[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79E3BQVEMSDG72FNT5KFSM3":3,"skill-same:01M79E3BQVEMSDG72FNT5KFSM3":52},{"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},"01M79E3BQVEMSDG72FNT5KFSM3","coding-orchestration",null,"Orchestrate non-trivial software work in Git repositories with bounded Codex agents, one writer by default, explicit lane closure, and measurable outcomes. Keep trivial localized work on the parent.","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\u002F1.5.10\u002Fadapters\u002Fcodex\u002Fcoding-orchestration\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: coding-orchestration\ndescription: Orchestrate non-trivial software work in Git repositories with bounded Codex agents, one writer by default, explicit lane closure, and measurable outcomes. Keep trivial localized work on the parent.\n---\n\n# Coding Orchestration\n\nThe parent owns decomposition, integration, conflicts, verification, and the requested end state. Optimize for verified delivery, not agent count or first-diff speed.\n\n## Choose direct, sequential, or delegated execution\n\n1. Read repository instructions and lock the smallest executable slice.\n2. Keep trivial, localized, reversible edits and short diagnostics on the parent.\n3. Delegate only when work is genuinely independent, crosses specialties, or an independent risk review materially improves confidence.\n4. Use direct or sequential execution when multi-agent v2 is unavailable, unhelpful, or would cost more coordination than the task.\n5. Never spawn agents merely to restate a prompt, duplicate discovery, or edit a few obvious lines.\n\n## Bound concurrency and ownership\n\n- Use at most three concurrent subagents in the normal path. Exceed that only with a recorded, task-specific reason.\n- Keep one writer for every non-trivial slice. Multiple writers require disjoint files or packages and explicit ownership.\n- Keep the parent useful while agents run. Prefer one event-driven wait when a result is the last blocker; do not poll with repeated list or wait calls.\n- Reuse a stable task name with a follow-up message instead of spawning replacement agents for corrections.\n- Keep spawned depth at one. Workers must not create more workers.\n\n## Route by evidence and risk\n\nUse the installed custom agent whose name matches the work: discovery and mapping, focused implementation, backend, UI design, browser QA, performance, security, review, tests, or release. The custom agent TOML is the source of truth for model and reasoning.\n\nRun only the review or QA lane justified by the changed risk. UI interactions need browser evidence; security boundaries need security review; a tiny deterministic code edit does not need a generic reviewer swarm. A full suite requires explicit authorization for that run.\n\nEach delegated prompt includes one objective, exact ownership, absolute worktree and branch, applicable instructions, whether edits are allowed, expected evidence, and escalation conditions.\n\n## Close every lane\n\nBefore the parent reports completion, every planned lane must have exactly one terminal state:\n\n- `integrated`: useful work or evidence was incorporated;\n- `discarded`: output was intentionally rejected with a reason;\n- `blocked-with-owner`: a named owner and concrete blocker remain;\n- `not-started`: the planned lane was deliberately unnecessary.\n\nAn open, merely idle, or unaccounted lane makes the orchestration run incomplete. Delegation never expands implementation, tracker, merge, release, production, migration, or paid-service authorization.\n\n## Measure the natural-work pilot\n\nRecord direct, sequential, and delegated runs so a correct zero-agent decision counts as evidence. At the first checkpoint after five non-trivial runs or five calendar days, compare the candidate period with historical comparable runs; do not repeat product work solely to create an A\u002FB test.\n\nRetain the policy only when verified outcomes do not regress and at least one coordination signal improves without another regressing: waits, open lanes, or correction\u002Frework. Otherwise adjust the policy or collect more evidence. Do not claim causal savings from uncontrolled history.\n\nFeed at most one first action per repository into Check-in, labeled `mobile`, `computer`, or `no-action`. The weekly Development Steward and on-demand Check-in surface the pilot; raw session evidence remains private.\n\n## Final evidence\n\nReport the chosen mode, agents used, terminal lane states, focused checks, review\u002FQA rationale, waits, corrections, and verified outcome. Missing runtime or model evidence remains unresolved rather than inferred.\n","# Coding Orchestration\n\nThe parent owns decomposition, integration, conflicts, verification, and the requested end state. Optimize for verified delivery, not agent count or first-diff speed.