[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DHA7Q6KDGTNPCPK2HRSENS":3,"skill-same:01M6DHA7Q6KDGTNPCPK2HRSENS":76},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":13,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":51,"install":52,"resources":65},"01M6DHA7Q6KDGTNPCPK2HRSENS","e2e",null,"End-to-end \u002F acceptance testing orchestration. Run the project's configured e2e suite against a phase's acceptance scenarios, pick an execution mode (suite \u002F conductor \u002F direct \u002F data-layer), and capture the per-scenario passing evidence the ATDD gate and stop check 03 require.","JAuto-Corp\u002Fjustinventit","JAuto-Corp","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F254009312?v=4","01M6DH85D43FJAXD8RPBY6A91C","01M6DH85M60CDJBZ9W2CAFCPXE",0,"MIT","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fe2e\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[5,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"capture","conductor","scenario","end","project","gate","stop","evidence","execution mode","check","testing","pick","direct","execution","data","acceptance","run","orchestration","2026-11-10 10:12:30",false,"---\nname: e2e\ndescription: \"End-to-end \u002F acceptance testing orchestration. Run the project's configured e2e suite against a phase's acceptance scenarios, pick an execution mode (suite \u002F conductor \u002F direct \u002F data-layer), and capture the per-scenario passing evidence the ATDD gate and stop check 03 require.\"\n---\n\n# End-to-End Testing\n\nExercise the running system the way a user (or an upstream caller) would, and prove each of the phase's acceptance scenarios passes. This is the orchestration that produces the RED-then-GREEN, per-scenario evidence `checks\u002F03-scenario-evidence` and `04-tdd-cycle` look for when a phase signals `[PHASE_COMPLETE]`. Unit tests prove the pieces; e2e proves the whole flow.\n\n> Navigate fast, validate thoroughly. Reach the feature under test by the shortest reliable path, then scrutinise the new behaviour step by step. e2e is milestone-driven — run it at phase\u002Fsprint completion, not on every edit.\n\n## The configured runner (never hardcode a framework)\n\nRead the `testing` answer from `.copier-answers.yml` — it names the project's chosen E2E framework (or `none`). The concrete run command lives in `CLAUDE.md` § Essential Commands; always invoke e2e through that command and never assume a specific tool's API. If `testing: none`, there is no automated suite — verify scenarios manually and record completion with `[EVIDENCE_OVERRIDE:manual-testing]`.\n\n---\n\n## \u002Fe2e:run\n\nRun the active phase's acceptance suite and capture pass\u002Ffail evidence per scenario.\n\n1. **Load the scenarios.** Follow the state chain (`docs\u002FCURRENT_WORK.md` → the active phase's `SCENARIOS.md`). Each `Scenario:` \u002F `####` heading is one acceptance case (Given\u002FWhen\u002FThen).\n2. **Pick a mode per scenario** (menu below) — the automated suite for gating evidence; conductor\u002Fdirect\u002Fdata-layer for scrutiny or no-UI flows.\n3. **Run RED then GREEN.** Before the feature exists the scenario must fail for the right reason (missing impl, not a bad setup); after it exists it must pass. Both runs are the evidence `check\u002F04` wants.\n4. **Capture evidence per scenario.** The configured runner records `{scenario, status}` to the evidence JSON; interactive modes capture logs\u002Fscreenshots that `\u002Fverify:complete` records. One passing run per scenario id, or the phase can't close.\n\n## E2E modes (generic menu)\n\n| Mode | What it is | When |\n|-|-|-|\n| suite | The configured runner, run headlessly across the scenarios; records machine evidence | Default — the phase-gating evidence path |\n| conductor | Guided, step-by-step walk of new UI, capturing key states | New\u002Fchanged UI that needs visual scrutiny |\n| direct | Quick ad-hoc interactive check of one thing | Debugging, spot-checks (not gating evidence) |\n| data-layer | No-UI validation: drive via API\u002FCLI, assert via data queries | Engine \u002F scheduler \u002F background \u002F pure-API scenarios |\n\nMode workflows: `modes.md`.\n\n## Session coordination (portable caveat)\n\nInteractive, stateful session tools (browser drivers, live app sessions) run from the **main session — not from spawned sub-agents.** This framework's Explore\u002Fverify sub-agents are read-only context-gatherers: they can't hold a live session or load skills. Drive conductor\u002Fdirect\u002Fdata-layer flows yourself; delegate only read-only investigation of results or logs.