[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DEVBHRDTPRS7TSKF78KZJG":3,"skill-same:01M6DEVBHRDTPRS7TSKF78KZJG":88},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":14,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":55,"install":56,"resources":69},"01M6DEVBHRDTPRS7TSKF78KZJG","smallest-check-ladder",null,"Use when you need to run \"the smallest test that could still catch this change\" instead of blindly running the whole suite (or nothing). Provides an invocable L0 to L3 ladder - L0 lint the edited file, L1 impacted tests via deterministic selectors, L2 full suite via longrun, L3 e2e - so a \"tests pass\" claim is backed by a proportionate check. Never ML \"predictive test selection\".","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\u002Fskills\u002Fsmallest-check-ladder\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"smallest check ladder","check","never","gem","tests","gates","full","claim","deterministic","selection","hunt","test","use","e2e","file","verification","lint","run","ml","change","2026-11-10 10:12:30",false,"---\nname: smallest-check-ladder\ndescription: Use when you need to run \"the smallest test that could still catch this change\" instead of blindly running the whole suite (or nothing). Provides an invocable L0 to L3 ladder - L0 lint the edited file, L1 impacted tests via deterministic selectors, L2 full suite via longrun, L3 e2e - so a \"tests pass\" claim is backed by a proportionate check. Never ML \"predictive test selection\".\norigin: gem-hunt-2026-07-12 (A-Tier2, verification-gates #4\u002F#5)\n---\n\n# Smallest-Check Ladder (L0 -> L3)\n\nPick the **smallest rung that could still falsify the change**, run it for real, and\nescalate only when the rung passes and you need broader confidence. The point is to make\n\"I ran the relevant tests\" a concrete, reproducible command — not a vibe — while staying\nproportionate to the size of the diff.\n\n**Deterministic only.** Every selector on this ladder chooses tests from a *dependency graph*\nor a *coverage map* (a fact about the code), never from a learned model that *predicts* which\ntests are \"probably\" relevant. ML predictive test selection is explicitly out of scope: it can\nsilently drop a test that actually covers the change, which defeats the purpose of the rung.\n\n## The ladder\n\n| Rung | Scope | Cost | Run when |\n|------|-------|------|----------|\n| **L0** | Lint \u002F typecheck the **edited file(s)** only | ~1s | Every save. Always cheap enough to skip nothing. |\n| **L1** | **Impacted** tests — the tests that exercise the changed files | seconds–low tens of s | Default for any code change before claiming \"tests pass\". |\n| **L2** | **Full** suite (+ coverage) | minutes | L1 passed and the change is cross-cutting, or before a PR \u002F task-completion gate. |\n| **L3** | **E2E** against the built\u002Fpackaged artifact | minutes+ | Packaging, wiring, or user-journey surface touched (see packaged-artifact smoke gate). |\n\nClimb from the lowest rung that can catch *this* class of defect. A one-line pure-function\nfix rarely needs L3; a change to the Electron main process or the ffmpeg argv builder does.\n\n## Concrete commands\n\nSubstitute the actual changed paths for `\u003Cfiles>`.\n\n### L0 — edited-file lint \u002F typecheck\n```bash\n# Python (Reframe: ruff + basedpyright)\nruff check \u003Cfiles>\nbasedpyright \u003Cfiles>\n\n# TypeScript (Reframe app\u002F)\nnpx tsc --noEmit               # project-wide but fast; or eslint just the files:\nnpx eslint \u003Cfiles>\n```\n\n### L1 — impacted tests (deterministic selectors)\n```bash\n# Python — pytest-testmon: selects tests whose recorded coverage touches the changed code.\n#   Deterministic: it replays a stored per-test coverage map, it does not predict.\n#   Prerequisite (one-time): pip install pytest-testmon   # the --testmon flag is absent until installed\npytest --testmon                       # uses the .testmondata db built on the prior run\npytest --testmon-noselect \u003Cfiles>      # first run \u002F to (re)seed the db for these files\n\n# JavaScript\u002FTypeScript — dependency-graph selection (deterministic: static import graph)\nnpx jest --findRelatedTests \u003Cfiles>    # jest projects\nnpx vitest related \u003Cfiles> --run       # vitest projects (Reframe app\u002F uses vitest)\n```\n`--testmon` needs its `.testmondata` db seeded once (run the suite under testmon, or use\n`--testmon-noselect`); if the db is stale or missing it falls back to running everything, so\ntreat a suspiciously-large L1 selection as \"seed first, then reselect\".