[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79ENVWPF2FXH092Q95TYQCB":3,"skill-same:01M79ENVWPF2FXH092Q95TYQCB":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},"01M79ENVWPF2FXH092Q95TYQCB","flow-implement",null,"Implement a requested software change through verification, corrections, and its authorized delivery endpoint.","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\u002F2.4.0\u002Fskills\u002Finternal\u002Fflow-implement\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: flow-implement\ndescription: Implement a requested software change through verification, corrections, and its authorized delivery endpoint.\n---\n\n# Implement a change\n\nFor non-trivial work, first restate in your own words the user's goal, the\nproblem it solves and how you plan to approach it (`in-your-own-words`); keep\ngoing unless that surfaces a real ambiguity. Recover the requested outcome,\nconstraints, working surface and authorized endpoint. Reuse settled decisions and repository context relevant to this change.\nFollow-up corrections steer the whole task unless the user replaces it. Define\ncompletion by observable behavior and delivery, not by producing a first diff.\n\nFor non-trivial repository work, use `coding-orchestration` for ownership,\ndelegation and verification. Reuse an already selected `orchestrate-work` method\ninstead of adding another execution loop. Clear work proceeds without another\nplanning or approval ceremony. A bounded worker executes its supplied packet.\nUse the [exact-default execution contract](..\u002Fcoding-orchestration\u002Freferences\u002Fexecution-contract.md)\nfor ordered actions, expected observations and receipts. Adapt the packet to\navailable capability without reducing acceptance. Resume model\u002Fquota changes\nthrough its linked continuity handoff, preserving valid evidence and ownership.\n\nFor a stateful UI or routing change, preserve the relevant state owners and\ntransitions: drafts, selection, filters, focus, dismissal and permissions. Check\nthe affected transition early; two static endpoints do not establish continuity.\nFor a visual redesign, recover the approved assets and criteria through\n`design-direction` before implementation. Refinements preserve the current identity.\n\nUse checks that establish the changed behavior and required repository gates.\nAdd no automated tests; real verification observes the changed behavior. A\nregression claim needs evidence that distinguishes the broken and corrected\nbehavior. Preserve command exit codes,\nresolve actual findings and rerun affected checks. Reuse still-valid evidence.\nContinue through authorized implementation, verification and correction without\nasking for another continuation message after the first pass.\n\nFor an on-screen outcome, use the repository's existing product-verification\ncapability to exercise the affected flow. Capture a useful baseline before edits\nwhere possible; missing baseline evidence remains a declared gap. Invoke\n`maintain-product-verification` only when that verification capability itself\nneeds maintenance. When visual quality is acceptance, `design-quality` owns\nindependent critique before `evidence-capture` packages final media. Record the\naffected behavior with useful data and the intended role. A backend change with\nno on-screen outcome uses relevant behavior checks without a visual workflow.\n\nFinish every requested criterion and the installation\u002Fpublication steps already\nauthorized. A missing authorization for a distinct external action does not stop\npreparation or independent work. State partial or blocked work plainly. The final\nresponse covers the complete outcome, checks, remaining gaps, candidate and\nrequested review link; code, Preview and production are separate claims.\n\nFor a requested standalone completion report or a durable media package, read\n[completion-report.md](references\u002Fcompletion-report.md).\n\n## Before integrating a PR\n\n1. Write or refresh the `system-recap` block from the diff; update\n   `docs\u002Farchitecture\u002Fprimitives.json` in the same PR when a primitive changes.\n2. Review the finished PR once, never each push. One independent Sol 6.1 High\n   review of the ready head; a docs-only or small low-risk PR skips it. A\n   second round only for a blocking finding (security, authorization, data\n   loss, money), reviewing only the fix diff. Non-blocking findings are fixed\n   without re-review or recorded as follow-ups. No third round without the\n   operator.\n3. Codex review: `development-system pr-review-status \u003Cpr>`. `pending` → run\n   it with `--request` once and wait (T3 `watch_pull_request` when available);\n   `findings` → fix or answer each one in its thread. Ask again at most once\n   after the fixes; after that second review, answer its findings, push\n   only their fixes and integrate on `budget-spent`, naming the later fix\n   commits in the report. Integrate on `no-findings` or `budget-spent` only. `unavailable` is\n   not approval.\n\n## Leave nothing running\n\nStop every dev server, model server or watcher you started before the final\nreport: kill the PIDs you launched, never by name, and never another thread's.