[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CQ2XHVX3F1GT08CCCY225D":3,"skill-same:01M7CQ2XHVX3F1GT08CCCY225D":45},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7CQ2XHVX3F1GT08CCCY225D","frame",null,"Surface the open questions before planning a multi-branch feature, and shape the feature plan mode drafts. Use before entering plan mode for work that obviously won't fit in one branch and one pull request -- never for a change that already does.","urban233\u002FCanon","urban233","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F81388165?v=4","01M7CPZG1XX0BZ1KTRAJWTGWFH","Martin Urban","01M7CPZG2JPZEX3EJEG98XGTA7",1,"BSD-3-Clause","https:\u002F\u002Fgithub.com\u002Furban233\u002FCanon\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex\u002Fskills\u002Fframe\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: frame\ndescription: Surface the open questions before planning a multi-branch feature, and shape the feature plan mode drafts. Use before entering plan mode for work that obviously won't fit in one branch and one pull request -- never for a change that already does.\n---\n\n# Frame\n\nThis runs once, before any branch exists for the feature. Framing decides\nwhat's worth building and what shape it takes; plan mode decides how one\npiece gets done. The branch is the line between them.\n\n## Ask only what's still open\n\nA competent engineer would want to know: who has this problem, what\nchanges for them, what does success look like, what's explicitly out of\nscope, and the shape at feature altitude -- the data model, the API\nsurface, not implementation detail. If the opening request already\nanswers some of these, don't re-ask them. Cover whatever's still open in\none combined question, not one per item.\n\n## What the draft should contain\n\nOnce the developer approves the feature plan drafted in `\u002Fplan` mode,\nwrite it yourself to `.canon\u002Fplans\u002Ffeatures\u002F\u003Cslug>.md` (the slug comes\nfrom the plan's own `# ` title -- Codex has no `ExitPlanMode` tool to\nname a file for you, so a `PostToolUse` hook, `normalize_plan.py`,\nderives this file's header from what you write, the same way the `plan`\nskill's hook does for a branch plan; see that skill for the underlying\nmechanism). Only write it once the developer has actually approved it --\nthis platform has no tool call that confirms that for you, so treat the\nwrite itself as the consequential step. Make sure the plan states:\n\n- `# \u003CFeature name>` as its title -- this becomes the saved plan's\n  filename.\n- `## Why`, `## Success`, and `## Non-goals` -- the same discipline\n  `plan` asks for at branch altitude, one level up.\n- `## Shape` -- the technical approach -- and `## Decisions`, only\n  where something was genuinely contested (an alternative seriously\n  considered, not just the obviously correct way of doing it).\n- `## Steps` -- an ordered list, each entry one branch-sized piece: one\n  branch, one pull request. A non-empty `## Steps` section is what\n  makes `normalize_plan.py` treat the file as a feature plan rather than\n  an ordinary branch plan.\n\n  **Lead each step with its branch slug**, then a colon:\n\n  ```markdown\n  ## Steps\n\n  - slugs: make duplicate slugs raise, with a regression test\n  - permalinks-api: expose the permalink endpoint\n  ```\n\n  That slug is how `canon_position` answers \"which step am I on\" -- it\n  matches the slug against branches that exist and pull requests that\n  merged. A branch may carry a prefix (`feature\u002Fslugs` matches the step\n  `slugs`), but a step written without a slug can never be matched to\n  anything, and `canon_position` will report it as `unmatched` rather\n  than guess. Matching step prose against branch names is exactly the\n  wrong-but-plausible inference Canon refuses to make.\n\n  **Say what a step waits for** where it isn't the step above it. No\n  annotation means it waits for the one above -- what an ordered list\n  already implies -- so write `(after: ...)` only where that's wrong:\n\n  ```markdown\n  ## Steps\n\n  - eval-corpus: 30 graded requests with their expected outcomes\n  - pymol-tools (after: none): expose the library to an agent\n  - baseline (after: eval-corpus, pymol-tools): record the score\n  ```\n\n  `(after: none)` waits for nothing; a comma-separated list waits for\n  all of them. `canon_position` reports every step whose dependencies\n  have merged as startable, so this is what lets two sessions pick up\n  different steps without colliding.\n\n  **Claim independence only where it's true.** A step wrongly marked\n  independent gets started against a base without its prerequisite in\n  it -- a wasted branch at best, a silent conflict at worst.\n\n## No gate, no new artifact\n\nNothing here is accepted or advanced through a status. The feature plan\nis a document the developer reads, edits, and reorders like any other\nfile in the repo -- there's no separate design doc, no brief, no launch\nplan. When work starts on step one, use the `plan` skill as usual; it\nalready asks for the parent feature plan when one exists.\n","# Frame\n\nThis runs once, before any branch exists for the feature. Framing decides\nwhat's worth building and what shape it takes; plan mode decides how one\npiece gets done. The branch is the line between them.\n\n## Ask only what's still open\n\nA competent engineer would want to know: who has this problem, what\nchanges for them, what does success look like, what's explicitly out of\nscope, and the shape at feature altitude -- the data model, the API\nsurface, not implementation detail. If the opening request already\nanswers some of these, don't re-ask them. Cover whatever's still open in\none combined question, not one per item.\n\n## What the draft should contain\n\nOnce the developer approves the feature plan drafted in `\u002Fplan` mode,\nwrite it yourself to `.canon\u002Fplans\u002Ffeatures\u002F\u003Cslug>.md` (the slug comes\nfrom the plan's own `# ` title -- Codex has no `ExitPlanMode` tool to\nname a file for you, so a `PostToolUse` hook, `normalize_plan.py`,\nderives this file's header from what you write, the same way the `plan`\nskill's hook does for a branch plan; see that skill for the underlying\nmechanism). Only write it once the developer has actually approved it --\nthis platform has no tool call that confirms that for you, so treat the\nwrite itself as the consequential step. Make sure the plan states:\n\n- `# \u003CFeature name>` as its title -- this becomes the saved plan's\n  filename.