[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79DF8NQFWT7QPNKK7QMTSSR":3,"skill-same:01M79DF8NQFWT7QPNKK7QMTSSR":62},{"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},"01M79DF8NQFWT7QPNKK7QMTSSR","work-multiple",null,"Execute several authorized software tickets through conflict-aware parallel worktrees and one integrated candidate. Use only when the user explicitly invokes $work-multiple or clearly says to work multiple tickets in parallel; never infer activation from ticket count, project size, or urgency.","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\u002F0.9.0\u002Fskills\u002Finternal\u002Fwork-multiple\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: work-multiple\ndescription: Execute several authorized software tickets through conflict-aware parallel worktrees and one integrated candidate. Use only when the user explicitly invokes $work-multiple or clearly says to work multiple tickets in parallel; never infer activation from ticket count, project size, or urgency.\n---\n\n# Work Multiple\n\nOptimize for one constant goal:\n\n> Deliver correct functionality to the authorized state as fast as possible,\n> with useful quality, the lowest measured cost, and the least complexity.\n\nThis skill is an explicit execution mode, not a router. If the current request\ndoes not clearly authorize multiple-ticket execution, stop without creating\nworktrees or agents.\n\n## Freeze the run\n\nRequire at least two authorized tickets. For each ticket, record:\n\n- its acceptance criterion;\n- owned product and code surfaces;\n- declared blockers;\n- whether it changes behavior or only mechanical text\u002Fstyle;\n- the publication and production boundary.\n\nDo not create, expand, reorder, merge, release, or deploy tickets unless that\noperation is separately authorized.\n\n## Build the smallest lane graph\n\n1. Put tickets sharing a product surface, file surface, or dependency chain in\n   one sequential lane.\n2. Put only disjoint lanes in separate registered Git worktrees.\n3. Use no more writers than disjoint lanes.\n4. Start disjoint lanes together. Run tickets inside a lane sequentially.\n5. Keep the parent responsible for conflicts and one integrated candidate.\n6. Create one review and one pull request, when publication is authorized.\n\nBefore starting writers, capture each lane's absolute worktree path, branch,\nHEAD, and `git worktree list --porcelain` evidence.\n\n## Route for speed\n\n- Keep trivial mapping and integration on the parent.\n- Use `fast_implementer` on Spark Low for exact bounded implementation.\n- If Spark is unavailable or fails the same bounded packet twice, use the\n  fastest currently validated implementation route; do not wait for Luna or\n  escalate to Sol merely because it is familiar.\n- Use discovery or QA agents only when their parallel work saves more time than\n  their startup and context cost.\n- Record actual harness runtime worker, model, reasoning, session, and event\n  metadata. A planned model or `inherit` is not execution evidence.\n\n## Run the fixed implementation loop\n\nFor each ticket:\n\n1. implement the smallest complete behavior;\n2. run the affected linter or typecheck when it is locally available and fast;\n3. run only focused local tests that prove the changed contract;\n4. run React Doctor or the applicable Impeccable CLI only when React,\n   interaction, or visual implementation changed and the repo exposes it;\n5. never run a full repository suite unless the user requests it for this run.\n\nAfter integration, run two independent code reviews concurrently. Give both\nreviewers only the fixed diff, acceptance criteria, and their own review brief.\nDo not give either reviewer the implementation narrative or the other report.\nResolve blocker\u002Fhigh findings before continuing.\n\n## Select manual QA by value\n\nRun `node scripts\u002Fselect-qa.mjs --input \u003Cchange.json>` from this skill.\n\n- No UI change: manual UI QA is not applicable.\n- Label, copy, icon, or obvious style-only change with no behavioral risk:\n  skip manual UI QA.\n- Interactive behavior, navigation, mutation, responsive behavior, a meaningful\n  regression, or a critical user flow: run one direct manual acceptance flow.\n- If the useful flow no longer exists, verify the closest observable\n  acceptance criterion instead of recreating obsolete ceremony.\n\nRecord the decision and one-sentence reason. Do not cite route, destination, or\ntest totals as quality.\n\n## Measure the goal\n\nStart timing when execution begins and stop `functionalEvidenceMs` when every\nacceptance criterion has observable evidence. Review, PR, CI, deployment, and\npromotion are separate timings.\n\nFinalize a private run record, then execute:\n\n```sh\nnode scripts\u002Fevaluate-goal.mjs --input \u002Fprivate\u002Fpath\u002Frun.json\n```\n\nThe evaluator reports correctness, quality, speed, cost, and simplicity as\nseparate axes:\n\n- tiny work meets the speed goal only at five minutes or less;\n- five to ten minutes is an exception, not success;\n- above ten minutes stops the run for process audit;\n- multiple work needs a comparable sequential baseline to prove speedup;\n- missing comparable authoritative price evidence makes the cost goal\n  unproven; token counts remain resource evidence, not price;\n- any missing acceptance proof, failed relevant check, non-independent review,\n  or unresolved blocker\u002Fhigh finding fails quality.\n\nDo not create a composite score. Return `met`, `missed`, or `unproven` with the\nexact failed or unavailable axes.\n","# Work Multiple\n\nOptimize for one constant goal:\n\n> Deliver correct functionality to the authorized state as fast as possible,\n> with useful quality, the lowest measured cost, and the least complexity.\n\nThis skill is an explicit execution mode, not a router. If the current request\ndoes not clearly authorize multiple-ticket execution, stop without creating\nworktrees or agents.