[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70M8RWXBKPEPF5JKYBV15PG":3,"skill-same:01M70M8RWXBKPEPF5JKYBV15PG":84},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":61,"commitSha":62,"skillDirectory":63,"forksCount":64,"repositoryHtmlUrl":65,"repositoryHomepageUrl":66,"ownerHtmlUrl":67,"ownerBlogUrl":68,"ownerDescription":69,"updatedAt":70,"install":71,"resources":83},"01M70M8RWXBKPEPF5JKYBV15PG","smoke-test",null,"Post-restart smoke tests + auto-fix for gbrain and OpenClaw environments.\nTests critical services, auto-fixes known issues, extensible via user-defined\ntest scripts in ~\u002F.gbrain\u002Fsmoke-tests.d\u002F*.sh.","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\u002Fgbrain-smoke-test\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"smoke test","test","smoke","tests","true","for","fixes","restart","environments","openclaw","read","scripts","break","run","run smoke tests","critical","auto","auto-fix","issues","fix","2026-11-10 10:12:30",false,"---\nname: smoke-test\ndescription: |\n  Post-restart smoke tests + auto-fix for gbrain and OpenClaw environments.\n  Tests critical services, auto-fixes known issues, extensible via user-defined\n  test scripts in ~\u002F.gbrain\u002Fsmoke-tests.d\u002F*.sh.\ntriggers:\n  - \"smoke test\"\n  - \"run smoke tests\"\n  - \"container restart check\"\n  - \"health check\"\n  - \"did the restart break anything\"\n  - \"did the container restart break anything\"\ntools:\n  - exec\n  - read\nmutating: true\n---\n\n# Smoke Test Skillpack\n\n> Run `gbrain smoke-test` or `bash scripts\u002Fsmoke-test.sh` after any container restart.\n\n## Contract\n\nThis skill guarantees:\n- 8 core tests verify gbrain + OpenClaw health after restart\n- Known failures are auto-fixed before reporting\n- User-extensible via `~\u002F.gbrain\u002Fsmoke-tests.d\u002F*.sh` drop-in scripts\n- Results logged to `\u002Ftmp\u002Fgbrain-smoke-test.log`\n- Exit code = number of unfixed failures (0 = all pass)\n\n## Built-in Tests\n\n| # | Test | Auto-Fix |\n|---|------|----------|\n| 1 | Bun runtime | Install from bun.sh |\n| 2 | GBrain CLI loads | Reinstall deps |\n| 3 | GBrain database (doctor) | — |\n| 4 | GBrain worker process | Start worker |\n| 5 | OpenClaw Codex plugin (Zod CJS) | `npm install zod@4 --force` |\n| 6 | OpenClaw gateway | — (may not be started yet) |\n| 7 | Embedding API key | — (check .env) |\n| 8 | Brain repo exists | — |\n\n## Usage\n\n### CLI\n```bash\ngbrain smoke-test\n```\n\n### Direct\n```bash\nbash scripts\u002Fsmoke-test.sh\n```\n\n### From OpenClaw bootstrap\nAdd to your `ensure-services.sh` or equivalent:\n```bash\nbash \u002Fpath\u002Fto\u002Fgbrain\u002Fscripts\u002Fsmoke-test.sh >> \u002Ftmp\u002Fbootstrap.log 2>&1\n```\n\n### From an agent\n```\nexec: bash \u002Fdata\u002Fgbrain\u002Fscripts\u002Fsmoke-test.sh\n```\n\n## Adding Custom Tests\n\nCreate executable scripts in `~\u002F.gbrain\u002Fsmoke-tests.d\u002F`:\n\n```bash\n# ~\u002F.gbrain\u002Fsmoke-tests.d\u002Fcheck-redis.sh\n#!