\n\n### L2 — full suite (always via longrun; it exceeds 60s)\n```bash\n# Wrap in longrun per the >60s rule; never a blocking foreground call.\n~\u002Fsource\u002Fagent-skills-toolchain\u002Fscripts\u002Flongrun.ps1 -Id l2-full -HangTimeoutSec 300 \\\n  -Cmd pytest --cov --cov-report=term-missing\n# TS:\n~\u002Fsource\u002Fagent-skills-toolchain\u002Fscripts\u002Flongrun.ps1 -Id l2-vitest -HangTimeoutSec 300 \\\n  -Cmd npx vitest run --coverage\n```\nCoverage thresholds are **not** decided here — `.coverage-thresholds.json` remains the single\nsource of truth and its enforcement command is the blocking gate. L2 just *runs* the suite.\n\n### L3 — e2e against the built artifact\n```bash\n# Run the project's e2e journeys against the packaged deliverable, not the source tree.\nnpx vitest run --config vitest.e2e.config.ts     # Reframe DOM e2e\n# packaged smoke: _electron.launch({executablePath}) \u002F pip install dist\u002F*.whl in a fresh venv\n```\n\n### Diff-scoped coverage (optional, orthogonal)\n```bash\n# \"Did the lines I changed get exercised?\" — deterministic, reads coverage.xml vs the diff.\ndiff-cover coverage.xml --compare-branch=main\n```\n\n## How to use it in a turn\n\n1. Identify the changed files.\n2. Run **L0** on them. Fix lint\u002Ftype errors first — they invalidate any test result below.\n3. Run **L1** (`--testmon` \u002F `related`). Capture the actual pass\u002Ffail output as evidence.\n4. If the change is cross-cutting or you are about to claim task-complete \u002F open a PR, climb to\n   **L2** (via longrun) and check `.coverage-thresholds.json`.\n5. If packaging \u002F wiring \u002F a user journey changed, climb to **L3**.\n6. Report the highest rung you ran and its real output — `SUCCESS:\u003Cid> L1 12 passed` \u002F\n   `FAILED:\u003Cid> L1 2 failed …`. Never claim \"tests pass\" from L0 alone.\n\n## Honesty rails\n\n- **A green rung is not a green suite.** L1 asserts only \"the impacted tests pass\". If you claim\n  *the change is verified*, name the rung you actually reached. A cross-cutting change verified\n  only at L1 is under-verified — say so.\n- **Selector fallback is a silent widener, not a narrower.** testmon with a missing db and\n  `related` with an empty match both tend to run *more* (or, for `related`, *nothing*) — inspect\n  the selected count; an empty L1 selection means \"seed the db \u002F check the path globs\", never\n  \"there's nothing to run, ship it\".\n- **No ML selection.** If a tool proposes \"predicted relevant tests\" from a model, do not use it\n  on this ladder — it can drop a covering test and manufacture a false green.\n\n## Scope \u002F non-goals\n\n- Does **not** author tests — that is `tdd-workflow` \u002F `test-driven-development` (write the test\n  first, watch it fail). This ladder only *selects and runs existing* tests.\n- Does **not** own coverage thresholds — `.coverage-thresholds.json` does.\n- **Pairs with `two-tier-verify`**, the same split stated as a decision rule: its INNER loop\n  (after every edit) is L0+L1 here, its OUTER loop (once, at the commit boundary) is L2+L3. Go\n  there for when to run which tier and its jest\u002Fvitest\u002Fpytest recipes; stay here for the rung\n  commands and the selector caveats.\n- **Deferred (handBuild):** wiring the concrete L1 command into `ClaimWarningModule` \u002F\n  `claim_warning` so a \"tests pass\" claim is auto-annotated with (or checked against) the\n  smallest-check command that was actually run. That integration ships separately and, per\n  council C5, in **shadow mode** (observe\u002Fannotate only — never blocks, never nags). This skill\n  is the deterministic-command reference it will point at.\n\n---\n*Evidence: gem-hunt-2026-07-12 MASTER decision queue, A-Tier2 \"Smallest-check ladder L0->L3\n(testmon \u002F jest-related \u002F diff-cover)\", verification-gates streams #4\u002F#5. Additive doc; ships no\ngate. Deterministic dependency\u002Fcoverage-map selectors only.*\n","# Smallest-Check Ladder (L0 -> L3)\n\nPick the **smallest rung that could still falsify the change**, run it for real, and\nescalate only when the rung passes and you need broader confidence. The point is to make\n\"I ran the relevant tests\" a concrete, reproducible command — not a vibe — while staying\nproportionate to the size of the diff.\n\n**Deterministic only.** Every selector on this ladder chooses tests from a *dependency graph*\nor a *coverage map* (a fact about the code), never from a learned model that *predicts* which\ntests are \"probably\" relevant. ML predictive test selection is explicitly out of scope: it can\nsilently drop a test that actually covers the change, which defeats the purpose of the rung.