[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71RG0PBMNZFMF3MTRPVS2RC":3,"skill-same:01M71RG0PBMNZFMF3MTRPVS2RC":97},{"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":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M71RG0PBMNZFMF3MTRPVS2RC","autospec-playwright",null,"Use when you want to run disciplined no-mock Playwright UI-test authoring (Stage 2A) for a project. Detects the .autospec\u002Ftest.yml authoring blocks, invokes autospec-test Stage 2A, and prints the coverage report.","berlinguyinca\u002Fautospec","berlinguyinca","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F16364?v=4","01M71R7C0SWBG05FNHQE4XQ7Y3","Gert Wohlgemuth","01M71R7C1VY5K3Q715RNDDBVGQ",3,"MIT","https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-playwright\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],"playwright","autospec playwright","autospec","ui","authoring","blocks","report","run","test","you","ui-test","stage","when","mock","use","project","for","coverage","2026-11-10 13:02:02",false,"---\nname: autospec-playwright\ndescription: Use when you want to run disciplined no-mock Playwright UI-test authoring (Stage 2A) for a project. Detects the .autospec\u002Ftest.yml authoring blocks, invokes autospec-test Stage 2A, and prints the coverage report.\n---\n\n# autospec-playwright — Disciplined Playwright Authoring Dispatcher\n\nThin dispatcher for the `autospec-test` Stage 2A disciplined-authoring pipeline.\nReads `.autospec\u002Ftest.yml` authoring and reset blocks, invokes Stage 2A, and\nprints the e2e coverage report from `e2e\u002F.autospec\u002Fcoverage.json`. Carries NO\nmachinery of its own — all logic lives in `autospec-test`.\n\n## Self-update mode\n\nDecide this purely from the request text the harness handed you. Do NOT\nshell out (no `grep`, `sed`, `[[ =~ ]]`, command substitution, etc.) to\ntest the user's free-form request — passing it through a shell is what\nhistorically tripped harness permission engines. Read the request, normalize\nit in your reasoning (collapse whitespace, trim, lowercase), and if the result is\nexactly `update`, this skill enters self-update mode and does NOT run the\nnormal pipeline.\n\n1. Detect harness by checking which install path exists for this skill:\n   - Claude Code: `~\u002F.claude\u002Fskills\u002Fautospec-playwright\u002FSKILL.md`\n   - OpenCode:    `~\u002F.config\u002Fopencode\u002Fagent\u002Fautospec-playwright.md`\n   - Codex CLI:   `~\u002F.codex\u002Fprompts\u002Fautospec-playwright.md`\n2. Re-install from `main` by piping the canonical installer:\n   ```\n   curl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fberlinguyinca\u002Fautospec\u002Fmain\u002Fbootstrap.sh | bash -s -- --skill all --harness all --update\n   ```\n   Run this one-liner once; it refreshes all autospec skills across all harnesses.\n3. Show the diff between the prior installed file(s) and the freshly fetched copy.\n4. Stop. Do not enter any pipeline phase. Print the upgrade summary and return to the user.\n\nIf no install path is detected, print `Self-update: no installed copy of autospec-playwright found; run install.sh first.` and exit.\n\n## Model tier\n\n**Model tier:** `TIER_B` for all dispatch work (thin dispatcher; no design decisions).\n\n## Required capabilities & harness adapter\n\nThis workflow assumes a small set of capabilities. Map each one to your harness's actual tool.\n\n| Capability                  | Claude Code                             | OpenCode                              | Codex CLI                             | Fallback if missing                    |\n|-----------------------------|-----------------------------------------|---------------------------------------|---------------------------------------|----------------------------------------|\n| Read-only codebase research | `Agent` (subagent_type=Explore)         | `task` agent in read-only mode        | shell `grep`                          | Do the search in-thread                |\n| Foreground delegation       | `Agent` (subagent_type=general-purpose) | nested `task` agent                   | spawn nested CLI session              | Do the work in-thread                  |\n| Ask the user a question     | `AskUserQuestion`                       | inline prompt                         | inline prompt                         | Ask in response and wait               |\n| Subagent model tier         | **Model tier:** `TIER_B` for all dispatch work | top task model + medium reasoning | top GPT + reasoning_effort=medium | Honor per-phase tier mapping          |\n| Subagent dispatch policy    | per AGENTS.md decision matrix           | per AGENTS.md decision matrix         | per AGENTS.md decision matrix         | inline with main-session token cost    |\n\n## Harness detection\n\nDetect your harness by checking available tools before any phase:\n\n1. **Claude Code** — the `Agent` tool with a `subagent_type` parameter is available.