\n\n## Friction\n\nBefore the report, look back at the session for paper cuts: slow or flaky\nstartup, missing test data, a workaround for a missing tool, a doc that was\nwrong. Record each with\n`development-system friction add --id \u003Cslug> --incident \u003Cref> --evidence \u003Cref> --repository \u003Crepo> --summary \u003Ctext>`.\nFrictions feed the Steward; confirmed root causes still go to `mistake add`.\n\n## Close every task\n\nEvery task that changed files ends with a report:\n\n1. Write the concise packet (`references\u002Fcompletion-report.md`). Its\n   Markdown opens with the sections Qué se hizo, Hallazgos, Qué sigue, Detalle\n   in that order (English: What was done, Findings, What's next, Detail);\n   the command rejects other shapes and tables without `allowTables`.\n2. Render it with `development-system document --input \u003Cpacket> --json`.\n3. Deliver it durably: in T3, render the page in the owning thread; otherwise\n   give the persistent `htmlPath` the command returns.\n4. A working-backwards `reader-live.mjs --tunnel` link is optional; when you\n   add one, state its expiry next to the durable delivery, never instead of it.\n\nA Stop hook asks once when files changed and no report was produced. If a\nreport is truly not useful, say why in one line. When the user asks for the\nanswer in the chat only, produce no document and no tunnel.\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## Spec and ticket handoff\n\nUse [the shared definition contract](..\u002Fcoding-orchestration\u002Freferences\u002Fspec-ticket-contract.md)\nfor stable criteria, linked tickets, dependencies, rules and required evidence.\nPreserve the selected parent. With an OpenAI parent, Opus 5.5 authors the\nplan and a fresh independent Sol 6.1 High reviews it; with an Anthropic parent,\nSol 6.1 High authors and a fresh independent Opus 5.5 reviews it. Use the\nexisting read-only routes and honor provider restrictions. Missing cross-family\ncontrast stays not reached; unresolved blocking objections prevent acceptance.\nFast researchers supply bounded source facts.\nWhen implementation is authorized, use coding-orchestration and its advisory\nJev recipe across the complete feature, including nonvisual behavior. Retrieve\nall tickets linked by the spec; preserve settled decisions across threads.\n","# Implement a change\n\nFor non-trivial work, first restate in your own words the user's goal, the\nproblem it solves and how you plan to approach it (`in-your-own-words`); keep\ngoing unless that surfaces a real ambiguity. Recover the requested outcome,\nconstraints, working surface and authorized endpoint. Reuse settled decisions and repository context relevant to this change.\nFollow-up corrections steer the whole task unless the user replaces it. Define\ncompletion by observable behavior and delivery, not by producing a first diff.\n\nFor non-trivial repository work, use `coding-orchestration` for ownership,\ndelegation and verification. Reuse an already selected `orchestrate-work` method\ninstead of adding another execution loop. Clear work proceeds without another\nplanning or approval ceremony. A bounded worker executes its supplied packet.\nUse the [exact-default execution contract](..\u002Fcoding-orchestration\u002Freferences\u002Fexecution-contract.md)\nfor ordered actions, expected observations and receipts. Adapt the packet to\navailable capability without reducing acceptance. Resume model\u002Fquota changes\nthrough its linked continuity handoff, preserving valid evidence and ownership.\n\nFor a stateful UI or routing change, preserve the relevant state owners and\ntransitions: drafts, selection, filters, focus, dismissal and permissions. Check\nthe affected transition early; two static endpoints do not establish continuity.\nFor a visual redesign, recover the approved assets and criteria through\n`design-direction` before implementation. Refinements preserve the current identity.\n\nUse checks that establish the changed behavior and required repository gates.\nAdd no automated tests; real verification observes the changed behavior. A\nregression claim needs evidence that distinguishes the broken and corrected\nbehavior. Preserve command exit codes,\nresolve actual findings and rerun affected checks. Reuse still-valid evidence.\nContinue through authorized implementation, verification and correction without\nasking for another continuation message after the first pass.\n\nFor an on-screen outcome, use the repository's existing product-verification\ncapability to exercise the affected flow. Capture a useful baseline before edits\nwhere possible; missing baseline evidence remains a declared gap. Invoke\n`maintain-product-verification` only when that verification capability itself\nneeds maintenance. When visual quality is acceptance, `design-quality` owns\nindependent critique before `evidence-capture` packages final media. Record the\naffected behavior with useful data and the intended role. A backend change with\nno on-screen outcome uses relevant behavior checks without a visual workflow.\n\nFinish every requested criterion and the installation\u002Fpublication steps already\nauthorized. A missing authorization for a distinct external action does not stop\npreparation or independent work. State partial or blocked work plainly. The final\nresponse covers the complete outcome, checks, remaining gaps, candidate and\nrequested review link; code, Preview and production are separate claims.