\n- `## Why`, `## Success`, and `## Non-goals` -- the same discipline\n  `plan` asks for at branch altitude, one level up.\n- `## Shape` -- the technical approach -- and `## Decisions`, only\n  where something was genuinely contested (an alternative seriously\n  considered, not just the obviously correct way of doing it).\n- `## Steps` -- an ordered list, each entry one branch-sized piece: one\n  branch, one pull request. A non-empty `## Steps` section is what\n  makes `normalize_plan.py` treat the file as a feature plan rather than\n  an ordinary branch plan.\n\n  **Lead each step with its branch slug**, then a colon:\n\n  ```markdown\n  ## Steps\n\n  - slugs: make duplicate slugs raise, with a regression test\n  - permalinks-api: expose the permalink endpoint\n  ```\n\n  That slug is how `canon_position` answers \"which step am I on\" -- it\n  matches the slug against branches that exist and pull requests that\n  merged. A branch may carry a prefix (`feature\u002Fslugs` matches the step\n  `slugs`), but a step written without a slug can never be matched to\n  anything, and `canon_position` will report it as `unmatched` rather\n  than guess. Matching step prose against branch names is exactly the\n  wrong-but-plausible inference Canon refuses to make.\n\n  **Say what a step waits for** where it isn't the step above it. No\n  annotation means it waits for the one above -- what an ordered list\n  already implies -- so write `(after: ...)` only where that's wrong:\n\n  ```markdown\n  ## Steps\n\n  - eval-corpus: 30 graded requests with their expected outcomes\n  - pymol-tools (after: none): expose the library to an agent\n  - baseline (after: eval-corpus, pymol-tools): record the score\n  ```\n\n  `(after: none)` waits for nothing; a comma-separated list waits for\n  all of them. `canon_position` reports every step whose dependencies\n  have merged as startable, so this is what lets two sessions pick up\n  different steps without colliding.\n\n  **Claim independence only where it's true.** A step wrongly marked\n  independent gets started against a base without its prerequisite in\n  it -- a wasted branch at best, a silent conflict at worst.\n\n## No gate, no new artifact\n\nNothing here is accepted or advanced through a status. The feature plan\nis a document the developer reads, edits, and reorders like any other\nfile in the repo -- there's no separate design doc, no brief, no launch\nplan. When work starts on step one, use the `plan` skill as usual; it\nalready asks for the parent feature plan when one exists.\n",{"name":5,"description":7},"main","453e779ab8a331947f8cb2b1168cb0ba8f1f3256","plugins\u002Fcodex\u002Fskills\u002Fframe",0,"https:\u002F\u002Fgithub.com\u002Furban233\u002FCanon","https:\u002F\u002Fgithub.com\u002Furban233","2026-10-01 06:44:57",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add urban233\u002FCanon --skill frame",{"tool":37,"command":38},"bunx","bunx skills add urban233\u002FCanon --skill frame",{"tool":40,"command":41},"pnpm","pnpm dlx skills add urban233\u002FCanon --skill frame","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Furban233\u002FCanon\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex\u002Fskills\u002Fframe\u002FSKILL.md",true,[],[46,53,60,67,73,80],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7CQ48XK94BYRMQVDCQRTY77","testing-craft","Provides Google-derived testing strategy, test-writing craft, and test-suite health reference, distilled from Software Engineering at Google (the Flamingo book), the Google Testing Blog, and Google's published testing-infrastructure research. Canon's `reviewer` subagent reads the writing-craft and strategy references as review criteria. Invoke directly to design a test strategy, audit an existing suite's health, or triage a flaky or brittle test.","https:\u002F\u002Fgithub.com\u002Furban233\u002FCanon\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex\u002Fskills\u002Ftesting-craft\u002FSKILL.md",[],[],{"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},"01M7CQ465824PE31REMF8HFB74","ship","Decide whether a change is ready to hand to a human, and open the pull request when it is. Use once the work is done and verified, before opening a PR or telling the developer the change is ready.","https:\u002F\u002Fgithub.com\u002Furban233\u002FCanon\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex\u002Fskills\u002Fship\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},"01M7CQ40YM28KQ9H79HEC2T0SB","review","Dispatch Canon's independent reviewer subagents for this branch and read their verdicts back from canon_review. Use once a change is built and verified, before shipping. This skill only dispatches and reads back -- the review itself runs inside the subagent, in a fresh context, and never in this session.","https:\u002F\u002Fgithub.com\u002Furban233\u002FCanon\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7CQ3ZK97QCHFZ7NNP6E1EZP","review-change","https:\u002F\u002Fgithub.com\u002Furban233\u002FCanon\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex\u002Fskills\u002Freview-change\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7CQ3KTVG5BAW4ZVMNYS1AFE","plan","Shape what plan mode drafts, so the plan Canon saves needs no follow-up. Use whenever drafting a plan for approval in plan mode, before writing it to .canon\u002Fplans\u002F.","https:\u002F\u002Fgithub.com\u002Furban233\u002FCanon\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex\u002Fskills\u002Fplan\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7CQ24Q1VA2M3R6XBYPN7HT8","decide","Draft and commit a decision record for a design or architecture choice made in this session, once it has survived implementation. Use at ship time, right before opening the pull request, when the branch made a decision worth recording.","https:\u002F\u002Fgithub.com\u002Furban233\u002FCanon\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex\u002Fskills\u002Fdecide\u002FSKILL.md",[],[]]