[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75P09VJB60541ECCTWD96GA":3,"skill-same:01M75P09VJB60541ECCTWD96GA":50},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M75P09VJB60541ECCTWD96GA","autonomous-agent-design",null,"Use when designing or evaluating an autonomous agent workflow. Covers task decomposition, tool scoping, result contracts, failure modes, and the shadow → draft → autonomous maturity sequence.","pixeloven\u002Fcrew","pixeloven","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5751260?v=4","01M75P0048G371B0AWRKQ7FJN8","PixelOven","01M75P0051RK1ZEY0SA9HCMX2Z",1,"MIT","https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-agent-design\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: autonomous-agent-design\ndescription: Use when designing or evaluating an autonomous agent workflow. Covers task decomposition, tool scoping, result contracts, failure modes, and the shadow → draft → autonomous maturity sequence.\ntier: concept\nrequires: []\nexpects-local: [agent-runtime]\n---\n\n## Core design principles\n\n**Behavioral specialization → skills. Operational specialization → agents.** Most specialization pressure resolves into a skill file, not a new agent. Only add an agent when the role genuinely requires a different stance or different tool scope.\n\n**Generic role agents, domain knowledge in skills.** Six role agents (Lead, Triage, Investigator, Researcher, Implementer, Reviewer) cover the work modes. A consumer with a genuinely different work mode adds its own role in its overlay — curation, for instance, is a Librarian in one deployment and nothing at all in another. Specificity flows through skill composition.\n\n**Privilege gradient.** Read-only and draft-only agents cover most work. Implementer is the deliberate write path. Design new capabilities at the lowest privilege level that accomplishes the task.\n\n## Task decomposition\n\nWell-designed autonomous tasks are:\n- **Bounded** — a clear start state, end state, and definition of done\n- **Single-purpose** — one agent, one responsibility per task\n- **Checkable** — acceptance criteria that are machine-verifiable, not \"looks right\"\n- **Recoverable** — a defined action if the task fails (retry, escalate, or skip)\n\nComplex work that spans multiple tasks belongs in a plan, not a single agent invocation.\n\n## Tool scoping\n\nGive each agent the minimum tools needed for its role:\n\n| Agent | Write tools? | Cluster access? |\n|---|---|---|\n| Triage | Labels and comments only | No |\n| Researcher | Research note and issue comments; reply drafts in its response, never posted | No |\n| Investigator | Issues and comments | Read-only |\n| Reviewer | PR comments only | No |\n| Implementer | Code, manifests, PRs | No (via the GitOps controller) |\n| Lead | Issues, plans, dispatch | No |\n\nDon't give an agent write access it doesn't need. A Researcher that can push code is a liability.\n\n## Result contracts\n\nEvery autonomous agent produces a structured result. The result must be:\n- Written to a structured result file at a path the runtime defines\n- Parseable by the orchestrator (Lead or the runtime's exit handler)\n- Sufficient for the next phase to proceed without re-reading the agent's full output\n\nMinimum result fields: `summary`, `status` (success\u002Fpartial\u002Ffailed), list of artifacts produced.\n\n## Failure modes\n\nDesign for three failure classes:\n\n| Class | Handling |\n|---|---|\n| Transient | Retry with backoff — network, rate limit, temporary unavailability |\n| Structural | No retry — escalate to human; task is broken |\n| Success | Proceed to next phase |\n\nThe concrete signaling (exit codes, result-file status fields) is the runtime's contract — see the project's agent-runtime local skill. A common mapping uses 75 \u002F 1 \u002F 0 for transient \u002F structural \u002F success, but the local contract is authoritative.\n\nA task that silently succeeds while producing wrong output is worse than a clean failure. Validate output before signaling success.\n\n## Maturity sequence\n\n**Shadow → Draft → Autonomous.** Never skip stages.\n\n| Stage | Agent behavior | Human role |\n|---|---|---|\n| Shadow | Runs, produces output, takes no action | Reviews output manually |\n| Draft | Produces artifacts (PRs, issue drafts, comments) but does not publish | Reviews and approves before publish |\n| Autonomous | Runs and publishes without review | Reviews asynchronously; intervenes on escalation |\n\nEarn autonomy on narrow, well-understood surfaces before expanding. A reviewer that auto-merges PRs is not a reviewer — it's a rubber stamp.\n\n## Idempotency\n\nAutonomous agents run repeatedly — scheduled sweeps, retries, re-triggers. Every agent action must be safe to run twice:\n- Opening an issue: check for duplicates before filing\n- Writing a vault note: check the substrate first (see the project's knowledge-capture local skill Read Routing) so you don't duplicate prior analysis\n- Applying labels: idempotent by nature\n- Writing code: operate on a fresh branch per task\n","## Core design principles\n\n**Behavioral specialization → skills. Operational specialization → agents.** Most specialization pressure resolves into a skill file, not a new agent. Only add an agent when the role genuinely requires a different stance or different tool scope.\n\n**Generic role agents, domain knowledge in skills.** Six role agents (Lead, Triage, Investigator, Researcher, Implementer, Reviewer) cover the work modes. A consumer with a genuinely different work mode adds its own role in its overlay — curation, for instance, is a Librarian in one deployment and nothing at all in another. Specificity flows through skill composition.\n\n**Privilege gradient.** Read-only and draft-only agents cover most work. Implementer is the deliberate write path. Design new capabilities at the lowest privilege level that accomplishes the task.