[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GVRFBY8YZM5FG504SW3GWH":3,"skill-same:01M6GVRFBY8YZM5FG504SW3GWH":77},{"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":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":52,"install":53,"resources":66},"01M6GVRFBY8YZM5FG504SW3GWH","qa-sweep",null,"Full-cycle QA orchestrator for Harnessy-compatible repositories: discovers feature surfaces, uses Playwright\u002Fbrowser walkthroughs when available, maps scenario gaps, updates regression artifacts, runs drift\u002Fvalidation, and reports coverage.","Flow-Research\u002Fharnessy","Flow-Research","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F204254796?v=4","01M6GVJZH9ZV0XGZTVBJRNW5BQ","Flow Research","01M6GVJZNSWAHPXW43628F7X76",30,"AGPL-3.0","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Fqa-sweep\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"qa","qa sweep","sweep","discover","artifacts","updates","apps","false","env","dry","app","feature","regression","local","map","drift","cycle","maps","coverage","Bash","2026-11-10 10:12:30",false,"---\nname: qa-sweep\ndescription: \"Full-cycle QA orchestrator for Harnessy-compatible repositories: discovers feature surfaces, uses Playwright\u002Fbrowser walkthroughs when available, maps scenario gaps, updates regression artifacts, runs drift\u002Fvalidation, and reports coverage.\"\ndisable-model-invocation: false\nallowed-tools: Read, Write, Grep, Glob, Bash, ApplyPatch\nargument-hint: \"[--all] [--apps \u003Capp,...>] [--features \u003Cslug,...>] [--phase discover|walk|map|codegen|execute|report] [--dry-run] [--skip-walk] [--env local|staging|production]\"\n---\n\n# QA Sweep\n\n## Purpose\n\nRun a complete QA coverage cycle in any repository that follows the Harnessy QA\nprofile contract. The sweep coordinates deterministic runtime checks with\nmodel-assisted discovery and browser inspection:\n\n1. discover app routes, APIs, actions, and existing regression coverage\n2. walk browser surfaces with Playwright when UI behavior or selectors matter\n3. map positive, negative, unauthorized, boundary, destructive, and persistence scenarios\n4. update regression specs and tests using codegen skills where appropriate\n5. execute or plan tests through repo-local commands\n6. report coverage gaps, failures, skips, and follow-up work\n\nTemplate paths are resolved from `${AGENTS_SKILLS_ROOT}\u002Fqa-sweep\u002F`.\n\n## Required Inputs\n\n- A canonical QA profile: `.jarvis\u002Fcontext\u002Fprofiles\u002Fqa.json`. Legacy\n  `.harnessy\u002Fqa-profile.json`, `.flow\u002Fqa-profile.json`, and `qa\u002Fqa-profile.json`\n  paths remain supported as fallbacks.\n- Regression specs and test roots declared by that profile.\n- Optional delivery profile metadata from `.flow\u002Fdelivery-profile.json` for\n  roles, routes, fixtures, helpers, selector inspection scripts, seeded account\n  flows, and result sinks.\n\n## Steps\n\n1. Follow `${AGENTS_SKILLS_ROOT}\u002Fqa-sweep\u002Fcommands\u002Fqa-sweep.md`.\n2. Run `qa ids`, `qa tests`, and `qa drift` before changing files.\n3. Discover source surfaces from the repo's actual framework and profile paths:\n   route files, API handlers, server actions\u002Fcontrollers, middleware\u002Fguards,\n   schemas, database migrations\u002Fpolicies, and shared workflow modules.\n4. Use `\u002Fbrowser-qa` or repo-local Playwright helpers for real browser\n   walkthroughs before writing browser assertions when selectors, redirects,\n   auth state, or persisted UI state are uncertain.\n5. Map scenarios with explicit roles and scenario types. Prefer container-backed\n   execution plans through Testcontainers or Docker Compose when DB\u002FAPI behavior\n   matters. Browser scenarios that\n   verify a persisted mutation or workflow transition must include a `DB Assert:`\n   or explain why persistence cannot be checked.\n6. Use `\u002Fbrowser-integration-codegen` and `\u002Fapi-integration-codegen` for test\n   scaffolding. Preserve canonical scenario IDs.\n7. Run `\u002Ftest-quality-validator` after generating or editing tests.\n8. Finish with `qa drift` and, when the target repo provides result-sink\n   commands, run the repo-local plan\u002Fexecute\u002Fsync commands documented by that repo.\n\n## Outputs\n\n- `.qa-sweep\u002F\u003Ctimestamp>\u002Fdiscover-*.md`\n- `.qa-sweep\u002F\u003Ctimestamp>\u002Fwalk-*.md` when browser walkthroughs run\n- `.qa-sweep\u002F\u003Ctimestamp>\u002Fmap-*.md`\n- `.qa-sweep\u002F\u003Ctimestamp>\u002Freport.md`\n- optional updates to regression specs, test files, feature catalog, and run results\n\n## Guardrails\n\n- Keep repo-specific auth, seed, sheet, dashboard, and CI behavior in the\n  target repo. This skill coordinates those commands but does not invent them.