[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBWCNFQWH9EJ96GZTJYMG6":3,"skill-same:01M6DBWCNFQWH9EJ96GZTJYMG6":80},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":14,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M6DBWCNFQWH9EJ96GZTJYMG6","seed-golden-journey",null,"Use when an app needs a keystone acceptance test that proves the real product works end to end, not just that units pass or coverage is high. Scaffolds a HELD-OUT golden-journey test that launches the REAL app, drives the ONE primary user journey, and asserts a REAL artifact on disk (ffprobe media file, a downloaded file) rather than element-present. Parameterized for Electron, web, and CLI.","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\u002Fseed-golden-journey\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"seed golden journey","seed","journey","coverage","app","end","present","artifact","units","use","cli","just","disk","Media","file","product","acceptance","web","test","electron","2026-11-10 10:12:30",false,"---\nname: seed-golden-journey\ndescription: Use when an app needs a keystone acceptance test that proves the real product works end to end, not just that units pass or coverage is high. Scaffolds a HELD-OUT golden-journey test that launches the REAL app, drives the ONE primary user journey, and asserts a REAL artifact on disk (ffprobe media file, a downloaded file) rather than element-present. Parameterized for Electron, web, and CLI.\n---\n\n# seed-golden-journey\n\nCoverage and \"unit-green\" are a **proxy the implementer controls**, so a capable agent optimizes\nthat proxy and stops — while the real A→B→C user journey stays broken. Live proof: Reframe shipped\nv1.4 with **100% coverage and green units**, and \"Make Shorts\" never produced a file on Windows.\nThree real Windows-only bugs sat exactly at the seams the unit tests mock and Linux CI can't reach.\nThe one signal that caught them was a **held-out golden-journey that drove the real app and\nasserted a real vertical short on disk**.\n\nThis skill scaffolds that keystone: the single external **done-signal** the implementer can't\nauthor or fake. It is the highest-leverage thing a user provides — no hook substitutes for it.\n\n## The five rules of a golden journey\n\n1. **Pick the ONE money journey.** The single flow that is the product's reason to exist — the\n   thing that, if it silently broke, the product is worthless regardless of coverage. Reframe:\n   *\"Make Shorts produces a real vertical short file on disk.\"* One journey, not a matrix.\n2. **Drive the REAL app — nothing stubbed.** Launch the actual built binary\u002Fapp; drive the real\n   UI; let it hit the real backend\u002Fsidecar, real ffmpeg, real filesystem. The bugs live precisely\n   at the seams unit tests mock; a mocked journey re-hides them.\n3. **Assert a REAL produced artifact, not element-present.** \"Button rendered\" \u002F \"toast appeared\"\n   is theater. The pass condition is the *thing the user came for* existing and being valid on\n   disk: a media file that `ffprobe` confirms has the right dims + a real duration; a downloaded\n   file that opens; a screenshot whose pixels match. Walk the **assertion ladder** (below).\n4. **Held-out + merge gate.** Author it so the implementing agent can't see or edit it, keep it\n   out of the default test select (an `e2e`\u002F`acceptance` marker or a separate project), and make\n   it the merge gate. Coverage\u002Funit-green are necessary but **may NOT be cited as done**.\n5. **A faithful red-repro is success.** If the pipeline is broken, the correct behavior is to fail\n   with a diagnostic snapshot of what *did* land on disk — never a green fantasy. Red-repro first,\n   then fix until it goes green against the real artifact.\n\n## The assertion ladder (climb every rung — stopping early is theater)\n\n1. **Exists** — the output file is on disk at the path the app reports (`existsSync` \u002F `os.path`).\n2. **Non-empty** — `statSync(path).size > 0` — a 0-byte file is a silent failure.\n3. **Structurally valid** — it opens\u002Fparses: `ffprobe` decodes it; the archive unzips; the JSON\n   parses; the image loads. A file that exists but won't decode is still a broken product.\n4. **Semantically correct** — the values the journey promised: media is **portrait** (height >\n   width) with duration > 0; the export has the expected rows; the screenshot matches baseline.