[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBNFXF9PESY5H1WXQ6MM9K":3,"skill-same:01M6DBNFXF9PESY5H1WXQ6MM9K":68},{"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":18,"publishedAt":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":14,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M6DBNFXF9PESY5H1WXQ6MM9K","packaged-artifact-smoke",null,"Use when you need to prove a BUILT deliverable actually works end-to-end, not just that its source tree is CI-green. Runs 3-5 golden journeys against the PACKAGED artifact (the built Electron binary via `_electron.launch`, or `pip install dist\u002F*.whl` in a fresh venv then invoke the installed CLI), each ending in a DETERMINISTIC on-disk postcondition probe (ffprobe, or file existence + size).","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpackaged-artifact-smoke\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"smoke","packaged artifact smoke","artifact","file","ci","disk","just","install","use","cli","probe","deterministic","launch","green","end","binary","fresh","electron","2026-11-10 10:12:30",false,"---\nname: packaged-artifact-smoke\ndescription: Use when you need to prove a BUILT deliverable actually works end-to-end, not just that its source tree is CI-green. Runs 3-5 golden journeys against the PACKAGED artifact (the built Electron binary via `_electron.launch`, or `pip install dist\u002F*.whl` in a fresh venv then invoke the installed CLI), each ending in a DETERMINISTIC on-disk postcondition probe (ffprobe, or file existence + size).\n---\n# Packaged-Artifact \u002F Effect-Assertion Smoke Runner\n\nProve the **built deliverable** does its job — by driving it and then asserting a\n**real artifact on disk**, deterministically. This is the one class of gap that a\ngreen source tree cannot catch: the code compiles, unit tests pass, coverage is\n100%, and the shipped `.exe` \u002F `.whl` still fails to launch or produces a broken\nfile because of a packaging error (missing runtime dependency, electron-builder\nresource mis-map, wheel metadata that imports but cannot execute).\n\n**Local precedent (why this exists):** Reframe v1.4 was CI-green on every unit\ntest yet the packaged app surfaced a cascade of latent packaging gaps only when\nrun end-to-end on the real target — `--no-deps` installs missing hypothesis\u002Fhttpx,\nunpinned opencv, `electron-builder --publish-never`, `assets.ensure` silently\nskipping. See gem-hunt **MASTER A-Tier2 packaged-artifact gate** (⊕3, REC\nBUILD-lite) and **agentic-repair-1 #4\u002F#5, agentic-repair-2 #4**.\n\n## The shape of a golden journey\n\nEach journey has two halves:\n\n1. **RUN** — invoke the *packaged* deliverable (never the source tree):\n   - **Electron:** Playwright's `_electron.launch({ executablePath: \u003CbuiltBinary> })`,\n     drive a minimal flow, trigger the export.\n   - **Python wheel:** `pip install dist\u002F*.whl` into a **fresh venv**, then run the\n     installed console-script \u002F `python -m pkg` on a fixture input.\n   - **Any CLI:** exec the built binary on a fixture.\n2. **POSTCONDITION PROBE** — assert the artifact it produced:\n   - `media` → `ffprobe` reads container \u002F video+audio codec \u002F width×height \u002F\n     duration (e.g. Reframe must emit a **non-zero, 1080×1920** mp4).\n   - `exists` → the file exists on disk and is ≥ N bytes (catches 0-byte \u002F silent-skip).\n\nKeep it to **3–5 journeys** — the highest-value user paths, not exhaustive coverage.\nCoverage is the source tree's job; this gate answers \"does the *thing we ship* work\".\n\n## The reusable helper: `postcondition.mjs`\n\nZero third-party deps — Node stdlib + system `ffprobe`\u002F`ffmpeg`. Import it as a\nlibrary (this is the primary use; A2-golden-journey-oracle and any pain app consume\nit) or drive it as a CLI.\n\n### Library API\n\n```js\nimport {\n  probeMedia, assertMedia, assertExists,\n  runJourney, runManifest, installWheelFreshVenv,\n} from '.