\u002Fbin\u002Fbash\nredis-cli ping | grep -q PONG\n```\n\nRules:\n- Exit 0 = pass, non-zero = fail\n- Filename becomes the test name (e.g. `check-redis` from `check-redis.sh`)\n- Keep tests fast (\u003C 10s each)\n- Tests run in alphabetical order\n\n## Adding Built-in Tests\n\nEdit `scripts\u002Fsmoke-test.sh`. Follow this pattern:\n\n```bash\n# ── N. [Service Name] ──────────────────────────────────────\nif [test condition]; then\n  pass \"[Service Name]\"\nelse\n  # Auto-fix attempt\n  [fix command]\n  if [re-test condition]; then\n    fixed \"[What was fixed]\"\n    pass \"[Service Name] (after fix)\"\n  else\n    fail \"[Service Name] — [error detail]\"\n  fi\nfi\n```\n\n### Design rules:\n1. **Test first** — never fix without confirming broken\n2. **Re-test after fix** — verify the fix worked\n3. **Timeout everything** — `timeout N` on any command that could hang\n4. **Use helpers** — `pass()`, `fail()`, `fixed()`, `skip()`\n5. **Idempotent fixes** — safe to run repeatedly\n6. **Skip gracefully** — `skip()` when a prerequisite is missing, don't fail\n\n## Environment Variables\n\n| Var | Default | Description |\n|-----|---------|-------------|\n| `GBRAIN_SMOKE_LOG` | `\u002Ftmp\u002Fgbrain-smoke-test.log` | Log file path |\n| `GBRAIN_DIR_OVERRIDE` | (auto-detect) | Force gbrain install path |\n| `GBRAIN_DATABASE_URL` | (from .env) | Database connection URL |\n| `OPENCLAW_GATEWAY_PORT` | `18789` | Gateway port to test |\n| `GBRAIN_BRAIN_PATH` | `\u002Fdata\u002Fbrain` | Brain repo path |\n\n## Known Issues & Their Auto-Fixes\n\n### Codex Zod core.cjs Missing (discovered 2026-04-23)\n- **Symptom:** `Cannot find module '.\u002Fcore.cjs'` → all Codex ACP sessions fail\n- **Cause:** Zod v4 npm package ships without `core.cjs` in some installs\n- **Auto-fix:** `npm install zod@4 --force` in the codex extension's zod dir\n- **Persistence:** Does NOT survive container restart (gateway reinstalls deps)\n- This is why smoke tests must run on every restart\n\n### GBrain Worker Auth Failure\n- **Symptom:** Worker can't connect to DB\n- **Cause:** `GBRAIN_DATABASE_URL` not propagated to worker subprocess\n- **Auto-fix:** Script explicitly passes both `DATABASE_URL` and `GBRAIN_DATABASE_URL`\n\n## Anti-Patterns\n\n- ❌ Running smoke tests on every chat turn. Once per container restart (or\n  on user request) is plenty. The script is cheap but it's not free.\n- ❌ Writing a user drop-in without `timeout N` around any command that\n  could hang. A single hung drop-in stalls every subsequent run.\n- ❌ Auto-fixing without confirming the check is actually broken first.\n  The `pass → fail-detected → fix → re-test` loop is the contract; fixes\n  that skip the re-test can report success on a still-broken state.\n- ❌ Treating `skip` as `fail`. Missing prerequisites (no OpenClaw installed,\n  no brain repo configured) are skips, not failures. Exit code = count of\n  real failures, not skipped checks.\n- ❌ Hardcoding paths in a user drop-in. Read env vars\n  (`GBRAIN_DATABASE_URL`, `HOME`, etc.) so the script travels across\n  container rebuilds.\n\n## Output Format\n\nThe script writes a one-line status per check to stdout (✅\u002F❌\u002F🔧\u002F⏭️) plus a\nfinal summary line: `Results: N\u002FM passed, F auto-fixed, S skipped`. A\nstructured timestamped log appends to `$GBRAIN_SMOKE_LOG`\n(default `\u002Ftmp\u002Fgbrain-smoke-test.log`) for post-run forensics. Exit code\nequals the count of unfixed failures (0 = all pass, positive integer =\ncount of remaining failures).\n","# Smoke Test Skillpack\n\n> Run `gbrain smoke-test` or `bash scripts\u002Fsmoke-test.sh` after any container restart.