\n- Do not guess selectors from source when browser behavior can be walked.\n- Do not design mock-first API or persistence tests when a container-backed\n  integration test is practical.\n- Do not mark scenarios as implemented unless matching tests exist or are added\n  in the same change.\n- Gate destructive flows behind explicit user intent or a repo-local destructive\n  flag.\n- Never run destructive flows against production.\n- Preserve existing scenario IDs. Add new IDs only for genuinely new scenarios.\n","# QA Sweep\n\n## Purpose\n\nRun a complete QA coverage cycle in any repository that follows the Harnessy QA\nprofile contract. The sweep coordinates deterministic runtime checks with\nmodel-assisted discovery and browser inspection:\n\n1. discover app routes, APIs, actions, and existing regression coverage\n2. walk browser surfaces with Playwright when UI behavior or selectors matter\n3. map positive, negative, unauthorized, boundary, destructive, and persistence scenarios\n4. update regression specs and tests using codegen skills where appropriate\n5. execute or plan tests through repo-local commands\n6. report coverage gaps, failures, skips, and follow-up work\n\nTemplate paths are resolved from `${AGENTS_SKILLS_ROOT}\u002Fqa-sweep\u002F`.\n\n## Required Inputs\n\n- A canonical QA profile: `.jarvis\u002Fcontext\u002Fprofiles\u002Fqa.json`. Legacy\n  `.harnessy\u002Fqa-profile.json`, `.flow\u002Fqa-profile.json`, and `qa\u002Fqa-profile.json`\n  paths remain supported as fallbacks.\n- Regression specs and test roots declared by that profile.\n- Optional delivery profile metadata from `.flow\u002Fdelivery-profile.json` for\n  roles, routes, fixtures, helpers, selector inspection scripts, seeded account\n  flows, and result sinks.\n\n## Steps\n\n1. Follow `${AGENTS_SKILLS_ROOT}\u002Fqa-sweep\u002Fcommands\u002Fqa-sweep.md`.\n2. Run `qa ids`, `qa tests`, and `qa drift` before changing files.\n3. Discover source surfaces from the repo's actual framework and profile paths:\n   route files, API handlers, server actions\u002Fcontrollers, middleware\u002Fguards,\n   schemas, database migrations\u002Fpolicies, and shared workflow modules.\n4. Use `\u002Fbrowser-qa` or repo-local Playwright helpers for real browser\n   walkthroughs before writing browser assertions when selectors, redirects,\n   auth state, or persisted UI state are uncertain.\n5. Map scenarios with explicit roles and scenario types. Prefer container-backed\n   execution plans through Testcontainers or Docker Compose when DB\u002FAPI behavior\n   matters. Browser scenarios that\n   verify a persisted mutation or workflow transition must include a `DB Assert:`\n   or explain why persistence cannot be checked.\n6. Use `\u002Fbrowser-integration-codegen` and `\u002Fapi-integration-codegen` for test\n   scaffolding. Preserve canonical scenario IDs.\n7. Run `\u002Ftest-quality-validator` after generating or editing tests.\n8. Finish with `qa drift` and, when the target repo provides result-sink\n   commands, run the repo-local plan\u002Fexecute\u002Fsync commands documented by that repo.\n\n## Outputs\n\n- `.qa-sweep\u002F\u003Ctimestamp>\u002Fdiscover-*.md`\n- `.qa-sweep\u002F\u003Ctimestamp>\u002Fwalk-*.md` when browser walkthroughs run\n- `.qa-sweep\u002F\u003Ctimestamp>\u002Fmap-*.md`\n- `.qa-sweep\u002F\u003Ctimestamp>\u002Freport.md`\n- optional updates to regression specs, test files, feature catalog, and run results\n\n## Guardrails\n\n- Keep repo-specific auth, seed, sheet, dashboard, and CI behavior in the\n  target repo. This skill coordinates those commands but does not invent them.\n- Do not guess selectors from source when browser behavior can be walked.\n- Do not design mock-first API or persistence tests when a container-backed\n  integration test is practical.\n- Do not mark scenarios as implemented unless matching tests exist or are added\n  in the same change.\n- Gate destructive flows behind explicit user intent or a repo-local destructive\n  flag.\n- Never run destructive flows against production.\n- Preserve existing scenario IDs. Add new IDs only for genuinely new scenarios.\n",{"name":5,"description":7,"allowed-tools":44,"argument-hint":45,"disable-model-invocation":40},"Read, Write, Grep, Glob, Bash, ApplyPatch","[--all] [--apps \u003Capp,...>] [--features \u003Cslug,...