts\u002Fauth-cli.mjs && echo \"✅ Installed\" || echo \"❌ Not found - run \u002Flocalexportcommands\"\n   ```\n2. **Check authentication status**:\n   ```bash\n   node ~\u002F.claude\u002Fscripts\u002Fauth-cli.mjs status\n   ```\n3. **If not authenticated or token expired**, run login (opens browser for OAuth):\n   ```bash\n   # Run this outside Claude Code in a regular terminal\n   node ~\u002F.claude\u002Fscripts\u002Fauth-cli.mjs login\n   ```\n4. Ensure `http` (HTTPie), `jq`, `python3`, and `node` (>=20.0.0) are installed in the environment.\n\n> ℹ️ **Seamless Auto-Refresh**: The `\u002Fsecondo` command uses the exact same auth-cli.mjs from AI Universe repo. If your token is valid, it does nothing. If expired, it auto-refreshes using your refresh token (silent, no browser popup). Only prompts for login if refresh token expires (30+ days).\n\n> ℹ️ **Token Location**: All tokens stored in `~\u002F.ai-universe\u002Fauth-token.json` (same as AI Universe repo)\n> - ID token: 1-hour expiration\n> - Refresh token: enables 30+ day sessions\n\n> ℹ️ For a dedicated authentication walkthrough see [ai-universe-auth.md](ai-universe-auth.md). Dependency notes live in [secondo-dependencies.md](secondo-dependencies.md).\n\n## Primary commands\n| Scenario | Command |\n| --- | --- |\n| Quick question (when SlashCommand is working) | `\u002Fsecondo \"Should I use Redis or in-memory caching?\"` |\n| Build MCP request with PR context | `python3 skills\u002Fsecond_opinion_workflow\u002Fscripts\u002Fbuild_second_opinion_request.py \u002Ftmp\u002Fmcp_request.json \"QUESTION\" 3 origin\u002Fmain` |\n| Call MCP via HTTPie | `http POST https:\u002F\u002Fai-universe-backend-dev-114133832173.us-central1.run.app\u002Fmcp \"Authorization:Bearer $TOKEN\" \u003C \u002Ftmp\u002Fmcp_request.json --timeout=180 --print=b` |\n| Parse embedded JSON response | `jq -r '.result.content[0].text' \u002Ftmp\u002Fmcp_response.json > \u002Ftmp\u002Fmcp_parsed.json` |\n| Summarize models\u002Fcosts | `python3 skills\u002Fsecond_opinion_workflow\u002Fscripts\u002Fparse_second_opinion.py \u002Ftmp\u002Fmcp_parsed.json` |\n| End-to-end helper | `skills\u002Fsecond_opinion_workflow\u002Fscripts\u002Frequest_second_opinion.sh \"QUESTION\" [MAX_OPINIONS]` |\n\n## Recommended workflow (HTTPie)\n1. **Generate the request payload** (captures diff + per-file patches automatically):\n   ```bash\n   python3 skills\u002Fsecond_opinion_workflow\u002Fscripts\u002Fbuild_second_opinion_request.py \\\n     \u002Ftmp\u002Fmcp_request.json \\\n     \"YOUR QUESTION HERE\" \\\n     3 \\\n     origin\u002Fmain\n   ```\n   Adjust `SECOND_OPINION_MAX_FILES`, `SECOND_OPINION_MAX_DIFF_CHARS`, or `SECOND_OPINION_MAX_PATCH_CHARS` if you need more\u002Fless context.\n2. **(Optional) Inspect\u002Ftweak** `\u002Ftmp\u002Fmcp_request.json` to refine the natural-language question while keeping the attached git context intact.\n3. **Get authentication token** (auto-refresh from AI Universe repo):\n   ```bash\n   # Get token (auto-refreshes if expired, does nothing if valid)\n   TOKEN=$(node ~\u002F.claude\u002Fscripts\u002Fauth-cli.mjs token)\n   ```\n4. **Send request** (allowing up to 180s for cold starts):\n   ```bash\n   http POST https:\u002F\u002Fai-universe-backend-dev-114133832173.us-central1.run.app\u002Fmcp \\\n     \"Accept:application\u002Fjson, text\u002Fevent-stream\" \\\n     \"Authorization:Bearer $TOKEN\" \\\n     \u003C \u002Ftmp\u002Fmcp_request.json \\\n     --timeout=180 \\\n     --print=b > \u002Ftmp\u002Fmcp_response.json\n   ```\n5. **Parse embedded JSON** and display summary (or use the helper script):\n   ```bash\n   jq -r '.result.content[0].text' \u002Ftmp\u002Fmcp_response.json > \u002Ftmp\u002Fmcp_parsed.json\n   python3 \u003C\u003C'PYEOF'\n   import json\n   with open('\u002Ftmp\u002Fmcp_parsed.json', 'r') as f:\n       data = json.load(f)\n   print(f\"✅ Received responses from {data['summary']['totalModels']} models\")\n   print(f\"? Total cost: ${data['summary']['totalCost']:.4f}\")\n   print(f\"? Total tokens: {data['summary']['totalTokens']:,}\")\n   print(\"\\nPrimary response:\\n\")\n   print(data['primary']['response'])\n   PYEOF\n   ```\n   Or run:\n   ```bash\n   python3 skills\u002Fsecond_opinion_workflow\u002Fscripts\u002Fparse_second_opinion.py \u002Ftmp\u002Fmcp_parsed.json\n   ```\n6. **Review synthesis** to confirm consensus and recommended actions.