\u002Fpostcondition.mjs';\n\n\u002F\u002F Probe -> normalized descriptor\nconst p = probeMedia('out\u002Fclip.mp4');\n\u002F\u002F { container, durationSec, sizeBytes, videoCodec, audioCodec, width, height, fps, nbStreams }\n\n\u002F\u002F Assert a produced media artifact (all expect fields optional)\nconst r = assertMedia('out\u002Fclip.mp4', {\n  container: 'mp4',        \u002F\u002F substring, case-insensitive (ffprobe returns a comma list)\n  videoCodec: 'h264', audioCodec: 'aac', hasAudio: true,\n  width: 1080, height: 1920,        \u002F\u002F exact\n  minWidth: 1080, minHeight: 1920,  \u002F\u002F or lower-bounds\n  minDurationSec: 0.5, maxDurationSec: 600,\n  minBytes: 1000,\n});\n\u002F\u002F -> { ok, checks:[{name,expected,actual,pass}], probe }\n\nassertExists('out\u002Freport.json', { minBytes: 2 });  \u002F\u002F -> { ok, checks, sizeBytes }\n\n\u002F\u002F Fresh-venv wheel install (proves the wheel installs from clean, not just imports)\nconst { python, venvDir } = installWheelFreshVenv('dist\u002Fapp-1.0-py3-none-any.whl');\n```\n\n### Journey \u002F manifest schema\n\n```jsonc\n{\n  \"app\": \"reframe\",\n  \"journeys\": [\n    {\n      \"id\": \"reframe-emits-1080x1920\",\n      \"run\": {                          \u002F\u002F omit for a probe-only journey\n        \"cmd\": \"C:\u002Fpath\u002Fto\u002FReframe.exe\", \u002F\u002F or the fresh-venv python, or a Playwright driver script\n        \"args\": [\"--in\", \"fixtures\u002Fland.mp4\", \"--out\", \"out\u002Fvert.mp4\"],\n        \"cwd\": \"C:\u002Fwork\", \"timeoutMs\": 180000, \"env\": {}, \"shell\": false\n      },\n      \"postcondition\": {\n        \"type\": \"media\",\n        \"file\": \"out\u002Fvert.mp4\",         \u002F\u002F relative resolves against run.cwd\n        \"expect\": { \"width\": 1080, \"height\": 1920, \"minDurationSec\": 1, \"minBytes\": 10000 }\n      }\n    }\n  ]\n}\n```\n\n`runJourney(journey)` returns a terminal-state receipt\n`{ id, outcome:'PASS'|'FAIL', run, assertion }`. If the RUN step exits non-zero the\njourney fails **without** probing (the build itself broke). `runManifest(manifest)`\nruns all journeys, prints per-journey `SUCCESS:\u003Cid>` \u002F `FAILED:\u003Cid> …` markers and a\nsummary, and returns `{ total, passed, failed, ok, receipts, enforce }`.\n\n### CLI\n\n```bash\nnode postcondition.mjs run \u003Cmanifest.json>            # SHADOW (default): observe+log, ALWAYS exit 0\nnode postcondition.mjs run \u003Cmanifest.json> --enforce  # blocking: exit 1 on any journey failure\nnode postcondition.mjs probe \u003Cfile>                   # dump ffprobe descriptor as JSON\nnode postcondition.mjs assert \u003Cfile> --width 1080 --height 1920 --videoCodec h264\nnode postcondition.mjs selftest                       # synthesize a fixture and self-verify (11 checks)\n```\n\n## Shadow-mode discipline (council C5 — mandatory)\n\nThis runner is **invoked only on demand** and defaults to **SHADOW**: it observes,\nlogs a structured report, and **exits 0 regardless of assertion outcome** — it can\nnever block a build or nag. A caller opts into blocking with `--enforce` (or\n`enforce:true`). The council **fast-tracks this class** (deterministic,\nnear-zero-false-positive, tautological) to `ENFORCE` after a **1-session burn-in**\nper repo — an ffprobe assertion cannot be miscalibrated, so a 4-stage ladder on it\nis pure time-to-value tax. Still: only turn on `--enforce` for a specific pain app\nonce a **signed golden journey exists** for it and it has cleared its burn-in\n(council C4\u002FC5). Route high-frequency shadow logs to a bounded, rotating sink — never\nthe main `terminal.jsonl` ledger.\n\n## When NOT to use\n\n- Unit \u002F integration tests on the **source** tree → `tdd-workflow`,\n  `smallest-check-ladder`.\n- Pixel \u002F design-quality critique of a running UI → `ui-audit`.\n- Transcription, caption cue generation, watermark removal → the media skills.\n- As a generic \"run any ffmpeg command\" helper — it is scoped to the\n  RUN-then-postcondition-probe contract above.\n\n## Requirements\n\n- Node ≥ 18 (uses `node:` builtins; ESM). Verified on Node 24 \u002F Windows.\n- `ffprobe` (and `ffmpeg` for `selftest`) on `PATH`, or set `FFPROBE` \u002F `FFMPEG`.\n- For wheel journeys: `python` on `PATH` (or set `PYTHON`).\n\n## Verification\n\n`node postcondition.mjs selftest` synthesizes a real 1080×1920 h264+aac mp4 with\nffmpeg and exercises probe \u002F assertMedia (pass **and** fail paths) \u002F assertExists \u002F\nrunManifest — 11 checks, all green on Node 24 + WinGet ffmpeg.\n","# Packaged-Artifact \u002F Effect-Assertion Smoke Runner\n\nProve the **built deliverable** does its job — by driving it and then asserting a\n**real artifact on disk**, deterministically. This is the one class of gap that a\ngreen source tree cannot catch: the code compiles, unit tests pass, coverage is\n100%, and the shipped `.exe` \u002F `.whl` still fails to launch or produces a broken\nfile because of a packaging error (missing runtime dependency, electron-builder\nresource mis-map, wheel metadata that imports but cannot execute).