>] [--phase discover|walk|map|codegen|execute|report] [--dry-run] [--skip-walk] [--env local|staging|production]","main","bae3fdddd99eabe649d0d53cea5d2a0b501aa8b3","tools\u002Fflow-install\u002Fskills\u002Fqa-sweep",7,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy","https:\u002F\u002Fgithub.com\u002FFlow-Research","2026-08-15 01:06:37",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add Flow-Research\u002Fharnessy --skill qa-sweep",{"tool":59,"command":60},"bunx","bunx skills add Flow-Research\u002Fharnessy --skill qa-sweep",{"tool":62,"command":63},"pnpm","pnpm dlx skills add Flow-Research\u002Fharnessy --skill qa-sweep","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Fqa-sweep\u002FSKILL.md",true,[67,73],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"commands\u002Fqa-sweep.md","REFERENCE","参考文档",3798,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Fqa-sweep\u002Fcommands\u002Fqa-sweep.md",{"path":74,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":75,"sourceHtmlUrl":76},"manifest.yaml",891,"https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Fqa-sweep\u002Fmanifest.yaml",[78,109,137,160,182,197],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":89,"publishedAt":39},"01M6GVTWDZDG82G8GGGYXXCT5B","wiki-research","Autonomous research orchestrator for Jarvis Wiki domains. Spawns a Claude agent with web tools to find new sources, drops them into raw\u002F, runs the compile pipeline, and emits autoresearch traces for the autoflow ratchet.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Fwiki-research\u002FSKILL.md",[84],{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[90,91,92,93,94,95,96,38,97,98,99,100,101,102,103,104,105,106,107,108],"research","wiki","wiki research","web","compile","autoresearch","pipeline","find","read","write","web tools","autonomous","orchestrator","domain","domains","sources","Autonomous Research","with","true",{"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":39},"01M6GVTQWAPB46BPQ6TCKSYDDA","tmux-agent-launcher","Launch Claude, OpenCode, or Codex in a named tmux session from the command line or agent workflows.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Ftmux-agent-launcher\u002FSKILL.md",[115],{"categoryNo":116,"categoryName":117,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000023","Skill与智能体开发",[119,120,121,122,123,124,125,126,98,127,128,129,130,131,132,133,134,135,108,136],"tmux","launcher","tmux agent launcher","codex","launch","workflows","command line","command","session","opencode","default","runner","options","permission","agent workflows","name","line","mode",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":146,"publishedAt":39},"01M6GVTJEW4N5BAT5AG1M58PF6","test-quality-validator","Validate generated or hand-written tests for coverage completeness, correctness, and false-green risks using the canonical QA runtime, regression artifacts, and optional delivery-profile rules.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Ftest-quality-validator\u002FSKILL.md",[143],{"categoryNo":144,"categoryName":145,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000008","测试与质量",[147,148,149,150,19,151,152,38,31,98,99,153,37,154,155,156,157,26,158,159],"test","quality","validator","test quality validator","browser","api","context","generated","only","delivery","green","canonical","hand",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":164,"categories":165,"keywords":166,"publishedAt":39},"01M6GVTE4BYCYCFKK2PS83ATX4","tech-spec","Generate production-ready technical specifications from product specs.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Ftech-spec\u002FSKILL.md",[],[167,168,169,170,171,172,173,174,175,98,99,176,177,178,108,179,180,181],"spec","tech spec","tech","review","generate","product","Production","grep","technical","ready","specifications","folder","websearch","path","production-ready",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":188,"publishedAt":39},"01M6GVT9FPGF2ME475HPQWKPSC","tech-spec-review","Seven-lens engineering review for technical_spec.md files, including an explicit simplicity and architectural fitness gate.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Ftech-spec-review\u002FSKILL.md",[],[170,167,189,168,169,190,191,174,175,98,99,192,193,194,195,196,108,179,180],"spec review","tech spec review","engineering","simplicity","files","gate","lens","quick",{"skillNo":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":208,"publishedAt":39},"01M6GVT3XTZ4W3P2XQRDNBPZ4M","spec-to-regression","Generate browser and API regression scenarios from approved product and technical specs using the Harnessy delivery profile and regression artifact contract.","https:\u002F\u002Fgithub.com\u002FFlow-Research\u002Fharnessy\u002Fblob\u002Fmain\u002Ftools\u002Fflow-install\u002Fskills\u002Fspec-to-regression\u002FSKILL.md",[203],{"categoryNo":204,"categoryName":205,"taxonomyType":206,"taxonomyTypeDesc":207},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[167,31,209,171,151,172,210,152,38,211,174,175,98,99,156,212,213,26,134,214],"spec to regression","flow","json","artifact","contract","EPIC"]