[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72WCKYRVKRTZWZH7HTCC2H7":3,"skill-same:01M72WCKYRVKRTZWZH7HTCC2H7":73},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M72WCKYRVKRTZWZH7HTCC2H7","adlc-workstream",null,"Plan grounded long-running workstreams with Codex goal-managed execution.","davidvictor\u002Fadlc-skills","davidvictor","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6255259?v=4","01M72WAWPEPQ8YW16DPGZJJRFX","David Victor","01M72WAWQK88GKM5JD1YTYR56P",1,"MIT","https:\u002F\u002Fgithub.com\u002Fdavidvictor\u002Fadlc-skills\u002Fblob\u002Fmain\u002Fskills\u002Fadlc\u002Fadlc-workstream\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: adlc-workstream\ndescription: Plan grounded long-running workstreams with Codex goal-managed execution.\n---\n\n# ADLC Workstream\n\nUse this when an epic is too large for one plan execution pass and needs durable Codex goal context, milestone sequencing, step cards, Kanban state, and execution handoffs.\n\n## Process\n\n1. Resolve effective ADLC paths from `.adlc\u002Fconfig.yaml`; use `adlc resolve-config` when the CLI is available.\n2. Ground the epic in live repo evidence, relevant interview specs, existing plans, architecture, rules, and user constraints before creating steps.\n3. For long-running or multi-sprint execution, create or attach the active Codex goal and record the goal objective in `WORKSTREAM.md`.\n4. Inspect the dirty tree before delegation. Commit small coherent existing work first; stop and ask for large, mixed, or unrelated dirty trees.\n5. Create or update `paths.workstreams\u002F\u003Cslug>\u002F` with a workstream overview, Kanban board, evidence log, decision log, milestone cards, step cards, and Codex handoff.\n6. Decompose the epic as `workstream -> milestone -> step -> task`. Each step should be one reviewable, commit-capable slice with a bounded write scope.\n7. Move each step through `ready -> build -> review -> fix -> test -> commit -> done`, with review\u002Ffix\u002Ftest loops handled autonomously unless a human-gated blocker is explicit.\n8. Assign each step an execution lane: `coordinator`, `worker`, `parallel`, or `human-gated`.\n9. For Codex handoff, include the exact ADLC workstream\u002Fstep path, bounded write scope, verification commands, expected gate outputs, and goal-continuity instructions.\n10. Keep blocked decisions explicit and avoid inventing dependencies that are not supported by evidence.\n\n## Rules\n\n- Workstreams coordinate execution; they do not replace `adlc-plan`, `adlc-implement`, `adlc-verify`, `adlc-review`, or `adlc-commit`.\n- Codex goals manage the active long-running objective. ADLC artifacts remain the detailed source of truth for scope, state, evidence, and decisions.\n- Interview specs remain binding clarification artifacts. Carry their non-goals, decision boundaries, pressure-pass findings, and acceptance criteria into milestones and step cards.\n- Every milestone must have a concrete outcome, dependency notes, exit criteria, and release or rollback considerations when relevant.\n- Every step must have evidence, scope, acceptance criteria, verification, commit checkpoint, and next-stage rules.\n- Split any step whose acceptance criteria span unrelated subsystems, cannot be verified in one pass, or would create a mixed commit.\n- Review, fix, and test gates are autonomous by default. A failed gate with actionable code, docs, tests, rules, or security findings should route to the next ADLC gate or fixer, then return to review\u002Fverify without operator approval.\n- Use human-blocked only for explicit human decisions, credentials or external accounts, destructive or production operations, legal\u002Fsecurity sign-off, scope or product ambiguity, or a user-requested approval point.\n- Do not encode an ordinary post-fix `review-required` handoff as a human blocker. Create or advance an autonomous review\u002Fverify gate, or mark the fix complete with the downstream gate pending.\n- Do not create hidden automation. ADLC exports work; execution lanes perform it through their normal Codex lifecycle.\n- Do not stop global worker services while stopping a task. Gateway, daemon, scheduler, or service shutdown requires an explicit operator request.