[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79DYVYYQ4172R4A4X68PMMM":3,"skill-same:01M79DYVYYQ4172R4A4X68PMMM":46},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M79DYVYYQ4172R4A4X68PMMM","orchestrate-work",null,"Coordinate or resume repository delivery with a pinned task contract and bounded native workers.","AO-HyS\u002Fdevelopment-system","AO-HyS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F286554351?v=4","01M79DCXZGC6076EH5QATNXCY2","AO HyS","01M79DCY06TSBCJ946VP0BT0RG",0,"MIT","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F1.35.1\u002Fskills\u002Finternal\u002Forchestrate-work\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: orchestrate-work\ndescription: Coordinate or resume repository delivery with a pinned task contract and bounded native workers.\n---\n\n# Orchestrate work\n\nOptimize rápido → bien → barato: deliver the complete usable result, correct\nit with focused evidence, then reduce measured waste. The model selected when\nthe conversation starts owns orchestration and the parent integrates the run.\n\n## Coordinate the full feature\n\nRead [Jev advisory execution](..\u002Fcoding-orchestration\u002Freferences\u002Fjev-advisory.md) once for nontrivial work.\nKeep the selected parent. Use fast research, Astra XHigh planning, a different\nfresh Astra XHigh plan review, bounded writers, independent final review and\nactual behavior evidence. Jev advises at useful routing and correction decisions;\nthe parent records the decision and executes through native tools. Classification\nfailure does not globally block work. Tiny deterministic edits stay direct.\n\n## Pin the target\n\nRecover the objective or ticket, latest correction, exact root, branch or\nrevision, current changes, authorized endpoint and final review surface. Make\ndone observable through required behavior, enumerated checks, resolved findings,\nevidence and the endpoint. Do not restart settled planning or stop at a first\ndraft.\n\nBefore any delegation, pin the execution contract:\n\n- owned files or module surface and one writer;\n- exact instructions by default, or a recorded reason for a bounded outcome exception;\n- expected public behavior and observable values;\n- authorization, stop conditions and terminal state;\n- focused checks, required gates and completion receipt.\n\nRead [the packet fields](..\u002Fcoding-orchestration\u002Freferences\u002Fexecution-contract.md)\nwhen composing a worker handoff; this reference owns the execution protocol.\nUse its ordered actions, expected observations and receipt. Adapt packet size\nand checkpoints to actual capability while preserving the acceptance standard.\nOn model, quota or session change, use\n[execution continuity](..\u002Fcoding-orchestration\u002Freferences\u002Fexecution-continuity.md)\nto preserve work, authorization and evidence and transfer ownership safely.\n\nUse the repository's local canonical recipes and domain architecture. A\nworkflow skill does not migrate forms or other product structures. Use Jev advice without adding global execution gates.\n\n## Dispatch supported workers\n\nChoose currently available workers within the user's provider, capability and\nquota constraints. A roster or profile does not establish runtime identity.\nUse native host tools and completion events; record actual observed identity. An unsupported route remains a capability gap.\nDesign, visual judgment and Computer Use require their actual capabilities;\nreport a gap instead of silently substituting a family.\n\nDelegate only when it shortens the critical path or supplies independent\njudgment. Start parallel packets only for disjoint ownership and explicit\ndependency order. Receive completion events, reuse the same worker for a\nfocused correction, and avoid repeated unchanged status calls or polling\nwithout a new event or observation.\n\nThe parent retains decomposition, integration, conflicts, acceptance and the\nterminal state. A worker packet states the root, revision, owned surface,\nsettled routing, behavior, checks, evidence shape, stop conditions and expected\nreceipt. Preserve unrelated edits.\n\nWriter packets: `Done when:` is executable (command plus expected\nobservation); the writer retries up to 3 times and the coordinator reruns it.\n`Outcome:` is optional.\n\n## Automated tests and evidence\n\nNo automated tests anywhere: do not create, run or restore them; delete them\nwhen found (`check-no-tests` and the guard enforce this). Every task includes\nreal verification without being asked: computer use, browser, and the\nrepository's verification CLI and feature map. Report passed \u002F failed \u002F not\nreached with evidence.\n\n## Headroom transport evidence\n\nHeadroom is an explicit same-account per-invocation option. Keep the existing\nCodex binary and CODEX_HOME, preserve caller arguments, and request lossless,\ncache-conservative operation. Provider cache reuse can still change request\nbytes; do not promise byte identity. Keep native usage from the parent and every\nactual descendant separate from proxy counters, and separate requested model or\ntier from observed identity. Use launch\u002Fcompletion events instead of polling.\nProxy counters and token deltas are descriptive; without complete controlled\nevidence, do not claim Headroom caused savings.