\n\n**Local precedent (why this exists):** Reframe v1.4 was CI-green on every unit\ntest yet the packaged app surfaced a cascade of latent packaging gaps only when\nrun end-to-end on the real target — `--no-deps` installs missing hypothesis\u002Fhttpx,\nunpinned opencv, `electron-builder --publish-never`, `assets.ensure` silently\nskipping. See gem-hunt **MASTER A-Tier2 packaged-artifact gate** (⊕3, REC\nBUILD-lite) and **agentic-repair-1 #4\u002F#5, agentic-repair-2 #4**.\n\n## The shape of a golden journey\n\nEach journey has two halves:\n\n1. **RUN** — invoke the *packaged* deliverable (never the source tree):\n   - **Electron:** Playwright's `_electron.launch({ executablePath: \u003CbuiltBinary> })`,\n     drive a minimal flow, trigger the export.\n   - **Python wheel:** `pip install dist\u002F*.whl` into a **fresh venv**, then run the\n     installed console-script \u002F `python -m pkg` on a fixture input.\n   - **Any CLI:** exec the built binary on a fixture.\n2. **POSTCONDITION PROBE** — assert the artifact it produced:\n   - `media` → `ffprobe` reads container \u002F video+audio codec \u002F width×height \u002F\n     duration (e.g. Reframe must emit a **non-zero, 1080×1920** mp4).\n   - `exists` → the file exists on disk and is ≥ N bytes (catches 0-byte \u002F silent-skip).\n\nKeep it to **3–5 journeys** — the highest-value user paths, not exhaustive coverage.\nCoverage is the source tree's job; this gate answers \"does the *thing we ship* work\".\n\n## The reusable helper: `postcondition.mjs`\n\nZero third-party deps — Node stdlib + system `ffprobe`\u002F`ffmpeg`. Import it as a\nlibrary (this is the primary use; A2-golden-journey-oracle and any pain app consume\nit) or drive it as a CLI.\n\n### Library API\n\n```js\nimport {\n  probeMedia, assertMedia, assertExists,\n  runJourney, runManifest, installWheelFreshVenv,\n} from '.\u002Fpostcondition.mjs';\n\n\u002F\u002F Probe -> normalized descriptor\nconst p = probeMedia('out\u002Fclip.mp4');\n\u002F\u002F { container, durationSec, sizeBytes, videoCodec, audioCodec, width, height, fps, nbStreams }\n\n\u002F\u002F Assert a produced media artifact (all expect fields optional)\nconst r = assertMedia('out\u002Fclip.mp4', {\n  container: 'mp4',        \u002F\u002F substring, case-insensitive (ffprobe returns a comma list)\n  videoCodec: 'h264', audioCodec: 'aac', hasAudio: true,\n  width: 1080, height: 1920,        \u002F\u002F exact\n  minWidth: 1080, minHeight: 1920,  \u002F\u002F or lower-bounds\n  minDurationSec: 0.5, maxDurationSec: 600,\n  minBytes: 1000,\n});\n\u002F\u002F -> { ok, checks:[{name,expected,actual,pass}], probe }\n\nassertExists('out\u002Freport.json', { minBytes: 2 });  \u002F\u002F -> { ok, checks, sizeBytes }\n\n\u002F\u002F Fresh-venv wheel install (proves the wheel installs from clean, not just imports)\nconst { python, venvDir } = installWheelFreshVenv('dist\u002Fapp-1.0-py3-none-any.whl');\n```\n\n### Journey \u002F manifest schema\n\n```jsonc\n{\n  \"app\": \"reframe\",\n  \"journeys\": [\n    {\n      \"id\": \"reframe-emits-1080x1920\",\n      \"run\": {                          \u002F\u002F omit for a probe-only journey\n        \"cmd\": \"C:\u002Fpath\u002Fto\u002FReframe.exe\", \u002F\u002F or the fresh-venv python, or a Playwright driver script\n        \"args\": [\"--in\", \"fixtures\u002Fland.mp4\", \"--out\", \"out\u002Fvert.mp4\"],\n        \"cwd\": \"C:\u002Fwork\", \"timeoutMs\": 180000, \"env\": {}, \"shell\": false\n      },\n      \"postcondition\": {\n        \"type\": \"media\",\n        \"file\": \"out\u002Fvert.mp4\",         \u002F\u002F relative resolves against run.cwd\n        \"expect\": { \"width\": 1080, \"height\": 1920, \"minDurationSec\": 1, \"minBytes\": 10000 }\n      }\n    }\n  ]\n}\n```\n\n`runJourney(journey)` returns a terminal-state receipt\n`{ id, outcome:'PASS'|'FAIL', run, assertion }`. If the RUN step exits non-zero the\njourney fails **without** probing (the build itself broke). `runManifest(manifest)`\nruns all journeys, prints per-journey `SUCCESS:\u003Cid>` \u002F `FAILED:\u003Cid> …` markers and a\nsummary, and returns `{ total, passed, failed, ok, receipts, enforce }`.