\n\n## How e2e evidence feeds the gates\n\n`SCENARIOS.md` is the ATDD contract (`CLAUDE.md` § TDD Gate: no code without scenarios). Each scenario id must have a recorded **passing** run before `[PHASE_COMPLETE]`:\n\n| Gate | What it checks |\n|-|-|\n| TDD\u002FATDD gate (`checks\u002F01`) | Standard+ scope has a `SCENARIOS.md` |\n| `checks\u002F04-tdd-cycle` | RED recorded before GREEN for each scenario |\n| `checks\u002F03-scenario-evidence` | Every `SCENARIOS.md` scenario has a passing run in the evidence JSON |\n\n`\u002Fe2e:run` produces those runs; `\u002Fverify:complete` (the exit gate `\u002Fwork:done` calls) reads and confirms them. A scenario with no passing run blocks the phase — fix it, or, for a legitimately manual\u002Fcode-free case, signal `[EVIDENCE_OVERRIDE:manual-testing]` honestly.\n\n## When to run\n\n| Trigger | Scope |\n|-|-|\n| Phase complete | Every scenario in the phase `SCENARIOS.md` |\n| Sprint complete | Full sweep of the sprint's features |\n| Bug-fix verify | The affected flow(s) only |\n\nNot on every code change — that's the job of unit tests and the TDD inner loop.\n","# End-to-End Testing\n\nExercise the running system the way a user (or an upstream caller) would, and prove each of the phase's acceptance scenarios passes. This is the orchestration that produces the RED-then-GREEN, per-scenario evidence `checks\u002F03-scenario-evidence` and `04-tdd-cycle` look for when a phase signals `[PHASE_COMPLETE]`. Unit tests prove the pieces; e2e proves the whole flow.\n\n> Navigate fast, validate thoroughly. Reach the feature under test by the shortest reliable path, then scrutinise the new behaviour step by step. e2e is milestone-driven — run it at phase\u002Fsprint completion, not on every edit.\n\n## The configured runner (never hardcode a framework)\n\nRead the `testing` answer from `.copier-answers.yml` — it names the project's chosen E2E framework (or `none`). The concrete run command lives in `CLAUDE.md` § Essential Commands; always invoke e2e through that command and never assume a specific tool's API. If `testing: none`, there is no automated suite — verify scenarios manually and record completion with `[EVIDENCE_OVERRIDE:manual-testing]`.\n\n---\n\n## \u002Fe2e:run\n\nRun the active phase's acceptance suite and capture pass\u002Ffail evidence per scenario.\n\n1. **Load the scenarios.** Follow the state chain (`docs\u002FCURRENT_WORK.md` → the active phase's `SCENARIOS.md`). Each `Scenario:` \u002F `####` heading is one acceptance case (Given\u002FWhen\u002FThen).\n2. **Pick a mode per scenario** (menu below) — the automated suite for gating evidence; conductor\u002Fdirect\u002Fdata-layer for scrutiny or no-UI flows.\n3. **Run RED then GREEN.** Before the feature exists the scenario must fail for the right reason (missing impl, not a bad setup); after it exists it must pass. Both runs are the evidence `check\u002F04` wants.\n4. **Capture evidence per scenario.** The configured runner records `{scenario, status}` to the evidence JSON; interactive modes capture logs\u002Fscreenshots that `\u002Fverify:complete` records. One passing run per scenario id, or the phase can't close.\n\n## E2E modes (generic menu)\n\n| Mode | What it is | When |\n|-|-|-|\n| suite | The configured runner, run headlessly across the scenarios; records machine evidence | Default — the phase-gating evidence path |\n| conductor | Guided, step-by-step walk of new UI, capturing key states | New\u002Fchanged UI that needs visual scrutiny |\n| direct | Quick ad-hoc interactive check of one thing | Debugging, spot-checks (not gating evidence) |\n| data-layer | No-UI validation: drive via API\u002FCLI, assert via data queries | Engine \u002F scheduler \u002F background \u002F pure-API scenarios |\n\nMode workflows: `modes.md`.\n\n## Session coordination (portable caveat)\n\nInteractive, stateful session tools (browser drivers, live app sessions) run from the **main session — not from spawned sub-agents.** This framework's Explore\u002Fverify sub-agents are read-only context-gatherers: they can't hold a live session or load skills. Drive conductor\u002Fdirect\u002Fdata-layer flows yourself; delegate only read-only investigation of results or logs.\n\n## How e2e evidence feeds the gates\n\n`SCENARIOS.md` is the ATDD contract (`CLAUDE.md` § TDD Gate: no code without scenarios). Each scenario id must have a recorded **passing** run before `[PHASE_COMPLETE]`:\n\n| Gate | What it checks |\n|-|-|\n| TDD\u002FATDD gate (`checks\u002F01`) | Standard+ scope has a `SCENARIOS.md` |\n| `checks\u002F04-tdd-cycle` | RED recorded before GREEN for each scenario |\n| `checks\u002F03-scenario-evidence` | Every `SCENARIOS.md` scenario has a passing run in the evidence JSON |\n\n`\u002Fe2e:run` produces those runs; `\u002Fverify:complete` (the exit gate `\u002Fwork:done` calls) reads and confirms them. A scenario with no passing run blocks the phase — fix it, or, for a legitimately manual\u002Fcode-free case, signal `[EVIDENCE_OVERRIDE:manual-testing]` honestly.\n\n## When to run\n\n| Trigger | Scope |\n|-|-|\n| Phase complete | Every scenario in the phase `SCENARIOS.md` |\n| Sprint complete | Full sweep of the sprint's features |\n| Bug-fix verify | The affected flow(s) only |\n\nNot on every code change — that's the job of unit tests and the TDD inner loop.