\n   - `TIER_A` = `opus` + `ultrathink`\n   - `TIER_B` = `sonnet`\n\n2. **OpenCode** — a `task` tool with model\u002Ftier configuration is available (no `subagent_type`).\n   - `TIER_A` = top-tier task model + high reasoning\n   - `TIER_B` = smaller-tier task model + medium reasoning\n\n3. **Codex CLI** — neither `Agent` nor a configurable `task` tool is available.\n   - `TIER_A` = current top GPT model + `reasoning_effort=high`\n   - `TIER_B` = the spark \u002F cost-optimized variant of the configured model when one exists, else the configured model + `reasoning_effort=medium`\n\n**Fallback rule:** If `TIER_B` is not available (quota, capacity, or authorization failure),\nsilently retry with `TIER_A`. Never ask the user.\n\n## Invocation\n\n```\n\u002Fautospec-playwright [--dry-run]\n```\n\n## Screenshot-audit guardrails\n\nProjects may turn the JSON produced by the screenshot audit into documentation\nand stable, pixel-independent Playwright checks:\n\n```bash\nnode skills\u002Fautospec-doc\u002Fscripts\u002Fgen-ui-audit-doc.mjs --input .autospec\u002Fscreenshot-audit.json --output docs\u002Fui-audit.md\nnode skills\u002Fautospec-qa\u002Fscripts\u002Fgen-layout-guardrails.mjs --input .autospec\u002Fscreenshot-audit.json --output e2e\u002Fgenerated\u002Flayout-guardrails.spec.mjs\n```\n\nThe generated suite checks visible content, auth-shell absence, and **document**\nhorizontal overflow at desktop\u002Ftablet\u002Fmobile widths. Intentional component\nscroll containers (tables and charts) are not treated as document overflow.\nPrimitive-count checks remain disabled by default; add `--strict-counts` only\nwhen the fixture's live data is deterministic, then include the generated file\nin the project's existing Playwright command. No pixel snapshots are required.\n\n- `--dry-run` — print what would be done; do not invoke Stage 2A.\n\n## Dispatcher flow\n\n1. **Locate config.** Read `.autospec\u002Ftest.yml` via `loadAuthoringConfig()` from\n   `skills\u002Fautospec-test\u002Fscripts\u002Fauthoring-config.mjs`. If the file is missing or\n   `e2e.authoring.enabled` is false, print:\n   ```\n   autospec-playwright: e2e.authoring.enabled is false (or .autospec\u002Ftest.yml missing).\n   Set e2e.authoring.enabled: true to enable Stage 2A authoring.\n   ```\n   and exit 0.\n\n2. **Invoke Stage 2A.** Call `autospec-test` Stage 2A — disciplined authoring —\n   passing the resolved `spec_dir`, `helpers_dir`, `route_clusters`, `coverage_target_pct`,\n   and `fanout_max` from the authoring config. Stage 2A is owned by\n   `skills\u002Fautospec-test\u002Fscripts\u002Fstage2a-orchestrator.mjs`; this dispatcher does\n   NOT duplicate any of its logic.\n\n3. **Print coverage report.** After Stage 2A completes, read\n   `e2e\u002F.autospec\u002Fcoverage.json` (shape: `{total, covered, pct}`) and print:\n   ```\n   autospec-playwright coverage: covered=\u003Ccovered>\u002F\u003Ctotal> (\u003Cpct>%)\n   ```\n   If the file is absent, print `autospec-playwright: coverage.json not found — Stage 2A may not have run.`\n\n4. **Exit code.** Exit 0 on success, 1 on Stage 2A failure.\n\n## Loaded-data dashboard evidence\n\nFor autospec-created dashboard E2E or visual tests, do not accept a fixture,\nscreenshot, or baseline until the test proves the dashboard is past its loading\nshell and has rendered service-backed data. The authored test must include at least one loaded-data assertion against\na stable KPI, table row, service field, or route-specific datum that comes from the installed fixture response rather\nthan from placeholder UI chrome.\n\nReject any visual baseline or snapshot whose visible page still matches\n`\u002Floading|skeleton|empty\u002Fi`, including loading spinners, skeleton cards, empty\nstates, or placeholder-only dashboards. If such text or UI is still present,\nwait for the loaded-data assertion to pass or fix the fixture route before\ncapturing the baseline.\n\nWhen dashboard tests install network fixtures, register broad catch-all mocks\nfirst, then install route-specific dashboard fixtures after catch-all mocks so\nthe loaded service response wins over fallback handlers. The acceptance proof\nmust cite the loaded-data assertion and the fixture route that supplies it.\n\n## Out of scope\n\n- Stage 2A machinery (owned by `autospec-test` issue #996).