\n\n## Wiring the async completion (background jobs)\n\nMost real \"make it\" actions dispatch a background job and return immediately, so the UI note\nappears **before** the artifact exists. Prove completion by **polling the real status channel**\n(the same RPC the product's own gallery\u002Flist renders from), with a hard deadline and a\n**diagnostic snapshot on timeout** so a red-repro tells you which stage was reached:\n\n```ts\n\u002F\u002F poll the product's OWN list RPC, not a private test hook:\nwhile (Date.now() \u003C deadline) {\n  const snapshot = await listViaRealBridge(win, id);           \u002F\u002F e.g. shorts.list {videoId}\n  const finished = snapshot.find(s => s.id === id && s.durationSec > 0);  \u002F\u002F metadata-bearing = pipeline done\n  if (finished) return { finished, snapshot };\n  await sleep(1500);\n}\nreturn { finished: null, snapshot };   \u002F\u002F timeout → assert non-null WITH JSON(snapshot) in the message\n```\n\n## Stack recipes — the LAUNCH is the only part that changes\n\nThe journey shape (launch → drive → poll → assert real artifact) is identical across stacks; only\nthe launch\u002Fdrive surface differs. Full annotated spec: `templates\u002Fgolden-journey.template.spec.ts`\n(Electron\u002Fweb) and `templates\u002Fgolden-journey.cli.template.spec.ts` (CLI).\n\n- **Electron** (the Reframe exemplar):\n  ```ts\n  import { _electron as electron } from '@playwright\u002Ftest';\n  const app = await electron.launch({\n    args: [builtMainJs, '--no-sandbox'],\n    executablePath: packagedExe,   \u002F\u002F prefer the SHIPPED .exe; fall back to the dev build\n    env: seededEnv,                \u002F\u002F a fresh data root so nothing leaks between runs\n  });\n  const win = await app.firstWindow();\n  ```\n- **Web** (Playwright against the running app):\n  ```ts\n  test('golden journey', async ({ page }) => {\n    await page.goto(process.env.BASE_URL ?? 'http:\u002F\u002Flocalhost:3000');\n    \u002F\u002F ...drive the ONE journey, then assert the produced artifact:\n    const download = await Promise.all([\n      page.waitForEvent('download'),\n      page.getByRole('button', { name: 'Export' }).click(),\n    ]).then(([d]) => d);\n    const file = await download.path();      \u002F\u002F the REAL produced file → run the assertion ladder\n  });\n  ```\n- **CLI** (spawn the real command, assert its output file):\n  ```ts\n  import { execFileSync } from 'node:child_process';\n  execFileSync('mytool', ['build', '--in', fixture, '--out', outPath], { stdio: 'inherit' });\n  \u002F\u002F then: exists → non-empty → parses\u002Fffprobe → semantically correct\n  ```\n  Python equivalent: `subprocess.run([...], check=True)` then assert on `out_path`.\n\n## Make it the gate + forbid the reward-hack surface\n\n- **Keep it held out of normal runs and make it the merge gate.** In the task that hands work to\n  an implementer, use this line verbatim:\n  > *Done = the golden-journey exits 0 on a clean checkout. Coverage \u002F unit-green are necessary\n  > but NOT sufficient and may NOT be cited as done.*\n- **Forbid the gaming surface and verify against the diff.** No net-new `pragma:no-cover` \u002F\n  `xfail` \u002F `skip` \u002F coverage-omit \u002F `addopts` \u002F `-m` marker \u002F `collectCoverageFrom` \u002F CI-trigger\n  edits. Require the final report to include a `git diff` of every test\u002FCI\u002Fcoverage-config change —\n  that diff is where the gaming hides.\n- **Red-repro before every fix; attach the artifact with every \"fixed.\"** Script the failure as a\n  red golden-journey first; attach the produced mp4\u002Fscreenshot\u002Ffile, never an isolated unit test,\n  as proof.\n\n## Anti-patterns\n\n- Asserting an element\u002Ftoast is visible instead of a real artifact on disk.\n- Mocking the backend\u002Fsidecar\u002Fffmpeg \"to make the E2E deterministic\" — that re-hides the seam bugs.\n- Letting the implementing agent read or edit the spec (it will fit the exam to its code).\n- Citing coverage % or \"all units pass\" as the done-signal.\n- Claiming done on a single-frame \u002F single-poll check instead of polling to real completion with a\n  timeout snapshot.\n- A green result while the artifact is 0 bytes or won't decode (ladder stopped at rung 1).\n","# seed-golden-journey\n\nCoverage and \"unit-green\" are a **proxy the implementer controls**, so a capable agent optimizes\nthat proxy and stops — while the real A→B→C user journey stays broken. Live proof: Reframe shipped\nv1.4 with **100% coverage and green units**, and \"Make Shorts\" never produced a file on Windows.\nThree real Windows-only bugs sat exactly at the seams the unit tests mock and Linux CI can't reach.\nThe one signal that caught them was a **held-out golden-journey that drove the real app and\nasserted a real vertical short on disk**.\n\nThis skill scaffolds that keystone: the single external **done-signal** the implementer can't\nauthor or fake. It is the highest-leverage thing a user provides — no hook substitutes for it.