[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DB4AKPB9NAT1GWRX06Q88Q":3,"skill-same:01M6DB4AKPB9NAT1GWRX06Q88Q":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":52,"commitSha":53,"skillDirectory":54,"forksCount":14,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6DB4AKPB9NAT1GWRX06Q88Q","ci-silent-pass-lint",null,"Use before any PR creation or \"gates green \u002F ready to merge\" claim to detect CI\u002Fgate workflows that report GREEN while masking real findings - the recurring \"qlty green yet 61 issues + 809 on Codacy\" \u002F stale-SHA-gate pattern. Runs a deterministic linter over .github\u002Fworkflows\u002F*.yml for 11 silent-pass shapes plus an MCP cross-check of actual finding-counts at HEAD vs the reported status.","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\u002Fci-silent-pass-lint\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","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],"ci silent pass lint","lint","ci","recurring","head","creation","gates","green","claim","deterministic","ready","use","MCP","linter","check","issues","pr","merge","workflows","github","2026-11-10 10:12:30",false,"---\nname: ci-silent-pass-lint\ndescription: Use before any PR creation or \"gates green \u002F ready to merge\" claim to detect CI\u002Fgate workflows that report GREEN while masking real findings - the recurring \"qlty green yet 61 issues + 809 on Codacy\" \u002F stale-SHA-gate pattern. Runs a deterministic linter over .github\u002Fworkflows\u002F*.yml for 11 silent-pass shapes plus an MCP cross-check of actual finding-counts at HEAD vs the reported status.\n---\n\n# CI Silent-Pass Lint\n\n## When to Trigger\n\nInvoke this skill **before any of the following**:\n\n- Creating a pull request (`gh pr create`, `\u002Fpr-shepherd`, `finishing-a-development-branch`)\n- Claiming \"all gates are green\" or \"ready to merge\"\n- Trusting a CI green badge on a new or recently modified workflow\n- After adding\u002Fmodifying any `.github\u002Fworkflows\u002F*.yml` file\n- When `qlty`, Codacy, or DeepSource findings seem inconsistently low (\"qlty green but Codacy shows 61 issues\")\n\nIt also runs implicitly as part of the metaswarm pre-PR gate chain (after `verification-before-completion`, before `pr-shepherd`).\n\n---\n\n## Architecture — Two Parts\n\n### Part A: Deterministic Workflow Linter (`lint_workflows.py`)\n\nPure-stdlib Python. Run with:\n\n```bash\npython skills\u002Fci-silent-pass-lint\u002Flint_workflows.py [repo-path]\n# default repo-path: current directory\n```\n\n- Scans `.github\u002Fworkflows\u002F*.{yml,yaml}`\n- Reports each shape hit with `file:line`, snippet, severity, and message\n- Exits **nonzero** if any `HIGH`-severity finding is detected → directly gate-able\n- Optionally uses `pyyaml` for structural shapes (S10, S11) if available; degrades gracefully without it\n\n**Gate rule:** If Part A exits nonzero, the pre-PR gate fails. Fix the workflow issues before creating the PR.\n\n### Part B: MCP Cross-Check (runbook in `gate_findings_at_head.md`)\n\nExecuted by the agent using the connected MCP tools. The agent:\n\n1. Resolves `HEAD` SHA via `git rev-parse HEAD`\n2. Queries each connected provider for finding-counts **at that exact SHA**\n3. Compares against the gate's reported \"green\"\n4. Emits a per-provider verdict table: `CLEAN PASS` vs `SILENT PASS` vs `UNKNOWN`\n\n**Gate rule:** Any `SILENT PASS` row (provider reports green while finding-count > 0 OR SHA is stale) means the \"gates are green\" claim is refuted. Surface the table before creating the PR.\n\nThe full SHA-finding primitive interface — including exact MCP tool names, parameters, and the `claim_guard_check()` contract — is in [`gate_findings_at_head.md`](gate_findings_at_head.md).\n\n---\n\n## The 11 Silent-Pass Shapes\n\n| # | Shape | Severity | Detection |\n|---|-------|----------|-----------|\n| S01 | `continue-on-error: true` on a gate\u002Fanalysis step | HIGH | Regex, line-local |\n| S02 | `\\|\\| true` \u002F `\\|\\| exit 0` swallowing command exit | HIGH | Regex, line-local |\n| S03 | Issue\u002Fquality policy `mode: audit` (reports, never fails) | HIGH | Regex, line-local |\n| S04 | Token-less \u002F empty-token uploads; `fail_ci_if_error: false` | HIGH | Regex, line-local |\n| S05 | `set +e` without recheck; `; true`; pipe masks failure | HIGH | Regex, line-local |\n| S06 | Gate step with pinned `--ref`\u002F`--sha` SHA arg instead of HEAD | MEDIUM | Regex, line-local† |\n| S07 | `if: always()` on a \"success\u002Fpass\u002Fgreen\u002Fsummary\" step | LOW | Regex, windowed‡ |\n| S08 | Soft thresholds: `--exit-zero`, `--no-error`, `--fail-under 0` | HIGH | Regex, line-local |\n| S09 | Required-check name that doesn't match any job name | INFO | Structural, job inventory§ |\n| S10 | Artifact\u002Fresult upload without a fail-on-findings gate after it | MEDIUM | Structural (pyyaml) |\n| S11 | `fail-fast: false` + matrix + no aggregate gate job | MEDIUM | Structural (pyyaml) |\n\n**Confidence notes:**\n\n- **†S06**: YAML alone cannot prove a SHA is stale (it may be a legitimately pinned historical ref in a backfill job). The linter flags `--ref`\u002F`--sha`\u002F`--commit` with hardcoded SHA args as MEDIUM; Part B's MCP cross-check is the authoritative stale-SHA detector. `uses: action@\u003Csha>` (security pinning) is **not** flagged — that is a recommended practice.\n- **‡S07**: `if: always()` is legitimate on artifact-upload and log-collection steps. The linter restricts flagging to steps whose `name:` contains \"success\", \"green\", \"pass\", or \"summary\" within 5 lines of the `if: always()` — narrow scope to reduce false positives. Severity is LOW\u002Fadvisory.\n- **§S09**: Branch-protection required-context names live in GitHub rulesets, not workflow files. The linter inventories job names as INFO; compare them against `gh api repos\u002F{owner}\u002F{repo}\u002Frulesets` to find mismatches.\n\n**Exit code:**\n- `0` — no HIGH findings (MEDIUM\u002FLOW\u002FINFO may be present; review them)\n- `1` — one or more HIGH findings → **gate fails**\n- `2` — usage error (bad path etc.)\n\n---\n\n## Composition with claim-guard #2\n\n`claim-guard #2` (the \"always-verify claims before trusting them\" guard) consumes the **same SHA-finding primitive** defined in `gate_findings_at_head.md`:\n\n```\nclaim_guard_check(repo_path, owner, repo, head_sha, project_keys)\n  -> SilentPassVerdict(clean: bool, silent_passes: list, unknowns: list)\n```\n\n`ci-silent-pass-lint` is the **proactive, pre-PR** trigger.\n`claim-guard #2` is the **reactive, claim-time** trigger (fires when any agent asserts \"green\").\nBoth consume the same primitive; neither re-implements it.\n\n---\n\n## Connected MCP Providers\n\n| Provider | MCP Tool (Part B) | SHA-pinned? |\n|----------|-------------------|-------------|\n| Codacy | `mcp__codacy__codacy_get_repository_with_analysis` | Partially (lags; check `lastAnalyzedCommit`) |\n| Codecov | `mcp__codecov__get_commit_coverage` | Yes — pass `commit_sha` directly |\n| DeepSource | `mcp__deepsource__run` with `isCommitOid: true` | Yes — pass `head_sha` as `runIdentifier` |\n| qlty | `mcp__qlty__qlty_check` (local run) | N\u002FA — always at working-tree HEAD |\n| SonarCloud | `curl sonarcloud.io\u002Fapi\u002Fqualitygates\u002Fproject_status` (no MCP) | Via branch + timestamp |\n\nSee `gate_findings_at_head.md` for exact parameters and extraction logic per provider.\n\n---\n\n## Common Failure Modes Detected\n\n- **\"qlty green yet 61 issues + 809 on Codacy\"** — S03 (audit mode) or S08 (--exit-zero) on the qlty step; Part B confirms actual Codacy count at HEAD.\n- **\"Gate green on stale SHA\"** — S06 in Part A; Part B's `is_stale` field confirms.\n- **\"Upload step succeeds, findings silently ignored\"** — S04 (no token) or S10 (no gate after upload).\n- **\"One matrix leg fails, overall workflow passes\"** — S11 (fail-fast:false, no aggregate).\n- **\"CI green, branch protection satisfied, but required check was never produced\"** — S09 (job name mismatch → INFO, confirmed via rulesets API).\n- **\"The red gate under-reports: one fixed defect, still red\"** — a test whose first `assert` fails hides every later `assert` in the same function, so the CI log shows ONE failure where there are two. Measured 2026-08-12 on `gate-tests-coverage command-center` (run 31617966828): `assert violations == []` failed on a stale register digest and masked `assert stats[\"open\"] == 59`, itself stale since commit 3a19b9a3. Not a silent PASS, so Part A cannot see it — the tell is a gate that stays red after a fix you verified. Read the NEW failure rather than assuming the fix did not land, and treat a defect count read off a CI log as a floor, never a census.\n","# CI Silent-Pass Lint\n\n## When to Trigger\n\nInvoke this skill **before any of the following**:\n\n- Creating a pull request (`gh pr create`, `\u002Fpr-shepherd`, `finishing-a-development-branch`)\n- Claiming \"all gates are green\" or \"ready to merge\"\n- Trusting a CI green badge on a new or recently modified workflow\n- After adding\u002Fmodifying any `.github\u002Fworkflows\u002F*.yml` file\n- When `qlty`, Codacy, or DeepSource findings seem inconsistently low (\"qlty green but Codacy shows 61 issues\")\n\nIt also runs implicitly as part of the metaswarm pre-PR gate chain (after `verification-before-completion`, before `pr-shepherd`).