[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79SPVN5C0XYAXWBH9HD1YF1":3,"skill-same:01M79SPVN5C0XYAXWBH9HD1YF1":47},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":46},"01M79SPVN5C0XYAXWBH9HD1YF1","two-axis-review",null,"Two-axis review of changes since a fixed point (commit, tag, HEAD~N, or default HEAD~1): Standards (does the code follow this repo's conventions?) and Spec (does the code do what it should?). Axes run as parallel sub-agents so neither masks the other. Use when the user says \"review against the spec\", \"does this follow our conventions\", \"standards and spec review\", or \"two-axis review\". Not a correctness bug hunt — that's the built-in `\u002Fcode-review`.","dannybrown37\u002Fskill-tree","dannybrown37","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F28059438?v=4","01M79SKVHAKWQH9VF0G6KQRZZ2","Danny Brown","01M79SKVJ1X8VHPTK7MKMHBRD2",0,"MIT","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Ftwo-axis-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: two-axis-review\ndescription: \"Two-axis review of changes since a fixed point (commit, tag, HEAD~N, or default HEAD~1): Standards (does the code follow this repo's conventions?) and Spec (does the code do what it should?). Axes run as parallel sub-agents so neither masks the other. Use when the user says \\\"review against the spec\\\", \\\"does this follow our conventions\\\", \\\"standards and spec review\\\", or \\\"two-axis review\\\". Not a correctness bug hunt — that's the built-in `\u002Fcode-review`.\"\nuser-invocable: true\nallowed-tools: Read, Grep, Glob, Bash, Agent\n---\n\n# Two-Axis Review\n\nTwo-axis review: **Standards** and **Spec**, run in parallel so one can't mask the other.\n\nA change can pass one axis and fail the other:\n- Code that follows every standard but implements the wrong thing -> Standards pass, Spec fail.\n- Code that does exactly what was asked but breaks conventions -> Spec pass, Standards fail.\n\n## Process\n\n### 1. Pin the fixed point\n\nUse whatever the user said as the fixed point (a commit SHA, branch, tag, `HEAD~5`, etc.).\nIf they didn't specify one, default to `HEAD~1` (the last commit). For uncommitted work,\ndiff against `HEAD`.\n\nCapture the diff once:\n\n```\ngit diff \u003Cfixed-point>...HEAD    # committed changes\ngit diff HEAD                    # if reviewing uncommitted work\n```\n\nAlso note commits: `git log \u003Cfixed-point>..HEAD --oneline`.\n\nVerify the fixed point resolves (`git rev-parse`) and the diff is non-empty. A bad ref or\nempty diff should fail here, not inside the sub-agents.\n\n### 2. Identify the spec source\n\nLook for what the changes are *supposed* to do, in this order:\n\n1. A path the user passed as an argument (\"review against docs\u002Fspec.md\").\n2. Issue references in commit messages (`#123`, `Closes #45`), fetched via `gh issue view`.\n3. A spec file under `docs\u002F`, `specs\u002F`, or `.scratch\u002F` matching the branch name or feature.\n\nIf nothing is found, ask the user. If they say there isn't one, skip the Spec axis entirely\nand note it in the final report.\n\n### 3. Identify the standards sources\n\nAnything in the repo that documents how code should be written:\n\n- `CLAUDE.md`, `.claude\u002FCLAUDE.md` (project instructions)\n- `CODING_STANDARDS.md`, `CONTRIBUTING.md`\n- Linter configs (`.ruff.toml`, `.eslintrc`, `mypy.ini`, etc.) — note these exist but don't\n  re-check what the linter already enforces\n\nOn top of repo-documented standards, always carry the **smell baseline** below: Fowler code\nsmells (Refactoring, ch.3) that apply even when a repo documents nothing. Two rules:\n\n- **The repo overrides.** A documented repo standard always wins; where it endorses something\n  the baseline would flag, suppress the smell.\n- **Always a judgement call.** Each smell is a labelled heuristic (\"possible Feature Envy\"),\n  never a hard violation. Skip anything tooling already enforces.\n\n#### Smell baseline\n\nEach entry: what it is -> how to fix.\n\n- **Mysterious Name**: name doesn't reveal what it does or holds -> rename; if no honest name\n  comes, the design is murky.\n- **Duplicated Code**: same logic shape in more than one hunk\u002Ffile -> extract, call from both.\n- **Feature Envy**: method reaches into another object's data more than its own -> move the\n  method onto the data it envies.\n- **Data Clumps**: same few fields\u002Fparams keep travelling together -> bundle into one type.\n- **Primitive Obsession**: a primitive standing in for a domain concept -> give the concept\n  its own small type.\n- **Repeated Switches**: same switch\u002Fif-cascade on the same type recurs -> replace with\n  polymorphism or one shared map.\n- **Shotgun Surgery**: one logical change forces scattered edits across many files -> gather\n  what changes together into one module.\n- **Divergent Change**: one file edited for several unrelated reasons -> split so each module\n  changes for one reason.\n- **Speculative Generality**: abstraction\u002Fparams\u002Fhooks added for needs that don't exist yet ->\n  delete; inline until a real need shows.\n- **Message Chains**: long `a.b().c().d()` navigation -> hide the walk behind one method.\n- **Middle Man**: class\u002Ffunction that mostly just delegates -> cut it, call the real target.\n- **Refused Bequest**: subclass that ignores most of what it inherits -> drop inheritance,\n  use composition.\n\n### 4. Spawn both sub-agents in parallel\n\nUse the `Agent` tool to launch both at the same time.\n\n**Standards sub-agent** prompt must include:\n- The full diff (command and output, or the output directly if small enough).\n- The commit list.\n- The standards sources found in step 3, plus the smell baseline pasted in full.