\n\n### CLI\n\n```bash\nnode postcondition.mjs run \u003Cmanifest.json>            # SHADOW (default): observe+log, ALWAYS exit 0\nnode postcondition.mjs run \u003Cmanifest.json> --enforce  # blocking: exit 1 on any journey failure\nnode postcondition.mjs probe \u003Cfile>                   # dump ffprobe descriptor as JSON\nnode postcondition.mjs assert \u003Cfile> --width 1080 --height 1920 --videoCodec h264\nnode postcondition.mjs selftest                       # synthesize a fixture and self-verify (11 checks)\n```\n\n## Shadow-mode discipline (council C5 — mandatory)\n\nThis runner is **invoked only on demand** and defaults to **SHADOW**: it observes,\nlogs a structured report, and **exits 0 regardless of assertion outcome** — it can\nnever block a build or nag. A caller opts into blocking with `--enforce` (or\n`enforce:true`). The council **fast-tracks this class** (deterministic,\nnear-zero-false-positive, tautological) to `ENFORCE` after a **1-session burn-in**\nper repo — an ffprobe assertion cannot be miscalibrated, so a 4-stage ladder on it\nis pure time-to-value tax. Still: only turn on `--enforce` for a specific pain app\nonce a **signed golden journey exists** for it and it has cleared its burn-in\n(council C4\u002FC5). Route high-frequency shadow logs to a bounded, rotating sink — never\nthe main `terminal.jsonl` ledger.\n\n## When NOT to use\n\n- Unit \u002F integration tests on the **source** tree → `tdd-workflow`,\n  `smallest-check-ladder`.\n- Pixel \u002F design-quality critique of a running UI → `ui-audit`.\n- Transcription, caption cue generation, watermark removal → the media skills.\n- As a generic \"run any ffmpeg command\" helper — it is scoped to the\n  RUN-then-postcondition-probe contract above.\n\n## Requirements\n\n- Node ≥ 18 (uses `node:` builtins; ESM). Verified on Node 24 \u002F Windows.\n- `ffprobe` (and `ffmpeg` for `selftest`) on `PATH`, or set `FFPROBE` \u002F `FFMPEG`.\n- For wheel journeys: `python` on `PATH` (or set `PYTHON`).\n\n## Verification\n\n`node postcondition.mjs selftest` synthesizes a real 1080×1920 h264+aac mp4 with\nffmpeg and exercises probe \u002F assertMedia (pass **and** fail paths) \u002F assertExists \u002F\nrunManifest — 11 checks, all green on Node 24 + WinGet ffmpeg.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fpackaged-artifact-smoke","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill packaged-artifact-smoke",{"tool":54,"command":55},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill packaged-artifact-smoke",{"tool":57,"command":58},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill packaged-artifact-smoke","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpackaged-artifact-smoke\u002FSKILL.md",true,[62],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"postcondition.mjs","SCRIPT","脚本",18888,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpackaged-artifact-smoke\u002Fpostcondition.mjs",[69,89,120,147,161,177],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":37},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[76,77,78,79,80,81,82,83,84,27,85,86,87,88,22],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":100,"publishedAt":37},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[95],{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[101,102,103,104,105,106,107,108,109,110,111,112,113,114,27,115,116,117,118,119],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"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":132,"publishedAt":37},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[126,129],{"categoryNo":127,"categoryName":128,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":130,"categoryName":131,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000008","测试与质量",[133,134,135,136,137,138,139,140,141,142,102,143,144,145,146],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":37},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[149,154,155,156,157,158,159,160],"setup","report","project","installation","project setup","issues","state",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":168,"publishedAt":37},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[167],{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},[163,169,81,170,171,172,27,173,174,175,176],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":178,"name":154,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":37},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[154,156,117,183,158,184],"files","interactive"]