\n\n## UI and benchmark evidence\n\nResolve fixture identity, role, organization and useful entities once. A\nneutral browser executor receives exact action inputs and values to record; the\nparent keeps the acceptance rubric and judges the resulting values. Complete\nImpeccable and independent capable critique, resolve material findings, and\nthen capture final media.\n\n## Finish\n\nInspect the integrated diff against the full objective, correct material\nfindings and run the named final checks after changes settle. Report candidate,\nactual model\u002Ftool identity, receipt, checks, links and remaining gaps. Keep\nsource, local runtime, PR, Preview, production and acceptance claims separate.\n\n## Close every task\n\nEvery task that changed files ends with a report:\n\n1. Write the concise packet (`flow-implement\u002Freferences\u002Fcompletion-report.md`):\n   at most 600 characters with the result, then the sections `## Qué se hizo`\n   (real verification marked pasó \u002F falló \u002F no se alcanzó, with evidence),\n   `## Hallazgos` (a mistake seen twice proposed as a hard rule at the highest\n   level: código > lint\u002FCI\u002Fguard > regla\u002Fskill), `## Qué sigue` and\n   `## Detalle`, in that order. No tables unless `\"allowTables\": true`.\n2. Render it with `development-system document --input \u003Cpacket> --json`.\n3. Serve it with working-backwards `reader-live.mjs --tunnel` from a\n   per-report copy directory.\n4. Put the URL in the final answer.\n\nWhen the user asks for the answer in the chat only, write no document and open\nno tunnel. A Stop hook asks once when files changed and no report was produced.\nIf a report is truly not useful, say why in one line.\n\n","# Orchestrate work\n\nOptimize rápido → bien → barato: deliver the complete usable result, correct\nit with focused evidence, then reduce measured waste. The model selected when\nthe conversation starts owns orchestration and the parent integrates the run.\n\n## Coordinate the full feature\n\nRead [Jev advisory execution](..\u002Fcoding-orchestration\u002Freferences\u002Fjev-advisory.md) once for nontrivial work.\nKeep the selected parent. Use fast research, Astra XHigh planning, a different\nfresh Astra XHigh plan review, bounded writers, independent final review and\nactual behavior evidence. Jev advises at useful routing and correction decisions;\nthe parent records the decision and executes through native tools. Classification\nfailure does not globally block work. Tiny deterministic edits stay direct.\n\n## Pin the target\n\nRecover the objective or ticket, latest correction, exact root, branch or\nrevision, current changes, authorized endpoint and final review surface. Make\ndone observable through required behavior, enumerated checks, resolved findings,\nevidence and the endpoint. Do not restart settled planning or stop at a first\ndraft.\n\nBefore any delegation, pin the execution contract:\n\n- owned files or module surface and one writer;\n- exact instructions by default, or a recorded reason for a bounded outcome exception;\n- expected public behavior and observable values;\n- authorization, stop conditions and terminal state;\n- focused checks, required gates and completion receipt.\n\nRead [the packet fields](..\u002Fcoding-orchestration\u002Freferences\u002Fexecution-contract.md)\nwhen composing a worker handoff; this reference owns the execution protocol.\nUse its ordered actions, expected observations and receipt. Adapt packet size\nand checkpoints to actual capability while preserving the acceptance standard.\nOn model, quota or session change, use\n[execution continuity](..\u002Fcoding-orchestration\u002Freferences\u002Fexecution-continuity.md)\nto preserve work, authorization and evidence and transfer ownership safely.\n\nUse the repository's local canonical recipes and domain architecture. A\nworkflow skill does not migrate forms or other product structures. Use Jev advice without adding global execution gates.\n\n## Dispatch supported workers\n\nChoose currently available workers within the user's provider, capability and\nquota constraints. A roster or profile does not establish runtime identity.\nUse native host tools and completion events; record actual observed identity. An unsupported route remains a capability gap.\nDesign, visual judgment and Computer Use require their actual capabilities;\nreport a gap instead of silently substituting a family.\n\nDelegate only when it shortens the critical path or supplies independent\njudgment. Start parallel packets only for disjoint ownership and explicit\ndependency order. Receive completion events, reuse the same worker for a\nfocused correction, and avoid repeated unchanged status calls or polling\nwithout a new event or observation.\n\nThe parent retains decomposition, integration, conflicts, acceptance and the\nterminal state. A worker packet states the root, revision, owned surface,\nsettled routing, behavior, checks, evidence shape, stop conditions and expected\nreceipt. Preserve unrelated edits.\n\nWriter packets: `Done when:` is executable (command plus expected\nobservation); the writer retries up to 3 times and the coordinator reruns it.\n`Outcome:` is optional.\n\n## Automated tests and evidence\n\nNo automated tests anywhere: do not create, run or restore them; delete them\nwhen found (`check-no-tests` and the guard enforce this). Every task includes\nreal verification without being asked: computer use, browser, and the\nrepository's verification CLI and feature map. Report passed \u002F failed \u002F not\nreached with evidence.