[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79PN52RM9P9ACZ0SA20AAM3":3,"skill-same:01M79PN52RM9P9ACZ0SA20AAM3":47},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M79PN52RM9P9ACZ0SA20AAM3","orch-pipeline",null,"Shared orchestration engine behind the orch-* skill family — the gated Research-Plan-TDD-Review-Commit pipeline, size classifier, agent and command map, and two human gates (plan approval, commit confirmation) that orch-* operation skills delegate to. Use indirectly via orch-add-feature, orch-fix-defect, orch-change-feature, orch-refine-code, or orch-build-mvp; read directly only when adding an orch operation or tuning shared phases.","JunMystery\u002FAgent-Guidance","JunMystery","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F161468934?v=4","01M79MTMV8F0BY8NK1A92RA8A0","Jun","01M79MTMWCFBKPHN5B25E6V20B",0,"MIT","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Forch-pipeline\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: orch-pipeline\ndescription: Shared orchestration engine behind the orch-* skill family — the gated Research-Plan-TDD-Review-Commit pipeline, size classifier, agent and command map, and two human gates (plan approval, commit confirmation) that orch-* operation skills delegate to. Use indirectly via orch-add-feature, orch-fix-defect, orch-change-feature, orch-refine-code, or orch-build-mvp; read directly only when adding an orch operation or tuning shared phases.\nmetadata:\n  origin: ECC\n---\n\n# Orchestrator Pipeline (shared engine)\n\nThe `orch-*` skills are thin wrappers. They do not re-implement any work — they\nclassify the request, choose which phases of *this* pipeline run, and delegate\neach phase to an existing ECC agent or command. This file is that pipeline.\n\n> Invoke an operation skill (`orch-add-feature`, `orch-fix-defect`, …) rather\n> than this engine directly. This file is the reference they point at.\n\n## When to Use\n\n- Loaded indirectly whenever an `orch-*` operation skill runs.\n- Read directly only when adding a new operation to the family or tuning the\n  shared phases, gates, or agent map.\n\n## The operation family\n\n| Skill | Operation | Trigger | First move |\n|-------|-----------|---------|------------|\n| `orch-add-feature` | feature | capability does not exist yet | research + plan a new slice |\n| `orch-change-feature` | tweak | works, but desired behavior differs | amend existing behavior *and its tests* |\n| `orch-fix-defect` | fix | broken; behavior is wrong | reproduce as a failing test, then fix |\n| `orch-refine-code` | refactor | behavior stays, structure improves | restructure while keeping tests green |\n| `orch-build-mvp` | mvp | bootstrap from a design\u002Fspec doc | ingest doc → vertical slices |\n\n> These wrappers **compose** existing ECC commands rather than replace them:\n> `\u002Ffeature-dev`, `\u002Fplan`, `\u002Fcode-review`, `\u002Fbuild-fix`, `\u002Frefactor-clean`, and\n> `\u002Fgan-build`, plus the `tdd-workflow` skill. The orch-* family adds the shared\n> size classifier and the two gates\n> on top of them, so one umbrella covers all five operations consistently.\n\n## Step 0 — Classify size (right-sizing)\n\nCeremony scales to blast radius. Score the request on three signals, take the\n**highest** tier any signal reaches, and state the result in one line so the user\ncan override:\n\n| Tier | Files touched | New dependency \u002F contract | Design ambiguity | Phases that run |\n|------|---------------|---------------------------|------------------|-----------------|\n| trivial | 1, a few lines | none | none — the change is obvious | 4 → 5 → 6 |\n| small | 1 file \u002F 1 function | none | clear once you read the code | (1 light) → 4 → 5 → 6 |\n| standard | 2–5 files | maybe a new internal module | one real choice to make | 1 → 2 → 4 → 5 → 6 |\n| large | many \u002F cross-cutting | new external dep, public API, or a spec doc | multiple open questions | 1 → 2 → (3) → 4 → 5 → 6 |\n\nPhase 0 (Intake) always runs and is omitted from the mask column above. The\ntie-breaker: anything touching a security trigger (below) or a public API \u002F\ncontract is **at least** standard, regardless of file count.