\n\n## The five rules of a golden journey\n\n1. **Pick the ONE money journey.** The single flow that is the product's reason to exist — the\n   thing that, if it silently broke, the product is worthless regardless of coverage. Reframe:\n   *\"Make Shorts produces a real vertical short file on disk.\"* One journey, not a matrix.\n2. **Drive the REAL app — nothing stubbed.** Launch the actual built binary\u002Fapp; drive the real\n   UI; let it hit the real backend\u002Fsidecar, real ffmpeg, real filesystem. The bugs live precisely\n   at the seams unit tests mock; a mocked journey re-hides them.\n3. **Assert a REAL produced artifact, not element-present.** \"Button rendered\" \u002F \"toast appeared\"\n   is theater. The pass condition is the *thing the user came for* existing and being valid on\n   disk: a media file that `ffprobe` confirms has the right dims + a real duration; a downloaded\n   file that opens; a screenshot whose pixels match. Walk the **assertion ladder** (below).\n4. **Held-out + merge gate.** Author it so the implementing agent can't see or edit it, keep it\n   out of the default test select (an `e2e`\u002F`acceptance` marker or a separate project), and make\n   it the merge gate. Coverage\u002Funit-green are necessary but **may NOT be cited as done**.\n5. **A faithful red-repro is success.** If the pipeline is broken, the correct behavior is to fail\n   with a diagnostic snapshot of what *did* land on disk — never a green fantasy. Red-repro first,\n   then fix until it goes green against the real artifact.\n\n## The assertion ladder (climb every rung — stopping early is theater)\n\n1. **Exists** — the output file is on disk at the path the app reports (`existsSync` \u002F `os.path`).\n2. **Non-empty** — `statSync(path).size > 0` — a 0-byte file is a silent failure.\n3. **Structurally valid** — it opens\u002Fparses: `ffprobe` decodes it; the archive unzips; the JSON\n   parses; the image loads. A file that exists but won't decode is still a broken product.\n4. **Semantically correct** — the values the journey promised: media is **portrait** (height >\n   width) with duration > 0; the export has the expected rows; the screenshot matches baseline.\n\n## Wiring the async completion (background jobs)\n\nMost real \"make it\" actions dispatch a background job and return immediately, so the UI note\nappears **before** the artifact exists. Prove completion by **polling the real status channel**\n(the same RPC the product's own gallery\u002Flist renders from), with a hard deadline and a\n**diagnostic snapshot on timeout** so a red-repro tells you which stage was reached:\n\n```ts\n\u002F\u002F poll the product's OWN list RPC, not a private test hook:\nwhile (Date.now() \u003C deadline) {\n  const snapshot = await listViaRealBridge(win, id);           \u002F\u002F e.g. shorts.list {videoId}\n  const finished = snapshot.find(s => s.id === id && s.durationSec > 0);  \u002F\u002F metadata-bearing = pipeline done\n  if (finished) return { finished, snapshot };\n  await sleep(1500);\n}\nreturn { finished: null, snapshot };   \u002F\u002F timeout → assert non-null WITH JSON(snapshot) in the message\n```\n\n## Stack recipes — the LAUNCH is the only part that changes\n\nThe journey shape (launch → drive → poll → assert real artifact) is identical across stacks; only\nthe launch\u002Fdrive surface differs. Full annotated spec: `templates\u002Fgolden-journey.template.spec.ts`\n(Electron\u002Fweb) and `templates\u002Fgolden-journey.cli.template.spec.ts` (CLI).\n\n- **Electron** (the Reframe exemplar):\n  ```ts\n  import { _electron as electron } from '@playwright\u002Ftest';\n  const app = await electron.launch({\n    args: [builtMainJs, '--no-sandbox'],\n    executablePath: packagedExe,   \u002F\u002F prefer the SHIPPED .exe; fall back to the dev build\n    env: seededEnv,                \u002F\u002F a fresh data root so nothing leaks between runs\n  });\n  const win = await app.firstWindow();\n  ```\n- **Web** (Playwright against the running app):\n  ```ts\n  test('golden journey', async ({ page }) => {\n    await page.goto(process.env.BASE_URL ?? 'http:\u002F\u002Flocalhost:3000');\n    \u002F\u002F ...drive the ONE journey, then assert the produced artifact:\n    const download = await Promise.all([\n      page.waitForEvent('download'),\n      page.getByRole('button', { name: 'Export' }).click(),\n    ]).then(([d]) => d);\n    const file = await download.path();      \u002F\u002F the REAL produced file → run the assertion ladder\n  });\n  ```\n- **CLI** (spawn the real command, assert its output file):\n  ```ts\n  import { execFileSync } from 'node:child_process';\n  execFileSync('mytool', ['build', '--in', fixture, '--out', outPath], { stdio: 'inherit' });\n  \u002F\u002F then: exists → non-empty → parses\u002Fffprobe → semantically correct\n  ```\n  Python equivalent: `subprocess.run([...], check=True)` then assert on `out_path`.