\n\n## The ladder\n\n| Rung | Scope | Cost | Run when |\n|------|-------|------|----------|\n| **L0** | Lint \u002F typecheck the **edited file(s)** only | ~1s | Every save. Always cheap enough to skip nothing. |\n| **L1** | **Impacted** tests — the tests that exercise the changed files | seconds–low tens of s | Default for any code change before claiming \"tests pass\". |\n| **L2** | **Full** suite (+ coverage) | minutes | L1 passed and the change is cross-cutting, or before a PR \u002F task-completion gate. |\n| **L3** | **E2E** against the built\u002Fpackaged artifact | minutes+ | Packaging, wiring, or user-journey surface touched (see packaged-artifact smoke gate). |\n\nClimb from the lowest rung that can catch *this* class of defect. A one-line pure-function\nfix rarely needs L3; a change to the Electron main process or the ffmpeg argv builder does.\n\n## Concrete commands\n\nSubstitute the actual changed paths for `\u003Cfiles>`.\n\n### L0 — edited-file lint \u002F typecheck\n```bash\n# Python (Reframe: ruff + basedpyright)\nruff check \u003Cfiles>\nbasedpyright \u003Cfiles>\n\n# TypeScript (Reframe app\u002F)\nnpx tsc --noEmit               # project-wide but fast; or eslint just the files:\nnpx eslint \u003Cfiles>\n```\n\n### L1 — impacted tests (deterministic selectors)\n```bash\n# Python — pytest-testmon: selects tests whose recorded coverage touches the changed code.\n#   Deterministic: it replays a stored per-test coverage map, it does not predict.\n#   Prerequisite (one-time): pip install pytest-testmon   # the --testmon flag is absent until installed\npytest --testmon                       # uses the .testmondata db built on the prior run\npytest --testmon-noselect \u003Cfiles>      # first run \u002F to (re)seed the db for these files\n\n# JavaScript\u002FTypeScript — dependency-graph selection (deterministic: static import graph)\nnpx jest --findRelatedTests \u003Cfiles>    # jest projects\nnpx vitest related \u003Cfiles> --run       # vitest projects (Reframe app\u002F uses vitest)\n```\n`--testmon` needs its `.testmondata` db seeded once (run the suite under testmon, or use\n`--testmon-noselect`); if the db is stale or missing it falls back to running everything, so\ntreat a suspiciously-large L1 selection as \"seed first, then reselect\".\n\n### L2 — full suite (always via longrun; it exceeds 60s)\n```bash\n# Wrap in longrun per the >60s rule; never a blocking foreground call.\n~\u002Fsource\u002Fagent-skills-toolchain\u002Fscripts\u002Flongrun.ps1 -Id l2-full -HangTimeoutSec 300 \\\n  -Cmd pytest --cov --cov-report=term-missing\n# TS:\n~\u002Fsource\u002Fagent-skills-toolchain\u002Fscripts\u002Flongrun.ps1 -Id l2-vitest -HangTimeoutSec 300 \\\n  -Cmd npx vitest run --coverage\n```\nCoverage thresholds are **not** decided here — `.coverage-thresholds.json` remains the single\nsource of truth and its enforcement command is the blocking gate. L2 just *runs* the suite.\n\n### L3 — e2e against the built artifact\n```bash\n# Run the project's e2e journeys against the packaged deliverable, not the source tree.\nnpx vitest run --config vitest.e2e.config.ts     # Reframe DOM e2e\n# packaged smoke: _electron.launch({executablePath}) \u002F pip install dist\u002F*.whl in a fresh venv\n```\n\n### Diff-scoped coverage (optional, orthogonal)\n```bash\n# \"Did the lines I changed get exercised?\" — deterministic, reads coverage.xml vs the diff.\ndiff-cover coverage.xml --compare-branch=main\n```\n\n## How to use it in a turn\n\n1. Identify the changed files.\n2. Run **L0** on them. Fix lint\u002Ftype errors first — they invalidate any test result below.\n3. Run **L1** (`--testmon` \u002F `related`). Capture the actual pass\u002Ffail output as evidence.\n4. If the change is cross-cutting or you are about to claim task-complete \u002F open a PR, climb to\n   **L2** (via longrun) and check `.coverage-thresholds.json`.\n5. If packaging \u002F wiring \u002F a user journey changed, climb to **L3**.\n6. Report the highest rung you ran and its real output — `SUCCESS:\u003Cid> L1 12 passed` \u002F\n   `FAILED:\u003Cid> L1 2 failed …`. Never claim \"tests pass\" from L0 alone.\n\n## Honesty rails\n\n- **A green rung is not a green suite.** L1 asserts only \"the impacted tests pass\". If you claim\n  *the change is verified*, name the rung you actually reached. A cross-cutting change verified\n  only at L1 is under-verified — say so.\n- **Selector fallback is a silent widener, not a narrower.** testmon with a missing db and\n  `related` with an empty match both tend to run *more* (or, for `related`, *nothing*) — inspect\n  the selected count; an empty L1 selection means \"seed the db \u002F check the path globs\", never\n  \"there's nothing to run, ship it\".