\n\nFor a requested standalone completion report or a durable media package, read\n[completion-report.md](references\u002Fcompletion-report.md).\n\n## Before integrating a PR\n\n1. Write or refresh the `system-recap` block from the diff; update\n   `docs\u002Farchitecture\u002Fprimitives.json` in the same PR when a primitive changes.\n2. Review the finished PR once, never each push. One independent Sol 6.1 High\n   review of the ready head; a docs-only or small low-risk PR skips it. A\n   second round only for a blocking finding (security, authorization, data\n   loss, money), reviewing only the fix diff. Non-blocking findings are fixed\n   without re-review or recorded as follow-ups. No third round without the\n   operator.\n3. Codex review: `development-system pr-review-status \u003Cpr>`. `pending` → run\n   it with `--request` once and wait (T3 `watch_pull_request` when available);\n   `findings` → fix or answer each one in its thread. Ask again at most once\n   after the fixes; after that second review, answer its findings, push\n   only their fixes and integrate on `budget-spent`, naming the later fix\n   commits in the report. Integrate on `no-findings` or `budget-spent` only. `unavailable` is\n   not approval.\n\n## Leave nothing running\n\nStop every dev server, model server or watcher you started before the final\nreport: kill the PIDs you launched, never by name, and never another thread's.\n\n## Friction\n\nBefore the report, look back at the session for paper cuts: slow or flaky\nstartup, missing test data, a workaround for a missing tool, a doc that was\nwrong. Record each with\n`development-system friction add --id \u003Cslug> --incident \u003Cref> --evidence \u003Cref> --repository \u003Crepo> --summary \u003Ctext>`.\nFrictions feed the Steward; confirmed root causes still go to `mistake add`.\n\n## Close every task\n\nEvery task that changed files ends with a report:\n\n1. Write the concise packet (`references\u002Fcompletion-report.md`). Its\n   Markdown opens with the sections Qué se hizo, Hallazgos, Qué sigue, Detalle\n   in that order (English: What was done, Findings, What's next, Detail);\n   the command rejects other shapes and tables without `allowTables`.\n2. Render it with `development-system document --input \u003Cpacket> --json`.\n3. Deliver it durably: in T3, render the page in the owning thread; otherwise\n   give the persistent `htmlPath` the command returns.\n4. A working-backwards `reader-live.mjs --tunnel` link is optional; when you\n   add one, state its expiry next to the durable delivery, never instead of it.\n\nA Stop hook asks once when files changed and no report was produced. If a\nreport is truly not useful, say why in one line. When the user asks for the\nanswer in the chat only, produce no document and no tunnel.\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## Spec and ticket handoff\n\nUse [the shared definition contract](..\u002Fcoding-orchestration\u002Freferences\u002Fspec-ticket-contract.md)\nfor stable criteria, linked tickets, dependencies, rules and required evidence.\nPreserve the selected parent. With an OpenAI parent, Opus 5.5 authors the\nplan and a fresh independent Sol 6.1 High reviews it; with an Anthropic parent,\nSol 6.1 High authors and a fresh independent Opus 5.5 reviews it. Use the\nexisting read-only routes and honor provider restrictions. Missing cross-family\ncontrast stays not reached; unresolved blocking objections prevent acceptance.\nFast researchers supply bounded source facts.\nWhen implementation is authorized, use coding-orchestration and its advisory\nJev recipe across the complete feature, including nonvisual behavior. Retrieve\nall tickets linked by the spec; preserve settled decisions across threads.\n",{"name":5,"description":7},"main","9f5b43aadb1a92441d65e9cb74a584cd6fca62bc","artifacts\u002F2.4.0\u002Fskills\u002Finternal\u002Fflow-implement","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 flow-implement",{"tool":38,"command":39},"bunx","bunx skills add AO-HyS\u002Fdevelopment-system --skill flow-implement",{"tool":41,"command":42},"pnpm","pnpm dlx skills add AO-HyS\u002Fdevelopment-system --skill flow-implement","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.4.0\u002Fskills\u002Finternal\u002Fflow-implement\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcompletion-report.md","REFERENCE","参考文档",4143,"https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.4.0\u002Fskills\u002Finternal\u002Fflow-implement\u002Freferences\u002Fcompletion-report.md",[53,60,65,72,79,86],{"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":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":62,"categories":63,"keywords":64,"publishedAt":19},"01M79EQ2E8P85Y1Y7VNJZMNEJE","https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.8.0\u002Fskills\u002Finternal\u002Fflow-implement\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},"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":90,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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",[],[]]