\n\n---\n\n## Architecture — Two Parts\n\n### Part A: Deterministic Workflow Linter (`lint_workflows.py`)\n\nPure-stdlib Python. Run with:\n\n```bash\npython skills\u002Fci-silent-pass-lint\u002Flint_workflows.py [repo-path]\n# default repo-path: current directory\n```\n\n- Scans `.github\u002Fworkflows\u002F*.{yml,yaml}`\n- Reports each shape hit with `file:line`, snippet, severity, and message\n- Exits **nonzero** if any `HIGH`-severity finding is detected → directly gate-able\n- Optionally uses `pyyaml` for structural shapes (S10, S11) if available; degrades gracefully without it\n\n**Gate rule:** If Part A exits nonzero, the pre-PR gate fails. Fix the workflow issues before creating the PR.\n\n### Part B: MCP Cross-Check (runbook in `gate_findings_at_head.md`)\n\nExecuted by the agent using the connected MCP tools. The agent:\n\n1. Resolves `HEAD` SHA via `git rev-parse HEAD`\n2. Queries each connected provider for finding-counts **at that exact SHA**\n3. Compares against the gate's reported \"green\"\n4. Emits a per-provider verdict table: `CLEAN PASS` vs `SILENT PASS` vs `UNKNOWN`\n\n**Gate rule:** Any `SILENT PASS` row (provider reports green while finding-count > 0 OR SHA is stale) means the \"gates are green\" claim is refuted. Surface the table before creating the PR.\n\nThe full SHA-finding primitive interface — including exact MCP tool names, parameters, and the `claim_guard_check()` contract — is in [`gate_findings_at_head.md`](gate_findings_at_head.md).\n\n---\n\n## The 11 Silent-Pass Shapes\n\n| # | Shape | Severity | Detection |\n|---|-------|----------|-----------|\n| S01 | `continue-on-error: true` on a gate\u002Fanalysis step | HIGH | Regex, line-local |\n| S02 | `\\|\\| true` \u002F `\\|\\| exit 0` swallowing command exit | HIGH | Regex, line-local |\n| S03 | Issue\u002Fquality policy `mode: audit` (reports, never fails) | HIGH | Regex, line-local |\n| S04 | Token-less \u002F empty-token uploads; `fail_ci_if_error: false` | HIGH | Regex, line-local |\n| S05 | `set +e` without recheck; `; true`; pipe masks failure | HIGH | Regex, line-local |\n| S06 | Gate step with pinned `--ref`\u002F`--sha` SHA arg instead of HEAD | MEDIUM | Regex, line-local† |\n| S07 | `if: always()` on a \"success\u002Fpass\u002Fgreen\u002Fsummary\" step | LOW | Regex, windowed‡ |\n| S08 | Soft thresholds: `--exit-zero`, `--no-error`, `--fail-under 0` | HIGH | Regex, line-local |\n| S09 | Required-check name that doesn't match any job name | INFO | Structural, job inventory§ |\n| S10 | Artifact\u002Fresult upload without a fail-on-findings gate after it | MEDIUM | Structural (pyyaml) |\n| S11 | `fail-fast: false` + matrix + no aggregate gate job | MEDIUM | Structural (pyyaml) |\n\n**Confidence notes:**\n\n- **†S06**: YAML alone cannot prove a SHA is stale (it may be a legitimately pinned historical ref in a backfill job). The linter flags `--ref`\u002F`--sha`\u002F`--commit` with hardcoded SHA args as MEDIUM; Part B's MCP cross-check is the authoritative stale-SHA detector. `uses: action@\u003Csha>` (security pinning) is **not** flagged — that is a recommended practice.\n- **‡S07**: `if: always()` is legitimate on artifact-upload and log-collection steps. The linter restricts flagging to steps whose `name:` contains \"success\", \"green\", \"pass\", or \"summary\" within 5 lines of the `if: always()` — narrow scope to reduce false positives. Severity is LOW\u002Fadvisory.\n- **§S09**: Branch-protection required-context names live in GitHub rulesets, not workflow files. The linter inventories job names as INFO; compare them against `gh api repos\u002F{owner}\u002F{repo}\u002Frulesets` to find mismatches.\n\n**Exit code:**\n- `0` — no HIGH findings (MEDIUM\u002FLOW\u002FINFO may be present; review them)\n- `1` — one or more HIGH findings → **gate fails**\n- `2` — usage error (bad path etc.)\n\n---\n\n## Composition with claim-guard #2\n\n`claim-guard #2` (the \"always-verify claims before trusting them\" guard) consumes the **same SHA-finding primitive** defined in `gate_findings_at_head.md`:\n\n```\nclaim_guard_check(repo_path, owner, repo, head_sha, project_keys)\n  -> SilentPassVerdict(clean: bool, silent_passes: list, unknowns: list)\n```\n\n`ci-silent-pass-lint` is the **proactive, pre-PR** trigger.\n`claim-guard #2` is the **reactive, claim-time** trigger (fires when any agent asserts \"green\").\nBoth consume the same primitive; neither re-implements it.