\n- **No ML selection.** If a tool proposes \"predicted relevant tests\" from a model, do not use it\n  on this ladder — it can drop a covering test and manufacture a false green.\n\n## Scope \u002F non-goals\n\n- Does **not** author tests — that is `tdd-workflow` \u002F `test-driven-development` (write the test\n  first, watch it fail). This ladder only *selects and runs existing* tests.\n- Does **not** own coverage thresholds — `.coverage-thresholds.json` does.\n- **Pairs with `two-tier-verify`**, the same split stated as a decision rule: its INNER loop\n  (after every edit) is L0+L1 here, its OUTER loop (once, at the commit boundary) is L2+L3. Go\n  there for when to run which tier and its jest\u002Fvitest\u002Fpytest recipes; stay here for the rung\n  commands and the selector caveats.\n- **Deferred (handBuild):** wiring the concrete L1 command into `ClaimWarningModule` \u002F\n  `claim_warning` so a \"tests pass\" claim is auto-annotated with (or checked against) the\n  smallest-check command that was actually run. That integration ships separately and, per\n  council C5, in **shadow mode** (observe\u002Fannotate only — never blocks, never nags). This skill\n  is the deterministic-command reference it will point at.\n\n---\n*Evidence: gem-hunt-2026-07-12 MASTER decision queue, A-Tier2 \"Smallest-check ladder L0->L3\n(testmon \u002F jest-related \u002F diff-cover)\", verification-gates streams #4\u002F#5. Additive doc; ships no\ngate. Deterministic dependency\u002Fcoverage-map selectors only.*\n",{"name":5,"origin":49,"description":7},"gem-hunt-2026-07-12 (A-Tier2, verification-gates","main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","skills\u002Fsmallest-check-ladder","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill smallest-check-ladder",{"tool":62,"command":63},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill smallest-check-ladder",{"tool":65,"command":66},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill smallest-check-ladder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fsmallest-check-ladder\u002FSKILL.md",true,[70,76,80,84],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"checklist.md","REFERENCE","参考文档",14349,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-create-story\u002Fchecklist.md",{"path":77,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":78,"sourceHtmlUrl":79},"discover-inputs.md",3911,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-create-story\u002Fdiscover-inputs.md",{"path":81,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":82,"sourceHtmlUrl":83},"template.md",948,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-create-story\u002Ftemplate.md",{"path":85,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":86,"sourceHtmlUrl":87},"workflow.md",19932,"https:\u002F\u002Fgithub.com\u002Fdinesh-style\u002Fportfolio\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-create-story\u002Fworkflow.md",[89,109,138,162,176,192],{"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":95,"publishedAt":44},"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",[],[96,97,98,99,100,101,102,103,104,36,105,106,107,108,38],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":118,"publishedAt":44},"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",[115],{"categoryNo":116,"categoryName":117,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[119,120,121,122,123,124,125,126,127,128,129,130,131,132,36,133,134,135,136,137],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":148,"publishedAt":44},"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",[144,147],{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[149,150,151,152,153,154,155,156,25,157,120,158,159,160,161],"review","visual","visual review","pages","web","false","iteration","take","slides","ui","screenshot","playwright","screenshots",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":168,"publishedAt":44},"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",[],[164,169,170,171,172,173,174,175],"setup","report","project","installation","project setup","issues","state",{"skillNo":177,"name":178,"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":183,"publishedAt":44},"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",[182],{"categoryNo":116,"categoryName":117,"taxonomyType":21,"taxonomyTypeDesc":22},[178,184,101,185,186,187,36,188,189,190,191],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":193,"name":169,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":197,"publishedAt":44},"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",[],[169,171,135,198,173,199],"files","interactive"]