\n\n## Make it the gate + forbid the reward-hack surface\n\n- **Keep it held out of normal runs and make it the merge gate.** In the task that hands work to\n  an implementer, use this line verbatim:\n  > *Done = the golden-journey exits 0 on a clean checkout. Coverage \u002F unit-green are necessary\n  > but NOT sufficient and may NOT be cited as done.*\n- **Forbid the gaming surface and verify against the diff.** No net-new `pragma:no-cover` \u002F\n  `xfail` \u002F `skip` \u002F coverage-omit \u002F `addopts` \u002F `-m` marker \u002F `collectCoverageFrom` \u002F CI-trigger\n  edits. Require the final report to include a `git diff` of every test\u002FCI\u002Fcoverage-config change —\n  that diff is where the gaming hides.\n- **Red-repro before every fix; attach the artifact with every \"fixed.\"** Script the failure as a\n  red golden-journey first; attach the produced mp4\u002Fscreenshot\u002Ffile, never an isolated unit test,\n  as proof.\n\n## Anti-patterns\n\n- Asserting an element\u002Ftoast is visible instead of a real artifact on disk.\n- Mocking the backend\u002Fsidecar\u002Fffmpeg \"to make the E2E deterministic\" — that re-hides the seam bugs.\n- Letting the implementing agent read or edit the spec (it will fit the exam to its code).\n- Citing coverage % or \"all units pass\" as the done-signal.\n- Claiming done on a single-frame \u002F single-poll check instead of polling to real completion with a\n  timeout snapshot.\n- A green result while the artifact is 0 bytes or won't decode (ladder stopped at rung 1).\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fseed-golden-journey","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill seed-golden-journey",{"tool":56,"command":57},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill seed-golden-journey",{"tool":59,"command":60},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill seed-golden-journey","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fseed-golden-journey\u002FSKILL.md",true,[64,70,76],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"README.md","REFERENCE","参考文档",2893,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fseed-golden-journey\u002FREADME.md",{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"templates\u002Fgolden-journey.cli.template.spec.ts","SCRIPT","脚本",3237,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fseed-golden-journey\u002Ftemplates\u002Fgolden-journey.cli.template.spec.ts",{"path":77,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":78,"sourceHtmlUrl":79},"templates\u002Fgolden-journey.template.spec.ts",10047,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fseed-golden-journey\u002Ftemplates\u002Fgolden-journey.template.spec.ts",[81,101,132,158,172,188],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":39},"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",[],[88,89,90,91,92,93,94,95,96,28,97,98,99,100,33],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":112,"publishedAt":39},"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",[107],{"categoryNo":108,"categoryName":109,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[113,114,115,116,117,118,119,120,121,122,123,124,125,126,28,127,128,129,130,131],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":144,"publishedAt":39},"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",[138,141],{"categoryNo":139,"categoryName":140,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":142,"categoryName":143,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000008","测试与质量",[145,146,147,148,36,149,150,151,152,153,114,154,155,156,157],"review","visual","visual review","pages","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":39},"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",[],[160,165,166,167,168,169,170,171],"setup","report","project","installation","project setup","issues","state",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":179,"publishedAt":39},"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",[178],{"categoryNo":108,"categoryName":109,"taxonomyType":110,"taxonomyTypeDesc":111},[174,180,93,181,182,183,28,184,185,186,187],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":189,"name":165,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":193,"publishedAt":39},"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",[],[165,167,129,194,169,195],"files","interactive"]