\n\n## The phases\n\nEach phase delegates — it does not do the work inline.\n\n- **0. Intake** — restate the request. For `orch-build-mvp`, read the spec\u002Fdesign\n  doc and extract scope, locked decisions, and a feature list.\n- **1. Research & Reuse** — per `rules\u002Fcommon\u002Fdevelopment-workflow.md`: `gh search repos` \u002F\n  `gh search code`, then Context7 \u002F vendor docs, then package registries, then\n  Exa. Prefer adopting a proven implementation over net-new code.\n- **2. Plan** — delegate to the `planner` agent (or `architect` \u002F\n  `code-architect` for structural decisions). Output a `task_list` ordered as\n  thin vertical slices. → **GATE 1.**\n- **3. Scaffold** — `orch-build-mvp` only: stand up the first end-to-end slice.\n- **4. Implement (TDD)** — drive each task through the `tdd-guide` agent (or the `tdd-workflow` skill):\n  red → green → refactor. Honor the operation's first-move rule.\n- **5. Review** — `code-reviewer` agent \u002F `\u002Fcode-review`. Add `security-reviewer`\n  whenever the diff touches a security trigger (below).\n- **6. Commit** — conventional commits (`feat:` \u002F `fix:` \u002F `refactor:` \u002F …), one\n  per logical chunk. → **GATE 2.**\n\n## The two gates\n\nThis family is **gated, not autonomous**:\n\n1. **GATE 1 — after Plan.** Present the `task_list`; do not write implementation\n   code until the user approves.\n2. **GATE 2 — before Commit.** Present the diff summary and proposed messages;\n   do not commit until the user confirms.\n\nEverything between the gates flows without stopping.\n\n## Agent \u002F command map\n\n| Phase | Primary | Fallback \u002F escalation |\n|-------|---------|----------------------|\n| Intake \u002F understand | `code-explorer` | trace existing paths before a tweak, fix, or refactor |\n| Plan | `planner` | `architect`, `code-architect` for structural calls |\n| Implement | `tdd-guide` (or `tdd-workflow` skill) | `build-error-resolver` \u002F `\u002Fbuild-fix` on build breaks |\n| Review | `code-reviewer` \u002F `\u002Fcode-review` | language reviewer (`python-reviewer`, `typescript-reviewer`, …) |\n| Security | `security-reviewer` | — |\n| MVP inner loop | `\u002Fgan-build \"\u003Cbrief>\" --skip-planner` | drives `gan-generator` → `gan-evaluator`; tune `--max-iterations` \u002F `--pass-threshold` |\n\nMatch the language reviewer to the repo (see the repo's own `CLAUDE.md`).\n\n## Security-review trigger\n\nPull in `security-reviewer` when the diff touches any of: authentication or\nauthorization, user-input handling, database queries, file-system paths,\nexternal API calls, cryptography, or secrets \u002F credentials. (Per `rules\u002Fcommon\u002Fsecurity.md`.)\n\n## Handoff artifacts\n\nThe pipeline carries no hidden state — the planning docs *are* the handoff:\n\n- `task_list` (from Plan) drives the Implement loop.\n- Larger work may also emit PRD \u002F architecture \u002F system_design under the repo's\n  `docs\u002F` per `rules\u002Fcommon\u002Fdevelopment-workflow.md`.\n- Review findings (CRITICAL \u002F HIGH) must be resolved before Gate 2.\n\n## Verification\n\n- size tier was stated and matched the work\n- Gate 1 (plan) and Gate 2 (commit) were both honored\n- `security-reviewer` ran iff a security trigger was touched\n- commits are conventional and scoped to one logical change\n- new \u002F changed behavior has tests; coverage ≥ 80% per `rules\u002Fcommon\u002Ftesting.md`\n","# Orchestrator Pipeline (shared engine)\n\nThe `orch-*` skills are thin wrappers. They do not re-implement any work — they\nclassify the request, choose which phases of *this* pipeline run, and delegate\neach phase to an existing ECC agent or command. This file is that pipeline.\n\n> Invoke an operation skill (`orch-add-feature`, `orch-fix-defect`, …) rather\n> than this engine directly. This file is the reference they point at.\n\n## When to Use\n\n- Loaded indirectly whenever an `orch-*` operation skill runs.\n- Read directly only when adding a new operation to the family or tuning the\n  shared phases, gates, or agent map.