\n\n> ? Need more HTTPie patterns? Use [ai-universe-httpie.md](ai-universe-httpie.md) as a companion reference.\n\n## SlashCommand fallback (Option A)\nUse `\u002Fsecondo \"QUESTION\"` for quick prompts **only when the command file is healthy**. If it fails or hangs, switch to the HTTPie workflow.\n\n## Automation helper script\nRun the bundled script from repo root for a streamlined flow:\n```bash\nskills\u002Fsecond_opinion_workflow\u002Fscripts\u002Frequest_second_opinion.sh \"How should I harden our auth endpoints?\" 4\n```\nThe script:\n1. Validates token presence and checks that `MAX_OPINIONS` is a positive integer.\n2. Invokes `build_second_opinion_request.py` to embed branch\u002Fbase metadata, diffstat, recent commits, and per-file patches into the payload.\n3. Calls the MCP endpoint with HTTPie and a 180s timeout.\n4. Parses the embedded JSON and prints model count, token usage, cost, and the primary + synthesis responses.\n5. Writes raw artifacts to `\u002Ftmp`; set `KEEP_TEMP_FILES=1` when running the script to keep them after completion.\n\nFor advanced prompting templates and interactive options, see the existing `~\u002F.claude\u002Fscripts\u002Fsecondo-cli.sh` utility.\n\n## Troubleshooting\n- **502 Bad Gateway \u002F cold start** → Retry after 30–60 seconds. Send a lightweight `\"What is 2+2?\"` request first to warm the backend.\n- **401 Unauthorized \u002F invalid token** → Token expired (30-day TTL). Re-run `node scripts\u002Fauth-cli.mjs login` outside Claude Code.\n- **\"command -c invalid\" errors** → Avoid nested command substitutions. Use heredocs + two-step token capture as shown above.\n- **Parsing failures** → Always extract `.result.content[0].text` before loading JSON. Use the helper Python snippet or script for safe parsing.\n\n## Cost & rate limits\n- Authenticated users: 100 requests\u002Fhour, with multi-model synthesis limited to 1\u002Fhr.\n- Typical cost ranges: $0.01–$0.20 depending on prompt complexity.\n- Model cost breakdown (approx.): Cerebras $0.003, Gemini 2.5 Flash $0.001, Perplexity $0.002, GPT-4o $0.10, synthesis $0.005.\n\n## Reporting expectations\n- Confirm authentication status and whether `\u002Fsecondo` or HTTPie path was used.\n- Provide model count, total tokens, and total cost from the parsed summary.\n- Include primary + synthesis takeaways or recommended next actions.\n- Note any errors encountered and remediation steps (e.g., re-authentication, retries).\n\n## Related references\n- `skills\u002Fsecond_opinion_workflow\u002Fscripts\u002F` for helper tooling.\n- [ai-universe-auth.md](ai-universe-auth.md) for login instructions.\n- [secondo-dependencies.md](secondo-dependencies.md) for HTTPie\u002FJQ requirements.\n- [ai-universe-httpie.md](ai-universe-httpie.md) for advanced HTTPie patterns.\n","# AI Universe Second Opinion Workflow\n\n**Quick start:** Use `\u002Fsecondo` or the HTTPie helper script to gather multi-model analysis (Cerebras, Gemini, Perplexity, GPT-4o + synthesis).\n\n---\n\n## Activation cues\n- Requests to run or debug the AI Universe \"second opinion\" workflow.\n- Follow-ups after failed `\u002Fsecondo` runs or HTTPie 401\u002F5xx errors.\n- Planning sessions that need step-by-step instructions for MCP calls.\n- Questions about cost, rate limits, or interpreting multi-model output.