[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79DPQZ7NJSYFJJZNAYHB5BQ":3,"skill-same:01M79DPQZ7NJSYFJJZNAYHB5BQ":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},"01M79DPQZ7NJSYFJJZNAYHB5BQ","orchestrate-work",null,"Coordinate or resume repository delivery with the selected model and the host's native agents.","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\u002F1.18.0\u002Fskills\u002Finternal\u002Forchestrate-work\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: orchestrate-work\ndescription: Coordinate or resume repository delivery with the selected model and the host's native agents.\n---\n\n# Orchestrate work\n\nOptimize **rápido → bien → barato**: time to the complete usable result,\nincluding corrections. The selected conversation model owns orchestration.\nUse this as the execution method; reuse settled planning and applicable repo\nrules instead of restarting a lifecycle or loading a second coordination stack.\n\n## Establish the current target\n\nRecover the requested outcome, latest corrections, authorized endpoint, exact\nworking root, branch and current changes. Verify a linked PR against Git;\nthread titles and sidebar associations can be stale. Preserve existing work.\nMake done observable: required behavior, relevant validation, material findings\nresolved, and the authorized delivery endpoint reached. Continue those steps\nwithout stopping for approval of an unrequested first-draft checkpoint.\nFor a broad assignment, keep a short requirement → implementation → verification\nrecord. Examples emphasized in a follow-up do not silently replace its scope.\n\nRead only the references that decide this task. For visual implementation,\nopen the approved images and design decisions before delegating; a URL nobody\ncan retrieve is not a usable design handoff. Resolve missing assets early while\ncontinuing independent work.\n\n## Use the host's agents\n\nChoose currently available models and tools within the user's provider,\ncapability and quota constraints. A recommended roster is optional guidance,\nnot a replacement parent or evidence of runtime identity. No particular model,\npaid plan or OpenAI access is required by this skill. Never silently substitute\nan excluded provider. Match vision\u002Fbrowser assignments to actual tool access.\n\nDelegate when it shortens the critical path or supplies needed independent\njudgment. In OpenCode, use native `task` subagents: `general` for writable work,\n`explore` for a bounded code question, and `scout` for external research when\navailable. Other hosts use their equivalent native tools. Do not build another\nagent launcher or launch nested CLIs merely to reproduce these capabilities.\nIf delegation is unavailable, report that and continue useful work directly.\n\nGive each worker a compact packet:\n\n- Exact root and relevant revision; owned files or surface.\n- Required behavior, existing contracts, and necessary source\u002Fasset pointers.\n- Constraints, focused checks, expected output, and any known blocker.\n- Routing and planning are settled; execute this packet, preserve others' work,\n  and report changed files, check results and remaining uncertainty.\n\nStart independent packets together where the host supports it. Keep one writer\nper surface; the parent owns shared contracts, integration and conflicts.\nReceive completion events rather than repeatedly polling or requesting status.\nReuse a worker for a focused correction when its context remains useful.\n\nSpecify outcomes more strongly than implementation guesses. Check consequential\nprovider\u002FAPI limits before prescribing an approach. A worker should challenge\na conflicting plan with concrete evidence, rather than reproduce its false\nassumptions in code and permissive mocks.\n\n## Integrate, verify, finish\n\nInspect the integrated diff against the whole requested behavior. Choose the\nsmallest adequate existing checks and required repository gates. Add a test\nonly when it catches a named failure and helps correct it. Preserve check exit\ncodes; output filtering must not conceal failure. Repeat checks only for a\nrelevant change, failure or unresolved concern. A mocked service does not prove\nthe real provider accepts the operation.\n\nFor UI work, verify the affected interaction with useful data and the intended\nrole. Check retained selection, edit\u002Fcancel behavior and permission transitions\nwhen the change affects them. Use isolated fixtures; clean up authorized test\nmutations without overwriting concurrent user changes.\n\nWhen visual fidelity is part of acceptance, use the approved direction and the\navailable Impeccable\u002Fdesign skills selectively. Have an independent agent with\nvision critique the rendered result; correct material findings before final\nevidence. If that capability is missing, state the acceptance gap. A screenshot\nalone is not a critique, and a text-only model must not claim to have seen it.\n\nCapture final evidence on the validated candidate, after data and layout settle.\nUse actual mobile dimensions for mobile claims. Stable capture steps can run as\na script; they need no model inference per click or frame. Share only curated\nmedia and reports, never auth state, secrets or entire session folders.