\n",{"name":5,"description":7},"main","07fef474a459f2562dbae35a3baf6470c8ae530d","template\u002F.claude\u002Fskills\u002Forchestrators\u002Fe2e","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit","https:\u002F\u002Fgithub.com\u002FJAuto-Corp","2026-11-10 13:45:22",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add JAuto-Corp\u002Fjustinventit --skill e2e",{"tool":58,"command":59},"bunx","bunx skills add JAuto-Corp\u002Fjustinventit --skill e2e",{"tool":61,"command":62},"pnpm","pnpm dlx skills add JAuto-Corp\u002Fjustinventit --skill e2e","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fe2e\u002FSKILL.md",true,[66,72],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"agents\u002Fopenai.yaml","REFERENCE","参考文档",100,"https:\u002F\u002Fgithub.com\u002Fstanley50z\u002Fsz-skills\u002Fblob\u002Fmain\u002Fskills\u002Fcode-review\u002Fagents\u002Fopenai.yaml",{"path":73,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":74,"sourceHtmlUrl":75},"modes.md",2908,"https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fe2e\u002Fmodes.md",[77,104,126,148,167,178],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":81,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":41},"01M6DHBJE2P291DTXAW6DE6ZSR","ponytail","Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says \"ponytail\", \"be lazy\", \"lazy mode\", \"simplest solution\", \"minimal solution\", \"yagni\", \"do less\", or \"shortest path\", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Fponytail\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Fponytail\u002FSKILL.md",[],[79,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103],"writing","yagni","line","recipes","platform","dependencies","task","do","translation","default","general","minimal","use","question","refactoring","knowledge","dev","code","libraries",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":118,"publishedAt":41},"01M6DHB61PAWVGHF53A89MJ6SM","workflow\u002Fskill","Patterns for adding or editing a skill — frontmatter contract, router + sub-file split, line budgets.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002Fskill.md",[110,113],{"categoryNo":111,"categoryName":112,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":114,"categoryName":115,"taxonomyType":116,"taxonomyTypeDesc":117},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[119,120,121,122,123,124,125,87],"workflow skill","workflow","patterns","router","editing","file","contract",{"skillNo":127,"name":120,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":132,"publishedAt":41},"01M6DHB1GD89RW71ZYZJZJH4ZG","Meta-skill for editing the framework itself — skills, hooks, commands, rules, CLAUDE.md. Use before changing anything under .claude\u002F or the routing docs, so the change keeps the system's shape (lazy-load, forge markers, hook auto-discovery, harness).","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fworkflow\u002FSKILL.md",[131],{"categoryNo":111,"categoryName":112,"taxonomyType":20,"taxonomyTypeDesc":21},[120,133,134,135,136,137,97,123,138,139,140,141,142,143,144,145,146,147],"commands","meta-skill","shape","hooks","auto","Rules","system","discovery","Meta","forge","harness","change","routing","docs","framework",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":41},"01M6DHAX1NCV3HXK4M1RMBWGAV","work","Work lifecycle orchestration: start, continue, pause, handoff, done, plus epic\u002Fsprint planning. Context gathering + goal-focused state-chain transitions.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fwork\u002FSKILL.md",[],[150,155,156,157,158,159,160,161,162,163,164,165,40,166],"continue","chain","sprint planning","transitions","done","goal","context","lifecycle","start","state","planning","handoff",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":41},"01M6DHASZYRB1ZZWVNQ6CN8FN3","verify","Verification and auditing. Validate acceptance scenarios, run multi-perspective audits, check type-check\u002Fbuild evidence, and gate phase\u002Fsprint completion.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fverify\u002FSKILL.md",[],[169,32,174,38,39,175,30,176,177,28],"verification","validate","type","build",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":41},"01M6DHAP9JN9X7ZSWCWYTWN1KT","team-lead","Coordinate an Agent Team for parallelizable work — implementation, audit, research, or testing. Teaches the mechanical constraints (WAIT pattern, file ownership, model tiers) and lets you design the team. For orchestration_tier=cluster \u002F multi-agent runs.","https:\u002F\u002Fgithub.com\u002FJAuto-Corp\u002Fjustinventit\u002Fblob\u002Fmain\u002Ftemplate\u002F.claude\u002Fskills\u002Forchestrators\u002Fteam-lead\u002FSKILL.md",[],[185,186,187,188,189,190,191,192,150,193,194,195,196,124,40,197,198,33],"team","team lead","implementation","wait","mechanical","pattern","agent team","coordinate","multi-agent","model","constraints","audit","research","design"]