\n\n## The operation family\n\n| Skill | Operation | Trigger | First move |\n|-------|-----------|---------|------------|\n| `orch-add-feature` | feature | capability does not exist yet | research + plan a new slice |\n| `orch-change-feature` | tweak | works, but desired behavior differs | amend existing behavior *and its tests* |\n| `orch-fix-defect` | fix | broken; behavior is wrong | reproduce as a failing test, then fix |\n| `orch-refine-code` | refactor | behavior stays, structure improves | restructure while keeping tests green |\n| `orch-build-mvp` | mvp | bootstrap from a design\u002Fspec doc | ingest doc → vertical slices |\n\n> These wrappers **compose** existing ECC commands rather than replace them:\n> `\u002Ffeature-dev`, `\u002Fplan`, `\u002Fcode-review`, `\u002Fbuild-fix`, `\u002Frefactor-clean`, and\n> `\u002Fgan-build`, plus the `tdd-workflow` skill. The orch-* family adds the shared\n> size classifier and the two gates\n> on top of them, so one umbrella covers all five operations consistently.\n\n## Step 0 — Classify size (right-sizing)\n\nCeremony scales to blast radius. Score the request on three signals, take the\n**highest** tier any signal reaches, and state the result in one line so the user\ncan override:\n\n| Tier | Files touched | New dependency \u002F contract | Design ambiguity | Phases that run |\n|------|---------------|---------------------------|------------------|-----------------|\n| trivial | 1, a few lines | none | none — the change is obvious | 4 → 5 → 6 |\n| small | 1 file \u002F 1 function | none | clear once you read the code | (1 light) → 4 → 5 → 6 |\n| standard | 2–5 files | maybe a new internal module | one real choice to make | 1 → 2 → 4 → 5 → 6 |\n| large | many \u002F cross-cutting | new external dep, public API, or a spec doc | multiple open questions | 1 → 2 → (3) → 4 → 5 → 6 |\n\nPhase 0 (Intake) always runs and is omitted from the mask column above. The\ntie-breaker: anything touching a security trigger (below) or a public API \u002F\ncontract is **at least** standard, regardless of file count.\n\n## The phases\n\nEach phase delegates — it does not do the work inline.\n\n- **0. Intake** — restate the request. For `orch-build-mvp`, read the spec\u002Fdesign\n  doc and extract scope, locked decisions, and a feature list.\n- **1. Research & Reuse** — per `rules\u002Fcommon\u002Fdevelopment-workflow.md`: `gh search repos` \u002F\n  `gh search code`, then Context7 \u002F vendor docs, then package registries, then\n  Exa. Prefer adopting a proven implementation over net-new code.\n- **2. Plan** — delegate to the `planner` agent (or `architect` \u002F\n  `code-architect` for structural decisions). Output a `task_list` ordered as\n  thin vertical slices. → **GATE 1.**\n- **3. Scaffold** — `orch-build-mvp` only: stand up the first end-to-end slice.\n- **4. Implement (TDD)** — drive each task through the `tdd-guide` agent (or the `tdd-workflow` skill):\n  red → green → refactor. Honor the operation's first-move rule.\n- **5. Review** — `code-reviewer` agent \u002F `\u002Fcode-review`. Add `security-reviewer`\n  whenever the diff touches a security trigger (below).\n- **6. Commit** — conventional commits (`feat:` \u002F `fix:` \u002F `refactor:` \u002F …), one\n  per logical chunk. → **GATE 2.**\n\n## The two gates\n\nThis family is **gated, not autonomous**:\n\n1. **GATE 1 — after Plan.** Present the `task_list`; do not write implementation\n   code until the user approves.\n2. **GATE 2 — before Commit.** Present the diff summary and proposed messages;\n   do not commit until the user confirms.\n\nEverything between the gates flows without stopping.\n\n## Agent \u002F command map\n\n| Phase | Primary | Fallback \u002F escalation |\n|-------|---------|----------------------|\n| Intake \u002F understand | `code-explorer` | trace existing paths before a tweak, fix, or refactor |\n| Plan | `planner` | `architect`, `code-architect` for structural calls |\n| Implement | `tdd-guide` (or `tdd-workflow` skill) | `build-error-resolver` \u002F `\u002Fbuild-fix` on build breaks |\n| Review | `code-reviewer` \u002F `\u002Fcode-review` | language reviewer (`python-reviewer`, `typescript-reviewer`, …) |\n| Security | `security-reviewer` | — |\n| MVP inner loop | `\u002Fgan-build \"\u003Cbrief>\" --skip-planner` | drives `gan-generator` → `gan-evaluator`; tune `--max-iterations` \u002F `--pass-threshold` |\n\nMatch the language reviewer to the repo (see the repo's own `CLAUDE.md`).