[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79ENQHKN9799476GZ4CWC2B":3,"skill-same:01M79ENQHKN9799476GZ4CWC2B":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},"01M79ENQHKN9799476GZ4CWC2B","cross-review",null,"Open a visible T3 review thread where a second model (Astra Extra High for a Claude author, Opus for a Codex author) reviews a plan or change, then go back and forth in that thread until both accept the same version. The owner can join the thread and steer. Use only when the operator asks for it (\u002Fcross-review or an explicit request); never start one on your own.","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\u002Fcross-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cross-review\ndescription: Open a visible T3 review thread where a second model (Astra Extra High for a Claude author, Opus for a Codex author) reviews a plan or change, then go back and forth in that thread until both accept the same version. The owner can join the thread and steer. Use only when the operator asks for it (\u002Fcross-review or an explicit request); never start one on your own.\n---\n\n# Cross review\n\nThe author keeps writing; the reviewer only proposes. The conversation lives in\none ordinary T3 thread the owner can open, read and write in: the owner asked\nfor one continuous visible thread, so this is the explicit exception to fresh\nreview rounds. It does not replace the Sol and Codex reviews the global review\nbudget requires for a PR: one Sol review of the finished PR (none for docs-only\nor small low-risk PRs) and Codex asked at most twice. The reviewer\nmodel is the owner's choice: Astra Extra High for a Claude author, Opus for a\nCodex author; the owner may name another.\n\n## Start\n\n1. Freeze the artifact: a file under\n   `$HOME\u002F.development-system\u002Fprivate\u002Fcross-review\u002F\u003Cid>\u002F` (plan, list or contract)\n   or a PR head SHA. Compute its SHA-256.\n2. Record `\u003Cid>.json` there: author thread id, artifact path and hash, round 0.\n3. Check `t3_thread_list` for an existing review thread for this id before\n   launching; a launch has no retry key.\n4. `t3_thread_launch` in the same project and workspace as the author\n   (`workspaceStrategy` of the author's checkout; never a new worktree), with:\n   - model: `codex` \u002F `gpt-6-astra`, `reasoningEffort: xhigh` for a Claude\n     author; `claudeAgent` \u002F `claude-opus-5-5` for a Codex author;\n   - first message: the owner's goal in your own words, the artifact path and\n     hash, the evidence it rests on, \"read only: do not edit, commit, switch\n     branches or start servers\", and the answer format below.\n5. Save the returned thread id and run id; link the thread to the owner as\n   `[title](t3-thread:\u002F\u002Fv1\u002F\u003CthreadId>)`.\n\nReviewer answer format: restate the owner's goal, then numbered findings\n(R\u003Cround>-H\u003Cn>) each with severity (blocking, important, minor), evidence and a\nconcrete change; end with exactly `VEREDICTO: SIN BLOQUEANTES` or\n`VEREDICTO: CON BLOQUEANTES`, and when there are no blockers, whether it accepts\nthe artifact with that hash.\n\n## Each round\n\n1. Wait for the recorded run with `t3_thread_wait` and that `runId`. Timeout,\n   interruption or failure leave the round pending; never read it as acceptance.\n2. Read the whole answer with `t3_thread_read` (page with `afterPosition`,\n   recover truncated text with `itemId`\u002F`textOffset`).\n3. If the owner wrote in the thread since the last round, the owner's message\n   wins: reconcile it before answering the reviewer.\n4. For every finding: fix the artifact, or reject it with evidence. Save the new\n   version, compute its hash, add a response table at the end.\n5. Send the response with `t3_thread_send`, mode `queue`, a stable\n   `clientRequestId` (`\u003Cid>-r\u003Cround>`), the new path and hash, and the request to\n   verify each fix and look for regressions. Record the new `messageId`\u002F`runId`.\n\n## Close\n\n- **Agreed:** the reviewer says `SIN BLOQUEANTES` and accepts the current hash.\n  The author uses exactly that version.