\n- Reset-endpoint generation (owned by `autospec-test` issue #997).\n- Loop classification (owned by `autospec-test` issue #998).\n- Any Playwright spec file authoring directly — this dispatcher wires; it does not author.\n","# autospec-playwright — Disciplined Playwright Authoring Dispatcher\n\nThin dispatcher for the `autospec-test` Stage 2A disciplined-authoring pipeline.\nReads `.autospec\u002Ftest.yml` authoring and reset blocks, invokes Stage 2A, and\nprints the e2e coverage report from `e2e\u002F.autospec\u002Fcoverage.json`. Carries NO\nmachinery of its own — all logic lives in `autospec-test`.\n\n## Self-update mode\n\nDecide this purely from the request text the harness handed you. Do NOT\nshell out (no `grep`, `sed`, `[[ =~ ]]`, command substitution, etc.) to\ntest the user's free-form request — passing it through a shell is what\nhistorically tripped harness permission engines. Read the request, normalize\nit in your reasoning (collapse whitespace, trim, lowercase), and if the result is\nexactly `update`, this skill enters self-update mode and does NOT run the\nnormal pipeline.\n\n1. Detect harness by checking which install path exists for this skill:\n   - Claude Code: `~\u002F.claude\u002Fskills\u002Fautospec-playwright\u002FSKILL.md`\n   - OpenCode:    `~\u002F.config\u002Fopencode\u002Fagent\u002Fautospec-playwright.md`\n   - Codex CLI:   `~\u002F.codex\u002Fprompts\u002Fautospec-playwright.md`\n2. Re-install from `main` by piping the canonical installer:\n   ```\n   curl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fberlinguyinca\u002Fautospec\u002Fmain\u002Fbootstrap.sh | bash -s -- --skill all --harness all --update\n   ```\n   Run this one-liner once; it refreshes all autospec skills across all harnesses.\n3. Show the diff between the prior installed file(s) and the freshly fetched copy.\n4. Stop. Do not enter any pipeline phase. Print the upgrade summary and return to the user.\n\nIf no install path is detected, print `Self-update: no installed copy of autospec-playwright found; run install.sh first.` and exit.\n\n## Model tier\n\n**Model tier:** `TIER_B` for all dispatch work (thin dispatcher; no design decisions).\n\n## Required capabilities & harness adapter\n\nThis workflow assumes a small set of capabilities. Map each one to your harness's actual tool.\n\n| Capability                  | Claude Code                             | OpenCode                              | Codex CLI                             | Fallback if missing                    |\n|-----------------------------|-----------------------------------------|---------------------------------------|---------------------------------------|----------------------------------------|\n| Read-only codebase research | `Agent` (subagent_type=Explore)         | `task` agent in read-only mode        | shell `grep`                          | Do the search in-thread                |\n| Foreground delegation       | `Agent` (subagent_type=general-purpose) | nested `task` agent                   | spawn nested CLI session              | Do the work in-thread                  |\n| Ask the user a question     | `AskUserQuestion`                       | inline prompt                         | inline prompt                         | Ask in response and wait               |\n| Subagent model tier         | **Model tier:** `TIER_B` for all dispatch work | top task model + medium reasoning | top GPT + reasoning_effort=medium | Honor per-phase tier mapping          |\n| Subagent dispatch policy    | per AGENTS.md decision matrix           | per AGENTS.md decision matrix         | per AGENTS.md decision matrix         | inline with main-session token cost    |\n\n## Harness detection\n\nDetect your harness by checking available tools before any phase:\n\n1. **Claude Code** — the `Agent` tool with a `subagent_type` parameter is available.\n   - `TIER_A` = `opus` + `ultrathink`\n   - `TIER_B` = `sonnet`\n\n2. **OpenCode** — a `task` tool with model\u002Ftier configuration is available (no `subagent_type`).\n   - `TIER_A` = top-tier task model + high reasoning\n   - `TIER_B` = smaller-tier task model + medium reasoning\n\n3. **Codex CLI** — neither `Agent` nor a configurable `task` tool is available.\n   - `TIER_A` = current top GPT model + `reasoning_effort=high`\n   - `TIER_B` = the spark \u002F cost-optimized variant of the configured model when one exists, else the configured model + `reasoning_effort=medium`\n\n**Fallback rule:** If `TIER_B` is not available (quota, capacity, or authorization failure),\nsilently retry with `TIER_A`. Never ask the user.