[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79DDDR5P5697YZX2X38BJCY":3,"skill-same:01M79DDDR5P5697YZX2X38BJCY":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},"01M79DDDR5P5697YZX2X38BJCY","flow-code-review",null,"Review a branch or diff through independent Standards and Spec lanes, then validate, deduplicate, and rank actionable findings by risk. Use when drive-development-flow selects review or after flow-implement completes.","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\u002F0.2.0\u002Fskills\u002Finternal\u002Fflow-code-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: flow-code-review\ndescription: Review a branch or diff through independent Standards and Spec lanes, then validate, deduplicate, and rank actionable findings by risk. Use when drive-development-flow selects review or after flow-implement completes.\n---\n\n# Flow Code Review\n\nReview the diff along two independent axes:\n\n- **Standards**: repository instructions, documented conventions, security, correctness, maintainability, and relevant smell heuristics.\n- **Spec**: requested behavior, missing or partial requirements, unrequested scope, and behavior that looks implemented incorrectly.\n\nKeep the inspections blind to each other. The parent owns the final integrated judgment.\n\n## 1. Pin the fixed point\n\nUse the fixed point supplied by the user. Otherwise infer it from repository evidence:\n\n1. current pull request base;\n2. configured upstream;\n3. remote default branch;\n4. `origin\u002Fdevelop`, then `origin\u002Fmain`, then `origin\u002Fmaster`, when exactly one is sensible.\n\nAsk only when the evidence leaves materially different comparisons. Confirm the ref resolves and the three-dot diff is non-empty before starting review lanes.\n\n## 2. Identify sources\n\nFind the spec from issue references, a user-supplied path, or matching files under `docs\u002F`, `specs\u002F`, or `.scratch\u002F`. Follow `docs\u002Fagents\u002Fissue-tracker.md` when external tracker data is required. If there is no spec, skip that lane and say so.\n\nFind applicable `AGENTS.md`, `CONTRIBUTING.md`, coding standards, domain docs, and validation rules. Repo rules override generic heuristics.\n\nThe Standards lane may flag these only as judgment calls when repo policy does not endorse them:\n\n- mysterious names;\n- duplicated code;\n- feature envy;\n- data clumps;\n- primitive obsession;\n- repeated switches;\n- shotgun surgery;\n- divergent change;\n- speculative generality;\n- message chains;\n- middle men;\n- refused bequests.\n\nSkip anything deterministic tooling already enforces unless the tool is absent or its result is failing.\n\n## 3. Run two blind lanes\n\nInside a Git repository, load `coding-orchestration`. Use its installed `reviewer` role through the active harness when independent delegation materially improves the review. Do not hardcode a generic agent type or harness tool name.\n\nGive each lane only the fixed diff packet, commit list, and its own sources. Do not give either lane the other report.\n\nStandards brief:\n\n> Cite actionable correctness, regression, security, maintainability, or documented-standard problems by tight file and line. Distinguish hard violations from smell judgments. Omit style-only findings already enforced by tooling. Return under 400 words.\n\nSpec brief:\n\n> Cite missing or partial requirements, scope creep, and incorrectly implemented requested behavior by tight file and line plus the supporting spec text. Return under 400 words.\n\nIf delegation is not useful or unavailable, run the passes sequentially with separate evidence notes.\n\n## 4. Integrate and verify\n\nThe parent must:\n\n1. Validate each candidate against the actual diff and source.\n2. Merge duplicates and resolve contradictions while retaining the producing axis.\n3. Rank findings by user impact and regression risk.\n4. Put actionable findings first with tight file and line references.\n5. Inspect the real command, log, route, or runtime behavior behind any material green-check claim.\n6. End with a short Standards\u002FSpec status and residual verification gaps.\n\nDo not edit product code unless the user asked to address findings. If nothing actionable remains, say so plainly.\n","# Flow Code Review\n\nReview the diff along two independent axes:\n\n- **Standards**: repository instructions, documented conventions, security, correctness, maintainability, and relevant smell heuristics.\n- **Spec**: requested behavior, missing or partial requirements, unrequested scope, and behavior that looks implemented incorrectly.\n\nKeep the inspections blind to each other. The parent owns the final integrated judgment.\n\n## 1. Pin the fixed point\n\nUse the fixed point supplied by the user. Otherwise infer it from repository evidence:\n\n1. current pull request base;\n2. configured upstream;\n3. remote default branch;\n4. `origin\u002Fdevelop`, then `origin\u002Fmain`, then `origin\u002Fmaster`, when exactly one is sensible.\n\nAsk only when the evidence leaves materially different comparisons. Confirm the ref resolves and the three-dot diff is non-empty before starting review lanes.\n\n## 2. Identify sources\n\nFind the spec from issue references, a user-supplied path, or matching files under `docs\u002F`, `specs\u002F`, or `.scratch\u002F`. Follow `docs\u002Fagents\u002Fissue-tracker.md` when external tracker data is required. If there is no spec, skip that lane and say so.\n\nFind applicable `AGENTS.md`, `CONTRIBUTING.md`, coding standards, domain docs, and validation rules. Repo rules override generic heuristics.\n\nThe Standards lane may flag these only as judgment calls when repo policy does not endorse them:\n\n- mysterious names;\n- duplicated code;\n- feature envy;\n- data clumps;\n- primitive obsession;\n- repeated switches;\n- shotgun surgery;\n- divergent change;\n- speculative generality;\n- message chains;\n- middle men;\n- refused bequests.\n\nSkip anything deterministic tooling already enforces unless the tool is absent or its result is failing.\n\n## 3. Run two blind lanes\n\nInside a Git repository, load `coding-orchestration`. Use its installed `reviewer` role through the active harness when independent delegation materially improves the review. Do not hardcode a generic agent type or harness tool name.\n\nGive each lane only the fixed diff packet, commit list, and its own sources. Do not give either lane the other report.\n\nStandards brief:\n\n> Cite actionable correctness, regression, security, maintainability, or documented-standard problems by tight file and line. Distinguish hard violations from smell judgments. Omit style-only findings already enforced by tooling. Return under 400 words.\n\nSpec brief:\n\n> Cite missing or partial requirements, scope creep, and incorrectly implemented requested behavior by tight file and line plus the supporting spec text. Return under 400 words.\n\nIf delegation is not useful or unavailable, run the passes sequentially with separate evidence notes.\n\n## 4. Integrate and verify\n\nThe parent must:\n\n1. Validate each candidate against the actual diff and source.\n2. Merge duplicates and resolve contradictions while retaining the producing axis.\n3. Rank findings by user impact and regression risk.\n4. Put actionable findings first with tight file and line references.\n5. Inspect the real command, log, route, or runtime behavior behind any material green-check claim.\n6. End with a short Standards\u002FSpec status and residual verification gaps.\n\nDo not edit product code unless the user asked to address findings. If nothing actionable remains, say so plainly.\n",{"name":5,"description":7},"main","9f5b43aadb1a92441d65e9cb74a584cd6fca62bc","artifacts\u002F0.2.0\u002Fskills\u002Finternal\u002Fflow-code-review","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-code-review",{"tool":38,"command":39},"bunx","bunx skills add AO-HyS\u002Fdevelopment-system --skill flow-code-review",{"tool":41,"command":42},"pnpm","pnpm dlx skills add AO-HyS\u002Fdevelopment-system --skill flow-code-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F0.2.0\u002Fskills\u002Finternal\u002Fflow-code-review\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",[],[]]