\n\nFinish at the authorized endpoint. Distinguish implemented code, verified\nbehavior, PR, Preview and production. Report the exact candidate, working\nlinks, checks and remaining gaps. For a separate review, leave a short handoff\nwith goal, root, revision, diff, verification receipts and known limitations;\ndo not export the whole conversation by default.\n","# Orchestrate work\n\nOptimize **rápido → bien → barato**: time to the complete usable result,\nincluding corrections. The selected conversation model owns orchestration.\nUse this as the execution method; reuse settled planning and applicable repo\nrules instead of restarting a lifecycle or loading a second coordination stack.\n\n## Establish the current target\n\nRecover the requested outcome, latest corrections, authorized endpoint, exact\nworking root, branch and current changes. Verify a linked PR against Git;\nthread titles and sidebar associations can be stale. Preserve existing work.\nMake done observable: required behavior, relevant validation, material findings\nresolved, and the authorized delivery endpoint reached. Continue those steps\nwithout stopping for approval of an unrequested first-draft checkpoint.\nFor a broad assignment, keep a short requirement → implementation → verification\nrecord. Examples emphasized in a follow-up do not silently replace its scope.\n\nRead only the references that decide this task. For visual implementation,\nopen the approved images and design decisions before delegating; a URL nobody\ncan retrieve is not a usable design handoff. Resolve missing assets early while\ncontinuing independent work.\n\n## Use the host's agents\n\nChoose currently available models and tools within the user's provider,\ncapability and quota constraints. A recommended roster is optional guidance,\nnot a replacement parent or evidence of runtime identity. No particular model,\npaid plan or OpenAI access is required by this skill. Never silently substitute\nan excluded provider. Match vision\u002Fbrowser assignments to actual tool access.\n\nDelegate when it shortens the critical path or supplies needed independent\njudgment. In OpenCode, use native `task` subagents: `general` for writable work,\n`explore` for a bounded code question, and `scout` for external research when\navailable. Other hosts use their equivalent native tools. Do not build another\nagent launcher or launch nested CLIs merely to reproduce these capabilities.\nIf delegation is unavailable, report that and continue useful work directly.\n\nGive each worker a compact packet:\n\n- Exact root and relevant revision; owned files or surface.\n- Required behavior, existing contracts, and necessary source\u002Fasset pointers.\n- Constraints, focused checks, expected output, and any known blocker.\n- Routing and planning are settled; execute this packet, preserve others' work,\n  and report changed files, check results and remaining uncertainty.\n\nStart independent packets together where the host supports it. Keep one writer\nper surface; the parent owns shared contracts, integration and conflicts.\nReceive completion events rather than repeatedly polling or requesting status.\nReuse a worker for a focused correction when its context remains useful.\n\nSpecify outcomes more strongly than implementation guesses. Check consequential\nprovider\u002FAPI limits before prescribing an approach. A worker should challenge\na conflicting plan with concrete evidence, rather than reproduce its false\nassumptions in code and permissive mocks.\n\n## Integrate, verify, finish\n\nInspect the integrated diff against the whole requested behavior. Choose the\nsmallest adequate existing checks and required repository gates. Add a test\nonly when it catches a named failure and helps correct it. Preserve check exit\ncodes; output filtering must not conceal failure. Repeat checks only for a\nrelevant change, failure or unresolved concern. A mocked service does not prove\nthe real provider accepts the operation.\n\nFor UI work, verify the affected interaction with useful data and the intended\nrole. Check retained selection, edit\u002Fcancel behavior and permission transitions\nwhen the change affects them. Use isolated fixtures; clean up authorized test\nmutations without overwriting concurrent user changes.\n\nWhen visual fidelity is part of acceptance, use the approved direction and the\navailable Impeccable\u002Fdesign skills selectively. Have an independent agent with\nvision critique the rendered result; correct material findings before final\nevidence. If that capability is missing, state the acceptance gap. A screenshot\nalone is not a critique, and a text-only model must not claim to have seen it.\n\nCapture final evidence on the validated candidate, after data and layout settle.\nUse actual mobile dimensions for mobile claims. Stable capture steps can run as\na script; they need no model inference per click or frame. Share only curated\nmedia and reports, never auth state, secrets or entire session folders.\n\nFinish at the authorized endpoint. Distinguish implemented code, verified\nbehavior, PR, Preview and production. Report the exact candidate, working\nlinks, checks and remaining gaps. For a separate review, leave a short handoff\nwith goal, root, revision, diff, verification receipts and known limitations;\ndo not export the whole conversation by default.\n",{"name":5,"description":7},"main","9f5b43aadb1a92441d65e9cb74a584cd6fca62bc","artifacts\u002F1.18.0\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\u002F1.18.0\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",[],[]]