\n\n## Contract\n\nThis skill guarantees:\n- 8 core tests verify gbrain + OpenClaw health after restart\n- Known failures are auto-fixed before reporting\n- User-extensible via `~\u002F.gbrain\u002Fsmoke-tests.d\u002F*.sh` drop-in scripts\n- Results logged to `\u002Ftmp\u002Fgbrain-smoke-test.log`\n- Exit code = number of unfixed failures (0 = all pass)\n\n## Built-in Tests\n\n| # | Test | Auto-Fix |\n|---|------|----------|\n| 1 | Bun runtime | Install from bun.sh |\n| 2 | GBrain CLI loads | Reinstall deps |\n| 3 | GBrain database (doctor) | — |\n| 4 | GBrain worker process | Start worker |\n| 5 | OpenClaw Codex plugin (Zod CJS) | `npm install zod@4 --force` |\n| 6 | OpenClaw gateway | — (may not be started yet) |\n| 7 | Embedding API key | — (check .env) |\n| 8 | Brain repo exists | — |\n\n## Usage\n\n### CLI\n```bash\ngbrain smoke-test\n```\n\n### Direct\n```bash\nbash scripts\u002Fsmoke-test.sh\n```\n\n### From OpenClaw bootstrap\nAdd to your `ensure-services.sh` or equivalent:\n```bash\nbash \u002Fpath\u002Fto\u002Fgbrain\u002Fscripts\u002Fsmoke-test.sh >> \u002Ftmp\u002Fbootstrap.log 2>&1\n```\n\n### From an agent\n```\nexec: bash \u002Fdata\u002Fgbrain\u002Fscripts\u002Fsmoke-test.sh\n```\n\n## Adding Custom Tests\n\nCreate executable scripts in `~\u002F.gbrain\u002Fsmoke-tests.d\u002F`:\n\n```bash\n# ~\u002F.gbrain\u002Fsmoke-tests.d\u002Fcheck-redis.sh\n#!\u002Fbin\u002Fbash\nredis-cli ping | grep -q PONG\n```\n\nRules:\n- Exit 0 = pass, non-zero = fail\n- Filename becomes the test name (e.g. `check-redis` from `check-redis.sh`)\n- Keep tests fast (\u003C 10s each)\n- Tests run in alphabetical order\n\n## Adding Built-in Tests\n\nEdit `scripts\u002Fsmoke-test.sh`. Follow this pattern:\n\n```bash\n# ── N. [Service Name] ──────────────────────────────────────\nif [test condition]; then\n  pass \"[Service Name]\"\nelse\n  # Auto-fix attempt\n  [fix command]\n  if [re-test condition]; then\n    fixed \"[What was fixed]\"\n    pass \"[Service Name] (after fix)\"\n  else\n    fail \"[Service Name] — [error detail]\"\n  fi\nfi\n```\n\n### Design rules:\n1. **Test first** — never fix without confirming broken\n2. **Re-test after fix** — verify the fix worked\n3. **Timeout everything** — `timeout N` on any command that could hang\n4. **Use helpers** — `pass()`, `fail()`, `fixed()`, `skip()`\n5. **Idempotent fixes** — safe to run repeatedly\n6. **Skip gracefully** — `skip()` when a prerequisite is missing, don't fail\n\n## Environment Variables\n\n| Var | Default | Description |\n|-----|---------|-------------|\n| `GBRAIN_SMOKE_LOG` | `\u002Ftmp\u002Fgbrain-smoke-test.log` | Log file path |\n| `GBRAIN_DIR_OVERRIDE` | (auto-detect) | Force gbrain install path |\n| `GBRAIN_DATABASE_URL` | (from .env) | Database connection URL |\n| `OPENCLAW_GATEWAY_PORT` | `18789` | Gateway port to test |\n| `GBRAIN_BRAIN_PATH` | `\u002Fdata\u002Fbrain` | Brain repo path |\n\n## Known Issues & Their Auto-Fixes\n\n### Codex Zod core.cjs Missing (discovered 2026-04-23)\n- **Symptom:** `Cannot find module '.\u002Fcore.cjs'` → all Codex ACP sessions fail\n- **Cause:** Zod v4 npm package ships without `core.cjs` in some installs\n- **Auto-fix:** `npm install zod@4 --force` in the codex extension's zod dir\n- **Persistence:** Does NOT survive container restart (gateway reinstalls deps)\n- This is why smoke tests must run on every restart\n\n### GBrain Worker Auth Failure\n- **Symptom:** Worker can't connect to DB\n- **Cause:** `GBRAIN_DATABASE_URL` not propagated to worker subprocess\n- **Auto-fix:** Script explicitly passes both `DATABASE_URL` and `GBRAIN_DATABASE_URL`\n\n## Anti-Patterns\n\n- ❌ Running smoke tests on every chat turn. Once per container restart (or\n  on user request) is plenty. The script is cheap but it's not free.