\n\n---\n\n## Connected MCP Providers\n\n| Provider | MCP Tool (Part B) | SHA-pinned? |\n|----------|-------------------|-------------|\n| Codacy | `mcp__codacy__codacy_get_repository_with_analysis` | Partially (lags; check `lastAnalyzedCommit`) |\n| Codecov | `mcp__codecov__get_commit_coverage` | Yes — pass `commit_sha` directly |\n| DeepSource | `mcp__deepsource__run` with `isCommitOid: true` | Yes — pass `head_sha` as `runIdentifier` |\n| qlty | `mcp__qlty__qlty_check` (local run) | N\u002FA — always at working-tree HEAD |\n| SonarCloud | `curl sonarcloud.io\u002Fapi\u002Fqualitygates\u002Fproject_status` (no MCP) | Via branch + timestamp |\n\nSee `gate_findings_at_head.md` for exact parameters and extraction logic per provider.\n\n---\n\n## Common Failure Modes Detected\n\n- **\"qlty green yet 61 issues + 809 on Codacy\"** — S03 (audit mode) or S08 (--exit-zero) on the qlty step; Part B confirms actual Codacy count at HEAD.\n- **\"Gate green on stale SHA\"** — S06 in Part A; Part B's `is_stale` field confirms.\n- **\"Upload step succeeds, findings silently ignored\"** — S04 (no token) or S10 (no gate after upload).\n- **\"One matrix leg fails, overall workflow passes\"** — S11 (fail-fast:false, no aggregate).\n- **\"CI green, branch protection satisfied, but required check was never produced\"** — S09 (job name mismatch → INFO, confirmed via rulesets API).\n- **\"The red gate under-reports: one fixed defect, still red\"** — a test whose first `assert` fails hides every later `assert` in the same function, so the CI log shows ONE failure where there are two. Measured 2026-08-12 on `gate-tests-coverage command-center` (run 31617966828): `assert violations == []` failed on a stale register digest and masked `assert stats[\"open\"] == 59`, itself stale since commit 3a19b9a3. Not a silent PASS, so Part A cannot see it — the tell is a gate that stays red after a fix you verified. Read the NEW failure rather than assuming the fix did not land, and treat a defect count read off a CI log as a floor, never a census.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fci-silent-pass-lint","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill ci-silent-pass-lint",{"tool":64,"command":65},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill ci-silent-pass-lint",{"tool":67,"command":68},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill ci-silent-pass-lint","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fci-silent-pass-lint\u002FSKILL.md",true,[72,78],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"gate_findings_at_head.md","REFERENCE","参考文档",8566,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fci-silent-pass-lint\u002Fgate_findings_at_head.md",{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"lint_workflows.py","SCRIPT","脚本",18698,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fci-silent-pass-lint\u002Flint_workflows.py",[85,106,132,158,171,186],{"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":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":47},"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",[],[92,93,94,95,96,97,98,99,100,38,101,102,103,104,105],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":113,"publishedAt":47},"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",[112],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[114,115,116,117,118,119,120,121,122,123,124,125,126,127,38,128,129,130,131,39],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do",{"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":47},"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":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":142,"categoryName":143,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[145,146,147,148,149,150,151,152,41,153,115,154,155,156,157],"review","visual","visual review","pages","web","false","iteration","take","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":47},"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",[],[160,165,166,167,168,169,42,170],"setup","report","project","installation","project setup","state",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":178,"publishedAt":47},"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",[177],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[173,179,97,180,37,181,38,182,183,184,185],"start issue","issue","work on issue","user","work","work on","development",{"skillNo":187,"name":165,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":191,"publishedAt":47},"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",[],[165,167,130,192,169,193],"files","interactive"]