\n- Long-running state must live in ADLC artifacts and Codex goal status, not chat memory.\n\n## Output\n\nReport the workstream root, Codex goal status, milestone count, step count, execution lanes, blocked decisions, current Kanban state, and the next runnable Codex step.\n","# ADLC Workstream\n\nUse this when an epic is too large for one plan execution pass and needs durable Codex goal context, milestone sequencing, step cards, Kanban state, and execution handoffs.\n\n## Process\n\n1. Resolve effective ADLC paths from `.adlc\u002Fconfig.yaml`; use `adlc resolve-config` when the CLI is available.\n2. Ground the epic in live repo evidence, relevant interview specs, existing plans, architecture, rules, and user constraints before creating steps.\n3. For long-running or multi-sprint execution, create or attach the active Codex goal and record the goal objective in `WORKSTREAM.md`.\n4. Inspect the dirty tree before delegation. Commit small coherent existing work first; stop and ask for large, mixed, or unrelated dirty trees.\n5. Create or update `paths.workstreams\u002F\u003Cslug>\u002F` with a workstream overview, Kanban board, evidence log, decision log, milestone cards, step cards, and Codex handoff.\n6. Decompose the epic as `workstream -> milestone -> step -> task`. Each step should be one reviewable, commit-capable slice with a bounded write scope.\n7. Move each step through `ready -> build -> review -> fix -> test -> commit -> done`, with review\u002Ffix\u002Ftest loops handled autonomously unless a human-gated blocker is explicit.\n8. Assign each step an execution lane: `coordinator`, `worker`, `parallel`, or `human-gated`.\n9. For Codex handoff, include the exact ADLC workstream\u002Fstep path, bounded write scope, verification commands, expected gate outputs, and goal-continuity instructions.\n10. Keep blocked decisions explicit and avoid inventing dependencies that are not supported by evidence.\n\n## Rules\n\n- Workstreams coordinate execution; they do not replace `adlc-plan`, `adlc-implement`, `adlc-verify`, `adlc-review`, or `adlc-commit`.\n- Codex goals manage the active long-running objective. ADLC artifacts remain the detailed source of truth for scope, state, evidence, and decisions.\n- Interview specs remain binding clarification artifacts. Carry their non-goals, decision boundaries, pressure-pass findings, and acceptance criteria into milestones and step cards.\n- Every milestone must have a concrete outcome, dependency notes, exit criteria, and release or rollback considerations when relevant.\n- Every step must have evidence, scope, acceptance criteria, verification, commit checkpoint, and next-stage rules.\n- Split any step whose acceptance criteria span unrelated subsystems, cannot be verified in one pass, or would create a mixed commit.\n- Review, fix, and test gates are autonomous by default. A failed gate with actionable code, docs, tests, rules, or security findings should route to the next ADLC gate or fixer, then return to review\u002Fverify without operator approval.\n- Use human-blocked only for explicit human decisions, credentials or external accounts, destructive or production operations, legal\u002Fsecurity sign-off, scope or product ambiguity, or a user-requested approval point.\n- Do not encode an ordinary post-fix `review-required` handoff as a human blocker. Create or advance an autonomous review\u002Fverify gate, or mark the fix complete with the downstream gate pending.\n- Do not create hidden automation. ADLC exports work; execution lanes perform it through their normal Codex lifecycle.\n- Do not stop global worker services while stopping a task. Gateway, daemon, scheduler, or service shutdown requires an explicit operator request.\n- Long-running state must live in ADLC artifacts and Codex goal status, not chat memory.\n\n## Output\n\nReport the workstream root, Codex goal status, milestone count, step count, execution lanes, blocked decisions, current Kanban state, and the next runnable Codex step.