\n- **Disagreement:** five rounds without agreement, or a finding the author\n  rejects twice. Report both positions to the owner; this is never approval.\n\nReport the rounds, the accepted hash and the thread link. The review validates a\ndesign; the work it describes is still pending until done and verified.\n","# Cross review\n\nThe author keeps writing; the reviewer only proposes. The conversation lives in\none ordinary T3 thread the owner can open, read and write in: the owner asked\nfor one continuous visible thread, so this is the explicit exception to fresh\nreview rounds. It does not replace the Sol and Codex reviews the global review\nbudget requires for a PR: one Sol review of the finished PR (none for docs-only\nor small low-risk PRs) and Codex asked at most twice. The reviewer\nmodel is the owner's choice: Astra Extra High for a Claude author, Opus for a\nCodex author; the owner may name another.\n\n## Start\n\n1. Freeze the artifact: a file under\n   `$HOME\u002F.development-system\u002Fprivate\u002Fcross-review\u002F\u003Cid>\u002F` (plan, list or contract)\n   or a PR head SHA. Compute its SHA-256.\n2. Record `\u003Cid>.json` there: author thread id, artifact path and hash, round 0.\n3. Check `t3_thread_list` for an existing review thread for this id before\n   launching; a launch has no retry key.\n4. `t3_thread_launch` in the same project and workspace as the author\n   (`workspaceStrategy` of the author's checkout; never a new worktree), with:\n   - model: `codex` \u002F `gpt-6-astra`, `reasoningEffort: xhigh` for a Claude\n     author; `claudeAgent` \u002F `claude-opus-5-5` for a Codex author;\n   - first message: the owner's goal in your own words, the artifact path and\n     hash, the evidence it rests on, \"read only: do not edit, commit, switch\n     branches or start servers\", and the answer format below.\n5. Save the returned thread id and run id; link the thread to the owner as\n   `[title](t3-thread:\u002F\u002Fv1\u002F\u003CthreadId>)`.\n\nReviewer answer format: restate the owner's goal, then numbered findings\n(R\u003Cround>-H\u003Cn>) each with severity (blocking, important, minor), evidence and a\nconcrete change; end with exactly `VEREDICTO: SIN BLOQUEANTES` or\n`VEREDICTO: CON BLOQUEANTES`, and when there are no blockers, whether it accepts\nthe artifact with that hash.\n\n## Each round\n\n1. Wait for the recorded run with `t3_thread_wait` and that `runId`. Timeout,\n   interruption or failure leave the round pending; never read it as acceptance.\n2. Read the whole answer with `t3_thread_read` (page with `afterPosition`,\n   recover truncated text with `itemId`\u002F`textOffset`).\n3. If the owner wrote in the thread since the last round, the owner's message\n   wins: reconcile it before answering the reviewer.\n4. For every finding: fix the artifact, or reject it with evidence. Save the new\n   version, compute its hash, add a response table at the end.\n5. Send the response with `t3_thread_send`, mode `queue`, a stable\n   `clientRequestId` (`\u003Cid>-r\u003Cround>`), the new path and hash, and the request to\n   verify each fix and look for regressions. Record the new `messageId`\u002F`runId`.\n\n## Close\n\n- **Agreed:** the reviewer says `SIN BLOQUEANTES` and accepts the current hash.\n  The author uses exactly that version.\n- **Disagreement:** five rounds without agreement, or a finding the author\n  rejects twice. Report both positions to the owner; this is never approval.\n\nReport the rounds, the accepted hash and the thread link. The review validates a\ndesign; the work it describes is still pending until done and verified.\n",{"name":5,"description":7},"main","9f5b43aadb1a92441d65e9cb74a584cd6fca62bc","artifacts\u002F2.4.0\u002Fskills\u002Finternal\u002Fcross-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 cross-review",{"tool":38,"command":39},"bunx","bunx skills add AO-HyS\u002Fdevelopment-system --skill cross-review",{"tool":41,"command":42},"pnpm","pnpm dlx skills add AO-HyS\u002Fdevelopment-system --skill cross-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAO-HyS\u002Fdevelopment-system\u002Fblob\u002Fmain\u002Fartifacts\u002F2.4.0\u002Fskills\u002Finternal\u002Fcross-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",[],[]]