\n\n## Prerequisites & authentication\n1. **Verify auth-cli.mjs installation**:\n   ```bash\n   test -f ~\u002F.claude\u002Fscripts\u002Fauth-cli.mjs && echo \"✅ Installed\" || echo \"❌ Not found - run \u002Flocalexportcommands\"\n   ```\n2. **Check authentication status**:\n   ```bash\n   node ~\u002F.claude\u002Fscripts\u002Fauth-cli.mjs status\n   ```\n3. **If not authenticated or token expired**, run login (opens browser for OAuth):\n   ```bash\n   # Run this outside Claude Code in a regular terminal\n   node ~\u002F.claude\u002Fscripts\u002Fauth-cli.mjs login\n   ```\n4. Ensure `http` (HTTPie), `jq`, `python3`, and `node` (>=20.0.0) are installed in the environment.\n\n> ℹ️ **Seamless Auto-Refresh**: The `\u002Fsecondo` command uses the exact same auth-cli.mjs from AI Universe repo. If your token is valid, it does nothing. If expired, it auto-refreshes using your refresh token (silent, no browser popup). Only prompts for login if refresh token expires (30+ days).\n\n> ℹ️ **Token Location**: All tokens stored in `~\u002F.ai-universe\u002Fauth-token.json` (same as AI Universe repo)\n> - ID token: 1-hour expiration\n> - Refresh token: enables 30+ day sessions\n\n> ℹ️ For a dedicated authentication walkthrough see [ai-universe-auth.md](ai-universe-auth.md). Dependency notes live in [secondo-dependencies.md](secondo-dependencies.md).\n\n## Primary commands\n| Scenario | Command |\n| --- | --- |\n| Quick question (when SlashCommand is working) | `\u002Fsecondo \"Should I use Redis or in-memory caching?\"` |\n| Build MCP request with PR context | `python3 skills\u002Fsecond_opinion_workflow\u002Fscripts\u002Fbuild_second_opinion_request.py \u002Ftmp\u002Fmcp_request.json \"QUESTION\" 3 origin\u002Fmain` |\n| Call MCP via HTTPie | `http POST https:\u002F\u002Fai-universe-backend-dev-114133832173.us-central1.run.app\u002Fmcp \"Authorization:Bearer $TOKEN\" \u003C \u002Ftmp\u002Fmcp_request.json --timeout=180 --print=b` |\n| Parse embedded JSON response | `jq -r '.result.content[0].text' \u002Ftmp\u002Fmcp_response.json > \u002Ftmp\u002Fmcp_parsed.json` |\n| Summarize models\u002Fcosts | `python3 skills\u002Fsecond_opinion_workflow\u002Fscripts\u002Fparse_second_opinion.py \u002Ftmp\u002Fmcp_parsed.json` |\n| End-to-end helper | `skills\u002Fsecond_opinion_workflow\u002Fscripts\u002Frequest_second_opinion.sh \"QUESTION\" [MAX_OPINIONS]` |\n\n## Recommended workflow (HTTPie)\n1. **Generate the request payload** (captures diff + per-file patches automatically):\n   ```bash\n   python3 skills\u002Fsecond_opinion_workflow\u002Fscripts\u002Fbuild_second_opinion_request.py \\\n     \u002Ftmp\u002Fmcp_request.json \\\n     \"YOUR QUESTION HERE\" \\\n     3 \\\n     origin\u002Fmain\n   ```\n   Adjust `SECOND_OPINION_MAX_FILES`, `SECOND_OPINION_MAX_DIFF_CHARS`, or `SECOND_OPINION_MAX_PATCH_CHARS` if you need more\u002Fless context.\n2. **(Optional) Inspect\u002Ftweak** `\u002Ftmp\u002Fmcp_request.json` to refine the natural-language question while keeping the attached git context intact.\n3. **Get authentication token** (auto-refresh from AI Universe repo):\n   ```bash\n   # Get token (auto-refreshes if expired, does nothing if valid)\n   TOKEN=$(node ~\u002F.claude\u002Fscripts\u002Fauth-cli.mjs token)\n   ```\n4. **Send request** (allowing up to 180s for cold starts):\n   ```bash\n   http POST https:\u002F\u002Fai-universe-backend-dev-114133832173.us-central1.run.app\u002Fmcp \\\n     \"Accept:application\u002Fjson, text\u002Fevent-stream\" \\\n     \"Authorization:Bearer $TOKEN\" \\\n     \u003C \u002Ftmp\u002Fmcp_request.json \\\n     --timeout=180 \\\n     --print=b > \u002Ftmp\u002Fmcp_response.json\n   ```\n5. **Parse embedded JSON** and display summary (or use the helper script):\n   ```bash\n   jq -r '.result.content[0].text' \u002Ftmp\u002Fmcp_response.json > \u002Ftmp\u002Fmcp_parsed.json\n   python3 \u003C\u003C'PYEOF'\n   import json\n   with open('\u002Ftmp\u002Fmcp_parsed.json', 'r') as f:\n       data = json.load(f)\n   print(f\"✅ Received responses from {data['summary']['totalModels']} models\")\n   print(f\"? Total cost: ${data['summary']['totalCost']:.4f}\")\n   print(f\"? Total tokens: {data['summary']['totalTokens']:,}\")\n   print(\"\\nPrimary response:\\n\")\n   print(data['primary']['response'])\n   PYEOF\n   ```\n   Or run:\n   ```bash\n   python3 skills\u002Fsecond_opinion_workflow\u002Fscripts\u002Fparse_second_opinion.py \u002Ftmp\u002Fmcp_parsed.json\n   ```\n6. **Review synthesis** to confirm consensus and recommended actions.