\n",{"name":5,"description":7},"main","27efc3f4f9a6f42ba03eb184b1ef1485db380275","skills\u002Fadlc\u002Fadlc-workstream",0,"https:\u002F\u002Fgithub.com\u002Fdavidvictor\u002Fadlc-skills","https:\u002F\u002Fgithub.com\u002Fdavidvictor","https:\u002F\u002Fmdrn.love","Design engineer building AI products and creative tools. Available to hire. Working with @the-pick-ai and Metamodern Studio.","2026-06-02 23:49:55",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add davidvictor\u002Fadlc-skills --skill adlc-workstream",{"tool":39,"command":40},"bunx","bunx skills add davidvictor\u002Fadlc-skills --skill adlc-workstream",{"tool":42,"command":43},"pnpm","pnpm dlx skills add davidvictor\u002Fadlc-skills --skill adlc-workstream","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavidvictor\u002Fadlc-skills\u002Fblob\u002Fmain\u002Fskills\u002Fadlc\u002Fadlc-workstream\u002FSKILL.md",true,[47,53,57,61,65,69],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"agents\u002Fopenai.yaml","REFERENCE","参考文档",179,"https:\u002F\u002Fgithub.com\u002Fdavidvictor\u002Fadlc-skills\u002Fblob\u002Fmain\u002Fskills\u002Fadlc\u002Fadlc-workstream\u002Fagents\u002Fopenai.yaml",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002FWORKSTREAM-CONTRACT.md",4129,"https:\u002F\u002Fgithub.com\u002Fdavidvictor\u002Fadlc-skills\u002Fblob\u002Fmain\u002Fskills\u002Fadlc\u002Fadlc-workstream\u002Freferences\u002FWORKSTREAM-CONTRACT.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"templates\u002FCODEX-HANDOFF.md",1370,"https:\u002F\u002Fgithub.com\u002Fdavidvictor\u002Fadlc-skills\u002Fblob\u002Fmain\u002Fskills\u002Fadlc\u002Fadlc-workstream\u002Ftemplates\u002FCODEX-HANDOFF.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"templates\u002FMILESTONE.md",374,"https:\u002F\u002Fgithub.com\u002Fdavidvictor\u002Fadlc-skills\u002Fblob\u002Fmain\u002Fskills\u002Fadlc\u002Fadlc-workstream\u002Ftemplates\u002FMILESTONE.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"templates\u002FSTEP.md",607,"https:\u002F\u002Fgithub.com\u002Fdavidvictor\u002Fadlc-skills\u002Fblob\u002Fmain\u002Fskills\u002Fadlc\u002Fadlc-workstream\u002Ftemplates\u002FSTEP.md",{"path":70,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":71,"sourceHtmlUrl":72},"templates\u002FWORKSTREAM.md",1037,"https:\u002F\u002Fgithub.com\u002Fdavidvictor\u002Fadlc-skills\u002Fblob\u002Fmain\u002Fskills\u002Fadlc\u002Fadlc-workstream\u002Ftemplates\u002FWORKSTREAM.md",[74,81,88,95,102,109],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M72WCPHGCYM5VJD7SC6R8YW0","adlc","Initialize or refresh ADLC project context and config artifacts.","https:\u002F\u002Fgithub.com\u002Fdavidvictor\u002Fadlc-skills\u002Fblob\u002Fmain\u002Fskills\u002Fadlc\u002Fadlc\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M72WCH4ZGT3TS8Z62F8RMJYR","adlc-verify","Verify implementation completeness against ADLC plans, rules, and repo behavior.","https:\u002F\u002Fgithub.com\u002Fdavidvictor\u002Fadlc-skills\u002Fblob\u002Fmain\u002Fskills\u002Fadlc\u002Fadlc-verify\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M72WCF7BK99TN2493EKYZ1FM","adlc-security-checklist","Run a read-only ADLC security gate for secrets, trust boundaries, and unsafe workflow changes.","https:\u002F\u002Fgithub.com\u002Fdavidvictor\u002Fadlc-skills\u002Fblob\u002Fmain\u002Fskills\u002Fadlc\u002Fadlc-security-checklist\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M72WCCV5DK5QGVF5HARKBF66","adlc-rules","Capture ADLC project rules, area conventions, and durable operating constraints.","https:\u002F\u002Fgithub.com\u002Fdavidvictor\u002Fadlc-skills\u002Fblob\u002Fmain\u002Fskills\u002Fadlc\u002Fadlc-rules\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M72WC9Y3AGTRQFEDKEXPCK3V","adlc-rules-check","Run a read-only ADLC rules compliance gate for plans, diffs, or release candidates.","https:\u002F\u002Fgithub.com\u002Fdavidvictor\u002Fadlc-skills\u002Fblob\u002Fmain\u002Fskills\u002Fadlc\u002Fadlc-rules-check\u002FSKILL.md",[],[],{"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":115,"publishedAt":19},"01M72WC761ZBSMN80RTTENJ60P","adlc-roadmap","Create or maintain ADLC roadmap artifacts for milestones, sequencing, and long-range direction.","https:\u002F\u002Fgithub.com\u002Fdavidvictor\u002Fadlc-skills\u002Fblob\u002Fmain\u002Fskills\u002Fadlc\u002Fadlc-roadmap\u002FSKILL.md",[],[]]