\n\n## Task decomposition\n\nWell-designed autonomous tasks are:\n- **Bounded** — a clear start state, end state, and definition of done\n- **Single-purpose** — one agent, one responsibility per task\n- **Checkable** — acceptance criteria that are machine-verifiable, not \"looks right\"\n- **Recoverable** — a defined action if the task fails (retry, escalate, or skip)\n\nComplex work that spans multiple tasks belongs in a plan, not a single agent invocation.\n\n## Tool scoping\n\nGive each agent the minimum tools needed for its role:\n\n| Agent | Write tools? | Cluster access? |\n|---|---|---|\n| Triage | Labels and comments only | No |\n| Researcher | Research note and issue comments; reply drafts in its response, never posted | No |\n| Investigator | Issues and comments | Read-only |\n| Reviewer | PR comments only | No |\n| Implementer | Code, manifests, PRs | No (via the GitOps controller) |\n| Lead | Issues, plans, dispatch | No |\n\nDon't give an agent write access it doesn't need. A Researcher that can push code is a liability.\n\n## Result contracts\n\nEvery autonomous agent produces a structured result. The result must be:\n- Written to a structured result file at a path the runtime defines\n- Parseable by the orchestrator (Lead or the runtime's exit handler)\n- Sufficient for the next phase to proceed without re-reading the agent's full output\n\nMinimum result fields: `summary`, `status` (success\u002Fpartial\u002Ffailed), list of artifacts produced.\n\n## Failure modes\n\nDesign for three failure classes:\n\n| Class | Handling |\n|---|---|\n| Transient | Retry with backoff — network, rate limit, temporary unavailability |\n| Structural | No retry — escalate to human; task is broken |\n| Success | Proceed to next phase |\n\nThe concrete signaling (exit codes, result-file status fields) is the runtime's contract — see the project's agent-runtime local skill. A common mapping uses 75 \u002F 1 \u002F 0 for transient \u002F structural \u002F success, but the local contract is authoritative.\n\nA task that silently succeeds while producing wrong output is worse than a clean failure. Validate output before signaling success.\n\n## Maturity sequence\n\n**Shadow → Draft → Autonomous.** Never skip stages.\n\n| Stage | Agent behavior | Human role |\n|---|---|---|\n| Shadow | Runs, produces output, takes no action | Reviews output manually |\n| Draft | Produces artifacts (PRs, issue drafts, comments) but does not publish | Reviews and approves before publish |\n| Autonomous | Runs and publishes without review | Reviews asynchronously; intervenes on escalation |\n\nEarn autonomy on narrow, well-understood surfaces before expanding. A reviewer that auto-merges PRs is not a reviewer — it's a rubber stamp.\n\n## Idempotency\n\nAutonomous agents run repeatedly — scheduled sweeps, retries, re-triggers. Every agent action must be safe to run twice:\n- Opening an issue: check for duplicates before filing\n- Writing a vault note: check the substrate first (see the project's knowledge-capture local skill Read Routing) so you don't duplicate prior analysis\n- Applying labels: idempotent by nature\n- Writing code: operate on a fresh branch per task\n",{"name":5,"tier":24,"requires":25,"description":7,"expects-local":26},"concept",[],[27],"agent-runtime","main","686d42537f9efddb1aeece969b1a4fee2e4d1a88","skills\u002Fautonomous-agent-design",0,"https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew","https:\u002F\u002Fgithub.com\u002Fpixeloven","www.pixeloven.com","2026-11-07 09:18:41",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add pixeloven\u002Fcrew --skill autonomous-agent-design",{"tool":42,"command":43},"bunx","bunx skills add pixeloven\u002Fcrew --skill autonomous-agent-design",{"tool":45,"command":46},"pnpm","pnpm dlx skills add pixeloven\u002Fcrew --skill autonomous-agent-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Fskills\u002Fautonomous-agent-design\u002FSKILL.md",true,[],[51,58,65,72,78,84],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M75P2X72QCY4H2H6C7D3KQ1Z","orchard-gh-runs","Use when reading a failed GitHub Actions run with the gh CLI in this project, before re-running it or reporting a CI failure, so the failing step's log is read instead of the whole run.","https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fproposals\u002Forchard\u002F.agents\u002Fskills\u002Forchard-gh-runs\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M75P2T76B22B314Q3W25GDCK","orchard-gh","Hand-edited after promotion; the learned marker was dropped, so Doctor and check_skills --local can no longer see it.","https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fproposals\u002Finvalid\u002F.agents\u002Fskills\u002Forchard-gh\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"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},"01M75P2Q410WX0H3ZZ61R210F4","demo-topology","Use when exercising the inventory contract fixture so that this fixture description comfortably clears the schema-v2 minimum length.","https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Finventory\u002Fproject\u002F.agents\u002Fskills\u002Fdemo-topology\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":68,"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},"01M75P2KTWZ94KNSKHPGFB6Y6J","helper-jq","https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Finventory\u002Fhome\u002F.codex\u002Fplugins\u002Fcache\u002Facme\u002Fhelper\u002F2.0.0\u002Fskills\u002Fhelper-jq\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":68,"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},"01M75P2GT2CXZR4EZE2DS9GTS7","user-notes","https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Finventory\u002Fhome\u002F.claude\u002Fskills\u002Fuser-notes\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M75P2D61GDSH9NFNEBV4HDBS","toolkit-gh","https:\u002F\u002Fgithub.com\u002Fpixeloven\u002Fcrew\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Finventory\u002Fhome\u002F.claude\u002Fplugins\u002Fcache\u002Facme\u002Ftoolkit\u002F1.2.0\u002Fskills\u002Ftoolkit-gh\u002FSKILL.md",[],[]]