\n\n> ? Need more HTTPie patterns? Use [ai-universe-httpie.md](ai-universe-httpie.md) as a companion reference.\n\n## SlashCommand fallback (Option A)\nUse `\u002Fsecondo \"QUESTION\"` for quick prompts **only when the command file is healthy**. If it fails or hangs, switch to the HTTPie workflow.\n\n## Automation helper script\nRun the bundled script from repo root for a streamlined flow:\n```bash\nskills\u002Fsecond_opinion_workflow\u002Fscripts\u002Frequest_second_opinion.sh \"How should I harden our auth endpoints?\" 4\n```\nThe script:\n1. Validates token presence and checks that `MAX_OPINIONS` is a positive integer.\n2. Invokes `build_second_opinion_request.py` to embed branch\u002Fbase metadata, diffstat, recent commits, and per-file patches into the payload.\n3. Calls the MCP endpoint with HTTPie and a 180s timeout.\n4. Parses the embedded JSON and prints model count, token usage, cost, and the primary + synthesis responses.\n5. Writes raw artifacts to `\u002Ftmp`; set `KEEP_TEMP_FILES=1` when running the script to keep them after completion.\n\nFor advanced prompting templates and interactive options, see the existing `~\u002F.claude\u002Fscripts\u002Fsecondo-cli.sh` utility.\n\n## Troubleshooting\n- **502 Bad Gateway \u002F cold start** → Retry after 30–60 seconds. Send a lightweight `\"What is 2+2?\"` request first to warm the backend.\n- **401 Unauthorized \u002F invalid token** → Token expired (30-day TTL). Re-run `node scripts\u002Fauth-cli.mjs login` outside Claude Code.\n- **\"command -c invalid\" errors** → Avoid nested command substitutions. Use heredocs + two-step token capture as shown above.\n- **Parsing failures** → Always extract `.result.content[0].text` before loading JSON. Use the helper Python snippet or script for safe parsing.\n\n## Cost & rate limits\n- Authenticated users: 100 requests\u002Fhour, with multi-model synthesis limited to 1\u002Fhr.\n- Typical cost ranges: $0.01–$0.20 depending on prompt complexity.\n- Model cost breakdown (approx.): Cerebras $0.003, Gemini 2.5 Flash $0.001, Perplexity $0.002, GPT-4o $0.10, synthesis $0.005.\n\n## Reporting expectations\n- Confirm authentication status and whether `\u002Fsecondo` or HTTPie path was used.\n- Provide model count, total tokens, and total cost from the parsed summary.\n- Include primary + synthesis takeaways or recommended next actions.\n- Note any errors encountered and remediation steps (e.g., re-authentication, retries).\n\n## Related references\n- `skills\u002Fsecond_opinion_workflow\u002Fscripts\u002F` for helper tooling.\n- [ai-universe-auth.md](ai-universe-auth.md) for login instructions.\n- [secondo-dependencies.md](secondo-dependencies.md) for HTTPie\u002FJQ requirements.\n- [ai-universe-httpie.md](ai-universe-httpie.md) for advanced HTTPie patterns.\n",{"type":31,"scope":29,"description":7},"main","42ccd02cbf5e8e47839dc3eab6fc754dc6b339cf",".claude\u002Fskills_archive\u002Flegacy-pre-2026-08-27\u002Fpackages\u002Fai-universe-second-opinion-workflow",0,"https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills","https:\u002F\u002Fgithub.com\u002Fjleechanorg","2026-11-11 22:19:36",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add jleechanorg\u002Fjleechan-skills --skill ai-universe-second-opinion-workflow",{"tool":51,"command":52},"bunx","bunx skills add jleechanorg\u002Fjleechan-skills --skill ai-universe-second-opinion-workflow",{"tool":54,"command":55},"pnpm","pnpm dlx skills add jleechanorg\u002Fjleechan-skills --skill