\n\n## Headroom transport evidence\n\nHeadroom is an explicit same-account per-invocation option. Keep the existing\nCodex binary and CODEX_HOME, preserve caller arguments, and request lossless,\ncache-conservative operation. Provider cache reuse can still change request\nbytes; do not promise byte identity. Keep native usage from the parent and every\nactual descendant separate from proxy counters, and separate requested model or\ntier from observed identity. Use launch\u002Fcompletion events instead of polling.\nProxy counters and token deltas are descriptive; without complete controlled\nevidence, do not claim Headroom caused savings.\n\n## UI and benchmark evidence\n\nResolve fixture identity, role, organization and useful entities once. A\nneutral browser executor receives exact action inputs and values to record; the\nparent keeps the acceptance rubric and judges the resulting values. Complete\nImpeccable and independent capable critique, resolve material findings, and\nthen capture final media.\n\n## Finish\n\nInspect the integrated diff against the full objective, correct material\nfindings and run the named final checks after changes settle. Report candidate,\nactual model\u002Ftool identity, receipt, checks, links and remaining gaps. Keep\nsource, local runtime, PR, Preview, production and acceptance claims separate.\n\n## Close every task\n\nEvery task that changed files ends with a report:\n\n1. Write the concise packet (`flow-implement\u002Freferences\u002Fcompletion-report.md`):\n   at most 600 characters with the result, then the sections `## Qué se hizo`\n   (real verification marked pasó \u002F falló \u002F no se alcanzó, with evidence),\n   `## Hallazgos` (a mistake seen twice proposed as a hard rule at the highest\n   level: código > lint\u002FCI\u002Fguard > regla\u002Fskill), `## Qué sigue` and\n   `## Detalle`, in that order. No tables unless `\"allowTables\": true`.\n2. Render it with `development-system document --input \u003Cpacket> --json`.\n3. Serve it with working-backwards `reader-live.mjs --tunnel` from a\n   per-report copy directory.\n4. Put the URL in the final answer.\n\nWhen the user asks for the answer in the chat only, write no document and open\nno tunnel. A Stop hook asks once when files changed and no report was produced.\nIf a report is truly not useful, say why in one line.\n\n",{"name":5,"description":7},"main","9f5b43aadb1a92441d65e9cb74a584cd6fca62bc","artifacts\u002F1.35.1\u002Fskills\u002Finternal\u002Forchestrate-work","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system","https:\u002F\u002Fgithub.com\u002FAO-HyS","https:\u002F\u002Faohys.net\u002F","Software Boutique, we make your projects come true live. ","2026-11-14 03:17:27",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add AO-HyS\u002Fdevelopment-system --skill orchestrate-work",{"tool":38,"command":39},"bunx","bunx skills add AO-HyS\u002Fdevelopment-system --skill orchestrate-work",{"tool":41,"command":42},"pnpm","pnpm dlx skills add AO-HyS\u002Fdevelopment-system --skill orchestrate-work","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F1.35.1\u002Fskills\u002Finternal\u002Forchestrate-work\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"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},"01M79EQ4BPYQTX8RWN1Y1J2K1F","working-backwards","Define a software feature through PRFAQ and staged documents when the user requests working backwards before coding.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.8.0\u002Fskills\u002Finternal\u002Fworking-backwards\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M79EQ2E8P85Y1Y7VNJZMNEJE","flow-implement","Implement a requested software change through verification, corrections, and its authorized delivery endpoint.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.8.0\u002Fskills\u002Finternal\u002Fflow-implement\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M79EQ0PNMKHPJ78F8WMNX06P","development-steward","Run the scheduled, read-only weekly maintenance review for the six explicitly opted-in repositories and prepare one concise private report for Check-in.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.8.0\u002Fskills\u002Finternal\u002Fdevelopment-steward\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M79EPXJ56MX7955GWP1HD4B0","grill-with-docs","Run one recoverable interview for functional, visual, or mixed software grills; reuse equivalent answers and offer the shared HTML questionnaire.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Finternal\u002Fgrill-with-docs\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M79EPTFPHYEV40ZG52Z0GVS2","global-agent-guardrails","Install, audit, test, or update the Development System's global destructive-command guard for Codex, Claude Code and T3 Code. Use when configuring agent safety hooks or investigating whether dangerous shell operations are blocked.","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Finternal\u002Fglobal-agent-guardrails\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M79EPR0KPHKAFN7V6CEEDR0Y","impeccable","Design or refine frontend UI using project context and a focused design playbook; also handles visual critique and polish.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Fexternal\u002Fimpeccable\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.7.0\u002Fskills\u002Fexternal\u002Fimpeccable\u002FSKILL.md",[],[]]