\n\n## Invocation\n\n```\n\u002Fautospec-playwright [--dry-run]\n```\n\n## Screenshot-audit guardrails\n\nProjects may turn the JSON produced by the screenshot audit into documentation\nand stable, pixel-independent Playwright checks:\n\n```bash\nnode skills\u002Fautospec-doc\u002Fscripts\u002Fgen-ui-audit-doc.mjs --input .autospec\u002Fscreenshot-audit.json --output docs\u002Fui-audit.md\nnode skills\u002Fautospec-qa\u002Fscripts\u002Fgen-layout-guardrails.mjs --input .autospec\u002Fscreenshot-audit.json --output e2e\u002Fgenerated\u002Flayout-guardrails.spec.mjs\n```\n\nThe generated suite checks visible content, auth-shell absence, and **document**\nhorizontal overflow at desktop\u002Ftablet\u002Fmobile widths. Intentional component\nscroll containers (tables and charts) are not treated as document overflow.\nPrimitive-count checks remain disabled by default; add `--strict-counts` only\nwhen the fixture's live data is deterministic, then include the generated file\nin the project's existing Playwright command. No pixel snapshots are required.\n\n- `--dry-run` — print what would be done; do not invoke Stage 2A.\n\n## Dispatcher flow\n\n1. **Locate config.** Read `.autospec\u002Ftest.yml` via `loadAuthoringConfig()` from\n   `skills\u002Fautospec-test\u002Fscripts\u002Fauthoring-config.mjs`. If the file is missing or\n   `e2e.authoring.enabled` is false, print:\n   ```\n   autospec-playwright: e2e.authoring.enabled is false (or .autospec\u002Ftest.yml missing).\n   Set e2e.authoring.enabled: true to enable Stage 2A authoring.\n   ```\n   and exit 0.\n\n2. **Invoke Stage 2A.** Call `autospec-test` Stage 2A — disciplined authoring —\n   passing the resolved `spec_dir`, `helpers_dir`, `route_clusters`, `coverage_target_pct`,\n   and `fanout_max` from the authoring config. Stage 2A is owned by\n   `skills\u002Fautospec-test\u002Fscripts\u002Fstage2a-orchestrator.mjs`; this dispatcher does\n   NOT duplicate any of its logic.\n\n3. **Print coverage report.** After Stage 2A completes, read\n   `e2e\u002F.autospec\u002Fcoverage.json` (shape: `{total, covered, pct}`) and print:\n   ```\n   autospec-playwright coverage: covered=\u003Ccovered>\u002F\u003Ctotal> (\u003Cpct>%)\n   ```\n   If the file is absent, print `autospec-playwright: coverage.json not found — Stage 2A may not have run.`\n\n4. **Exit code.** Exit 0 on success, 1 on Stage 2A failure.\n\n## Loaded-data dashboard evidence\n\nFor autospec-created dashboard E2E or visual tests, do not accept a fixture,\nscreenshot, or baseline until the test proves the dashboard is past its loading\nshell and has rendered service-backed data. The authored test must include at least one loaded-data assertion against\na stable KPI, table row, service field, or route-specific datum that comes from the installed fixture response rather\nthan from placeholder UI chrome.\n\nReject any visual baseline or snapshot whose visible page still matches\n`\u002Floading|skeleton|empty\u002Fi`, including loading spinners, skeleton cards, empty\nstates, or placeholder-only dashboards. If such text or UI is still present,\nwait for the loaded-data assertion to pass or fix the fixture route before\ncapturing the baseline.\n\nWhen dashboard tests install network fixtures, register broad catch-all mocks\nfirst, then install route-specific dashboard fixtures after catch-all mocks so\nthe loaded service response wins over fallback handlers. The acceptance proof\nmust cite the loaded-data assertion and the fixture route that supplies it.\n\n## Out of scope\n\n- Stage 2A machinery (owned by `autospec-test` issue #996).\n- Reset-endpoint generation (owned by `autospec-test` issue #997).\n- Loop classification (owned by `autospec-test` issue #998).\n- Any Playwright spec file authoring directly — this dispatcher wires; it does not author.\n",{"name":5,"description":7},"main","9e7f04357ff46ab731d4f56a4ac5ca5449c13bb0","skills\u002Fautospec-playwright",1,"https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec","https:\u002F\u002Fgithub.com\u002Fberlinguyinca","Love to lead, code, cook and contribute to open source and believe that you can learn anything you set your mind too.