\n\n## Freeze the run\n\nRequire at least two authorized tickets. For each ticket, record:\n\n- its acceptance criterion;\n- owned product and code surfaces;\n- declared blockers;\n- whether it changes behavior or only mechanical text\u002Fstyle;\n- the publication and production boundary.\n\nDo not create, expand, reorder, merge, release, or deploy tickets unless that\noperation is separately authorized.\n\n## Build the smallest lane graph\n\n1. Put tickets sharing a product surface, file surface, or dependency chain in\n   one sequential lane.\n2. Put only disjoint lanes in separate registered Git worktrees.\n3. Use no more writers than disjoint lanes.\n4. Start disjoint lanes together. Run tickets inside a lane sequentially.\n5. Keep the parent responsible for conflicts and one integrated candidate.\n6. Create one review and one pull request, when publication is authorized.\n\nBefore starting writers, capture each lane's absolute worktree path, branch,\nHEAD, and `git worktree list --porcelain` evidence.\n\n## Route for speed\n\n- Keep trivial mapping and integration on the parent.\n- Use `fast_implementer` on Spark Low for exact bounded implementation.\n- If Spark is unavailable or fails the same bounded packet twice, use the\n  fastest currently validated implementation route; do not wait for Luna or\n  escalate to Sol merely because it is familiar.\n- Use discovery or QA agents only when their parallel work saves more time than\n  their startup and context cost.\n- Record actual harness runtime worker, model, reasoning, session, and event\n  metadata. A planned model or `inherit` is not execution evidence.\n\n## Run the fixed implementation loop\n\nFor each ticket:\n\n1. implement the smallest complete behavior;\n2. run the affected linter or typecheck when it is locally available and fast;\n3. run only focused local tests that prove the changed contract;\n4. run React Doctor or the applicable Impeccable CLI only when React,\n   interaction, or visual implementation changed and the repo exposes it;\n5. never run a full repository suite unless the user requests it for this run.\n\nAfter integration, run two independent code reviews concurrently. Give both\nreviewers only the fixed diff, acceptance criteria, and their own review brief.\nDo not give either reviewer the implementation narrative or the other report.\nResolve blocker\u002Fhigh findings before continuing.\n\n## Select manual QA by value\n\nRun `node scripts\u002Fselect-qa.mjs --input \u003Cchange.json>` from this skill.\n\n- No UI change: manual UI QA is not applicable.\n- Label, copy, icon, or obvious style-only change with no behavioral risk:\n  skip manual UI QA.\n- Interactive behavior, navigation, mutation, responsive behavior, a meaningful\n  regression, or a critical user flow: run one direct manual acceptance flow.\n- If the useful flow no longer exists, verify the closest observable\n  acceptance criterion instead of recreating obsolete ceremony.\n\nRecord the decision and one-sentence reason. Do not cite route, destination, or\ntest totals as quality.\n\n## Measure the goal\n\nStart timing when execution begins and stop `functionalEvidenceMs` when every\nacceptance criterion has observable evidence. Review, PR, CI, deployment, and\npromotion are separate timings.\n\nFinalize a private run record, then execute:\n\n```sh\nnode scripts\u002Fevaluate-goal.mjs --input \u002Fprivate\u002Fpath\u002Frun.json\n```\n\nThe evaluator reports correctness, quality, speed, cost, and simplicity as\nseparate axes:\n\n- tiny work meets the speed goal only at five minutes or less;\n- five to ten minutes is an exception, not success;\n- above ten minutes stops the run for process audit;\n- multiple work needs a comparable sequential baseline to prove speedup;\n- missing comparable authoritative price evidence makes the cost goal\n  unproven; token counts remain resource evidence, not price;\n- any missing acceptance proof, failed relevant check, non-independent review,\n  or unresolved blocker\u002Fhigh finding fails quality.\n\nDo not create a composite score. Return `met`, `missed`, or `unproven` with the\nexact failed or unavailable axes.\n",{"name":5,"description":7},"main","9f5b43aadb1a92441d65e9cb74a584cd6fca62bc","artifacts\u002F0.9.0\u002Fskills\u002Finternal\u002Fwork-multiple","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 work-multiple",{"tool":38,"command":39},"bunx","bunx skills add AO-HyS\u002Fdevelopment-system --skill work-multiple",{"tool":41,"command":42},"pnpm","pnpm dlx skills add AO-HyS\u002Fdevelopment-system --skill work-multiple","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F0.9.0\u002Fskills\u002Finternal\u002Fwork-multiple\u002FSKILL.md",true,[46,52,58],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",246,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F0.9.0\u002Fskills\u002Finternal\u002Fwork-multiple\u002Fagents\u002Fopenai.yaml",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"scripts\u002Fevaluate-goal.mjs","SCRIPT","脚本",7203,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F0.9.0\u002Fskills\u002Finternal\u002Fwork-multiple\u002Fscripts\u002Fevaluate-goal.mjs",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"scripts\u002Fselect-qa.mjs",2280,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F0.9.0\u002Fskills\u002Finternal\u002Fwork-multiple\u002Fscripts\u002Fselect-qa.mjs",[63,70,77,84,91,98],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"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":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"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":78,"name":79,"nameZh":6,"description":80,"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},"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":102,"licenseFileUrl":103,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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",[],[]]