\n- ❌ Writing a user drop-in without `timeout N` around any command that\n  could hang. A single hung drop-in stalls every subsequent run.\n- ❌ Auto-fixing without confirming the check is actually broken first.\n  The `pass → fail-detected → fix → re-test` loop is the contract; fixes\n  that skip the re-test can report success on a still-broken state.\n- ❌ Treating `skip` as `fail`. Missing prerequisites (no OpenClaw installed,\n  no brain repo configured) are skips, not failures. Exit code = count of\n  real failures, not skipped checks.\n- ❌ Hardcoding paths in a user drop-in. Read env vars\n  (`GBRAIN_DATABASE_URL`, `HOME`, etc.) so the script travels across\n  container rebuilds.\n\n## Output Format\n\nThe script writes a one-line status per check to stdout (✅\u002F❌\u002F🔧\u002F⏭️) plus a\nfinal summary line: `Results: N\u002FM passed, F auto-fixed, S skipped`. A\nstructured timestamped log appends to `$GBRAIN_SMOKE_LOG`\n(default `\u002Ftmp\u002Fgbrain-smoke-test.log`) for post-run forensics. Exit code\nequals the count of unfixed failures (0 = all pass, positive integer =\ncount of remaining failures).\n",{"name":5,"tools":52,"mutating":54,"triggers":55,"description":60},[53,37],"exec",true,[27,41,56,57,58,59],"container restart check","health check","did the restart break anything","did the container restart break anything","Post-restart smoke tests + auto-fix for gbrain and OpenClaw environments.\nTests critical services, auto-fixes known issues, extensible via user-defined\ntest scripts in ~\u002F.gbrain\u002Fsmoke-tests.d\u002F*.sh.\n","main","7850740bd837adb32f0a109ab2af82482196c6f2","skills\u002Fgbrain-smoke-test",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":72,"prompt":82,"zipAvailable":54},[73,76,79],{"tool":74,"command":75},"npx","npx skills add shengdabai\u002FTony-Claude-Code-Skills --skill smoke-test",{"tool":77,"command":78},"bunx","bunx skills add shengdabai\u002FTony-Claude-Code-Skills --skill smoke-test",{"tool":80,"command":81},"pnpm","pnpm dlx skills add shengdabai\u002FTony-Claude-Code-Skills --skill smoke-test","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fgbrain-smoke-test\u002FSKILL.md",[],[85,94,102,110,118,126],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":89,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":93},"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":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":98,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":93},"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":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":93},"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":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":114,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":93},"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":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":122,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":93},"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":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":93},"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",[],[]]