ai-universe-second-opinion-workflow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills_archive\u002Flegacy-pre-2026-08-27\u002Fpackages\u002Fai-universe-second-opinion-workflow\u002FSKILL.md",true,[59,65],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"manifest.json","REFERENCE","参考文档",93,"https:\u002F\u002Fgithub.com\u002Fmanagedcode\u002Fdotnet-skills\u002Fblob\u002Fmain\u002Fcatalog\u002FFrameworks\u002FUno-Platform\u002Fskills\u002Funo-platform\u002Fmanifest.json",{"path":66,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fpatterns.md",10713,"https:\u002F\u002Fgithub.com\u002Fmanagedcode\u002Fdotnet-skills\u002Fblob\u002Fmain\u002Fcatalog\u002FFrameworks\u002FUno-Platform\u002Fskills\u002Funo-platform\u002Freferences\u002Fpatterns.md",[70,88,109,123,136,152],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":33},"01M716Y5MTJ6GYJZ2ATXCJK8G4","instinct","Use when the user invokes \u002Finstinct or \u002Fin, or asks to \"message Instinct\", \"ask Instinct\", \"tell Instinct\", \"check Instinct\", or read replies from the configured peer assistant. iMessage first, WhatsApp Web as fallback.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Finstinct\u002FSKILL.md",[],[72,77,78,79,80,81,82,83,84,85,86,87],"user","when","replies","check","use","identity","whatsapp","gmail","read","message","ask",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":99,"publishedAt":33},"01M716Y4HF7FVVMJSA2CCVN5VF","hr","Compatibility alias for history-resume; produce the same fresh-state, provenance-aware resume briefing.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhr\u002FSKILL.md",[94],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[90,100,101,102,32,103,104,105,106,107,108],"resume","compatibility","provenance","history","produce","alias","briefing","state","fresh",{"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":116,"publishedAt":33},"01M716Y1FFNFKFJYYKF8HQA6T8","history-resume","Resume briefing for the current repository branch or worktree using fresh state and admitted history sources.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhistory-resume\u002FSKILL.md",[115],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},[103,100,117,118,77,119,106,120,32,121,122,107,108],"history resume","branch","analysis","repository","worktree","sources",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":33},"01M716XWXJ8EPHK4RH9T14TR85","grok","Alias for the canonical grokbot browser conversation workflow; \u002Fgrok talks to the Grok bot the same way \u002Fdot talks to Dot.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fgrok\u002FSKILL.md",[],[125,130,131,23,32,132,105,133,134,135],"dot","bot","canonical","conversation","browser","grokbot",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":33},"01M70N9Q07DTE0EW5KFXMMMSJ0","codexa-bench","Compare `codexa` and normal `codex` on a fair split of comparable work by default; use `--strict` for duplicate runs of the exact same task.","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcodexa-bench\u002FSKILL.md",[],[143,144,145,81,146,32,147,148,149,150,151],"codexa bench","work","split","default","duplicate","task","compare","normal","codex",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":156,"licenseFileUrl":157,"sourceHtmlUrl":158,"categories":159,"keywords":169,"publishedAt":33},"01M6C24S2X60SP8BBFGAEKPEGW","frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML\u002FCSS layouts, or when styling\u002Fbeautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ffrontend-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fjleechanorg\u002Fjleechan-skills\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ffrontend-design\u002FSKILL.md",[160,163,166],{"categoryNo":161,"categoryName":162,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":164,"categoryName":165,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":167,"categoryName":168,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000032","设计师",[170,171,172,81,173,174,175,77,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,78,194],"frontend","design","frontend design","generic","ui design","react","html","components","code","artifacts","ui","aesthetics","Production","web components","landing","applications","quality","web","css","create","examples","with","react components","web ui","pages"]