\n\n## Choose direct, sequential, or delegated execution\n\n1. Read repository instructions and lock the smallest executable slice.\n2. Keep trivial, localized, reversible edits and short diagnostics on the parent.\n3. Delegate only when work is genuinely independent, crosses specialties, or an independent risk review materially improves confidence.\n4. Use direct or sequential execution when multi-agent v2 is unavailable, unhelpful, or would cost more coordination than the task.\n5. Never spawn agents merely to restate a prompt, duplicate discovery, or edit a few obvious lines.\n\n## Bound concurrency and ownership\n\n- Use at most three concurrent subagents in the normal path. Exceed that only with a recorded, task-specific reason.\n- Keep one writer for every non-trivial slice. Multiple writers require disjoint files or packages and explicit ownership.\n- Keep the parent useful while agents run. Prefer one event-driven wait when a result is the last blocker; do not poll with repeated list or wait calls.\n- Reuse a stable task name with a follow-up message instead of spawning replacement agents for corrections.\n- Keep spawned depth at one. Workers must not create more workers.\n\n## Route by evidence and risk\n\nUse the installed custom agent whose name matches the work: discovery and mapping, focused implementation, backend, UI design, browser QA, performance, security, review, tests, or release. The custom agent TOML is the source of truth for model and reasoning.\n\nRun only the review or QA lane justified by the changed risk. UI interactions need browser evidence; security boundaries need security review; a tiny deterministic code edit does not need a generic reviewer swarm. A full suite requires explicit authorization for that run.\n\nEach delegated prompt includes one objective, exact ownership, absolute worktree and branch, applicable instructions, whether edits are allowed, expected evidence, and escalation conditions.\n\n## Close every lane\n\nBefore the parent reports completion, every planned lane must have exactly one terminal state:\n\n- `integrated`: useful work or evidence was incorporated;\n- `discarded`: output was intentionally rejected with a reason;\n- `blocked-with-owner`: a named owner and concrete blocker remain;\n- `not-started`: the planned lane was deliberately unnecessary.\n\nAn open, merely idle, or unaccounted lane makes the orchestration run incomplete. Delegation never expands implementation, tracker, merge, release, production, migration, or paid-service authorization.\n\n## Measure the natural-work pilot\n\nRecord direct, sequential, and delegated runs so a correct zero-agent decision counts as evidence. At the first checkpoint after five non-trivial runs or five calendar days, compare the candidate period with historical comparable runs; do not repeat product work solely to create an A\u002FB test.\n\nRetain the policy only when verified outcomes do not regress and at least one coordination signal improves without another regressing: waits, open lanes, or correction\u002Frework. Otherwise adjust the policy or collect more evidence. Do not claim causal savings from uncontrolled history.\n\nFeed at most one first action per repository into Check-in, labeled `mobile`, `computer`, or `no-action`. The weekly Development Steward and on-demand Check-in surface the pilot; raw session evidence remains private.\n\n## Final evidence\n\nReport the chosen mode, agents used, terminal lane states, focused checks, review\u002FQA rationale, waits, corrections, and verified outcome. Missing runtime or model evidence remains unresolved rather than inferred.\n",{"name":5,"description":7},"main","9f5b43aadb1a92441d65e9cb74a584cd6fca62bc","artifacts\u002F1.5.10\u002Fadapters\u002Fcodex\u002Fcoding-orchestration","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 coding-orchestration",{"tool":38,"command":39},"bunx","bunx skills add AO-HyS\u002Fdevelopment-system --skill coding-orchestration",{"tool":41,"command":42},"pnpm","pnpm dlx skills add AO-HyS\u002Fdevelopment-system --skill coding-orchestration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F1.5.10\u002Fadapters\u002Fcodex\u002Fcoding-orchestration\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",225,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F1.5.10\u002Fadapters\u002Fcodex\u002Fcoding-orchestration\u002Fagents\u002Fopenai.yaml",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"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},"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":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":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},"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":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},"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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",[],[]]