\n\n## Security-review trigger\n\nPull in `security-reviewer` when the diff touches any of: authentication or\nauthorization, user-input handling, database queries, file-system paths,\nexternal API calls, cryptography, or secrets \u002F credentials. (Per `rules\u002Fcommon\u002Fsecurity.md`.)\n\n## Handoff artifacts\n\nThe pipeline carries no hidden state — the planning docs *are* the handoff:\n\n- `task_list` (from Plan) drives the Implement loop.\n- Larger work may also emit PRD \u002F architecture \u002F system_design under the repo's\n  `docs\u002F` per `rules\u002Fcommon\u002Fdevelopment-workflow.md`.\n- Review findings (CRITICAL \u002F HIGH) must be resolved before Gate 2.\n\n## Verification\n\n- size tier was stated and matched the work\n- Gate 1 (plan) and Gate 2 (commit) were both honored\n- `security-reviewer` ran iff a security trigger was touched\n- commits are conventional and scoped to one logical change\n- new \u002F changed behavior has tests; coverage ≥ 80% per `rules\u002Fcommon\u002Ftesting.md`\n",{"name":5,"metadata":24,"description":7},{"origin":25},"ECC","main","5d0a87185c0e172c3901e2a6e5916b6d544b8b94","skills\u002Forch-pipeline","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance","https:\u002F\u002Fgithub.com\u002FJunMystery","AI is the typist, I am the architect. Building efficient, secure, and user-centric products through disciplined AI prompt engineering.","2026-11-13 17:41:25",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add JunMystery\u002FAgent-Guidance --skill orch-pipeline",{"tool":39,"command":40},"bunx","bunx skills add JunMystery\u002FAgent-Guidance --skill orch-pipeline",{"tool":42,"command":43},"pnpm","pnpm dlx skills add JunMystery\u002FAgent-Guidance --skill orch-pipeline","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Forch-pipeline\u002FSKILL.md",true,[],[48,54,60,66,72,78],{"skillNo":49,"name":50,"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":51,"categories":52,"keywords":53,"publishedAt":19},"01M79QR1E309VJ6CTQKB32AWWA","zero-trust-architecture-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fzero-trust-architecture-cheat-sheet\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"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":57,"categories":58,"keywords":59,"publishedAt":19},"01M79QQV7GHYR02DYGN41S23WN","xss-filter-evasion-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fxss-filter-evasion-cheat-sheet\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"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":63,"categories":64,"keywords":65,"publishedAt":19},"01M79QQNSN7YB8XB61FFSCS3WH","xs-leaks-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fxs-leaks-cheat-sheet\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"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":69,"categories":70,"keywords":71,"publishedAt":19},"01M79QQHZZJKFDY9132G5A65C2","xpath-injection-prevention-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fxpath-injection-prevention-cheat-sheet\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"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":75,"categories":76,"keywords":77,"publishedAt":19},"01M79QQB9ZSD3DJG8658EHQXR1","xml-security-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fxml-security-cheat-sheet\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"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":81,"categories":82,"keywords":83,"publishedAt":19},"01M79QQ60WKV7PFMXWT9CW8PM6","xml-external-entity-prevention-cheat-sheet","https:\u002F\u002Fgithub.com\u002FJunMystery\u002FAgent-Guidance\u002Fblob\u002Fmain\u002Fskills\u002Fxml-external-entity-prevention-cheat-sheet\u002FSKILL.md",[],[]]