\r\n","2026-11-11 07:09:35",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add berlinguyinca\u002Fautospec --skill autospec-playwright",{"tool":61,"command":62},"bunx","bunx skills add berlinguyinca\u002Fautospec --skill autospec-playwright",{"tool":64,"command":65},"pnpm","pnpm dlx skills add berlinguyinca\u002Fautospec --skill autospec-playwright","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-playwright\u002FSKILL.md",true,[69,75,81,85,89,93],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"codex\u002Fprompt.md","REFERENCE","参考文档",7826,"https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-playwright\u002Fcodex\u002Fprompt.md",{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"install.sh","SCRIPT","脚本",4924,"https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-playwright\u002Finstall.sh",{"path":82,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":83,"sourceHtmlUrl":84},"opencode\u002Fagent.md",8100,"https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-playwright\u002Fopencode\u002Fagent.md",{"path":86,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":87,"sourceHtmlUrl":88},"README.md",714,"https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-playwright\u002FREADME.md",{"path":90,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":91,"sourceHtmlUrl":92},"uninstall.sh",3838,"https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-playwright\u002Funinstall.sh",{"path":94,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":95,"sourceHtmlUrl":96},"validate.sh",4051,"https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-playwright\u002Fvalidate.sh",[98,109,118,127,153,175],{"skillNo":99,"name":100,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":106,"publishedAt":42},"01M71RJHYMKPTC9AAPXWQ6F4RT","trio-pass-skill","https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flockstep-trio-pass\u002FSKILL.md",[103],{"categoryNo":104,"categoryName":105,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[107,108],"trio","trio pass skill",{"skillNo":110,"name":111,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":115,"publishedAt":42},"01M71RJFBQ1KAF9XM3T3Y4VMSK","duo-pass-skill","https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flockstep-duo-pass\u002FSKILL.md",[114],{"categoryNo":104,"categoryName":105,"taxonomyType":21,"taxonomyTypeDesc":22},[116,117],"duo pass skill","duo",{"skillNo":119,"name":120,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":124,"publishedAt":42},"01M71RJDT1TB3P9TRWR6A534FB","duo-divergence-skill","https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flockstep-duo-divergence\u002FSKILL.md",[123],{"categoryNo":104,"categoryName":105,"taxonomyType":21,"taxonomyTypeDesc":22},[125,117,126],"duo divergence skill","divergence",{"skillNo":128,"name":26,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":135,"publishedAt":42},"01M71RJAC4NNEQSYBDSY3NZS73","Use when the user wants to ship a feature end-to-end across multiple commits — bootstraps repo if missing, brainstorms a design spec, decomposes into linked GitHub issues, or splits an existing spec into issues, then runs an autonomous implementation loop with auto-merge.","https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec\u002FSKILL.md",[132],{"categoryNo":133,"categoryName":134,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[26,136,137,138,139,140,141,142,36,143,144,145,146,147,148,149,150,151,152,38],"ship a feature","end","issues","design","autonomous","auto","loop","across","design spec","merge","ship","implementation loop","github issues","feature","commits","repo","missing",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":42},"01M71RJ4F9HT8PT26CKNM9XE1M","autospec-upgrade","Use when the user wants to upgrade an Angular, Next.js, or React project to the latest official versions safely — by locking observable behavior before touching versions, upgrading one major at a time with official codemods, and gating completion on mutation score rather than coverage theater.","https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-upgrade\u002FSKILL.md",[],[160,26,161,162,41,163,39,164,165,36,166,167,168,169,38,170,171,172,173,174],"autospec upgrade","upgrade","mutation","official","time","gating","angular","react","next","at","Next.js","one","with","behavior","latest",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":186,"publishedAt":42},"01M71RJ28FJ4PM6DXHB7T5CF8H","autospec-ui-audit","Use when a React Router application needs a deterministic whole-site route inventory before UI, UX, navigation, or evidence auditing begins.","https:\u002F\u002Fgithub.com\u002Fberlinguyinca\u002Fautospec\u002Fblob\u002Fmain\u002Fskills\u002Fautospec-ui-audit\u002FSKILL.md",[181],{"categoryNo":182,"categoryName":183,"taxonomyType":184,"taxonomyTypeDesc":185},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[187,26,188,189,27,38,190,191,192,193,194,195,196,197,198,167,199,36,200],"ui audit","audit","autospec ui audit","inventory","evidence","deterministic","route","ux","site","react router","navigation","application","needs","router"]