\n- The brief: \"Report, per file\u002Fhunk where relevant: (a) every place the diff violates a\n  documented standard — cite the standard (file + rule); (b) any baseline smell you spot —\n  name it and quote the hunk. Distinguish hard violations from judgement calls:\n  documented-standard breaches are hard, baseline smells are always judgement calls, and a\n  documented repo standard overrides the baseline. Skip anything tooling enforces.\n  Under 400 words.\"\n\n**Spec sub-agent** prompt must include:\n- The diff and commit list.\n- The spec contents (path or fetched issue body).\n- The brief: \"Report: (a) requirements the spec asked for that are missing or partial;\n  (b) behaviour in the diff that wasn't asked for (scope creep); (c) requirements that look\n  implemented but where the implementation looks wrong. Quote the spec line for each finding.\n  Under 400 words.\"\n\nIf no spec was found, skip the Spec sub-agent and note it in the final report.\n\n### 5. Aggregate\n\nPresent the two reports under `## Standards` and `## Spec` headings, verbatim or lightly\ncleaned. **Do not merge or rerank** — the axes are deliberately separate.\n\nEnd with a one-line summary: total findings per axis and the worst issue within each.\nDon't pick a single winner across axes.\n","# Two-Axis Review\n\nTwo-axis review: **Standards** and **Spec**, run in parallel so one can't mask the other.\n\nA change can pass one axis and fail the other:\n- Code that follows every standard but implements the wrong thing -> Standards pass, Spec fail.\n- Code that does exactly what was asked but breaks conventions -> Spec pass, Standards fail.\n\n## Process\n\n### 1. Pin the fixed point\n\nUse whatever the user said as the fixed point (a commit SHA, branch, tag, `HEAD~5`, etc.).\nIf they didn't specify one, default to `HEAD~1` (the last commit). For uncommitted work,\ndiff against `HEAD`.\n\nCapture the diff once:\n\n```\ngit diff \u003Cfixed-point>...HEAD    # committed changes\ngit diff HEAD                    # if reviewing uncommitted work\n```\n\nAlso note commits: `git log \u003Cfixed-point>..HEAD --oneline`.\n\nVerify the fixed point resolves (`git rev-parse`) and the diff is non-empty. A bad ref or\nempty diff should fail here, not inside the sub-agents.\n\n### 2. Identify the spec source\n\nLook for what the changes are *supposed* to do, in this order:\n\n1. A path the user passed as an argument (\"review against docs\u002Fspec.md\").\n2. Issue references in commit messages (`#123`, `Closes #45`), fetched via `gh issue view`.\n3. A spec file under `docs\u002F`, `specs\u002F`, or `.scratch\u002F` matching the branch name or feature.\n\nIf nothing is found, ask the user. If they say there isn't one, skip the Spec axis entirely\nand note it in the final report.\n\n### 3. Identify the standards sources\n\nAnything in the repo that documents how code should be written:\n\n- `CLAUDE.md`, `.claude\u002FCLAUDE.md` (project instructions)\n- `CODING_STANDARDS.md`, `CONTRIBUTING.md`\n- Linter configs (`.ruff.toml`, `.eslintrc`, `mypy.ini`, etc.) — note these exist but don't\n  re-check what the linter already enforces\n\nOn top of repo-documented standards, always carry the **smell baseline** below: Fowler code\nsmells (Refactoring, ch.3) that apply even when a repo documents nothing. Two rules:\n\n- **The repo overrides.** A documented repo standard always wins; where it endorses something\n  the baseline would flag, suppress the smell.\n- **Always a judgement call.** Each smell is a labelled heuristic (\"possible Feature Envy\"),\n  never a hard violation. Skip anything tooling already enforces.\n\n#### Smell baseline\n\nEach entry: what it is -> how to fix.\n\n- **Mysterious Name**: name doesn't reveal what it does or holds -> rename; if no honest name\n  comes, the design is murky.\n- **Duplicated Code**: same logic shape in more than one hunk\u002Ffile -> extract, call from both.\n- **Feature Envy**: method reaches into another object's data more than its own -> move the\n  method onto the data it envies.\n- **Data Clumps**: same few fields\u002Fparams keep travelling together -> bundle into one type.\n- **Primitive Obsession**: a primitive standing in for a domain concept -> give the concept\n  its own small type.\n- **Repeated Switches**: same switch\u002Fif-cascade on the same type recurs -> replace with\n  polymorphism or one shared map.\n- **Shotgun Surgery**: one logical change forces scattered edits across many files -> gather\n  what changes together into one module.\n- **Divergent Change**: one file edited for several unrelated reasons -> split so each module\n  changes for one reason.\n- **Speculative Generality**: abstraction\u002Fparams\u002Fhooks added for needs that don't exist yet ->\n  delete; inline until a real need shows.\n- **Message Chains**: long `a.b().c().d()` navigation -> hide the walk behind one method.\n- **Middle Man**: class\u002Ffunction that mostly just delegates -> cut it, call the real target.\n- **Refused Bequest**: subclass that ignores most of what it inherits -> drop inheritance,\n  use composition.\n\n### 4. Spawn both sub-agents in parallel\n\nUse the `Agent` tool to launch both at the same time.\n\n**Standards sub-agent** prompt must include:\n- The full diff (command and output, or the output directly if small enough).\n- The commit list.\n- The standards sources found in step 3, plus the smell baseline pasted in full.\n- The brief: \"Report, per file\u002Fhunk where relevant: (a) every place the diff violates a\n  documented standard — cite the standard (file + rule); (b) any baseline smell you spot —\n  name it and quote the hunk. Distinguish hard violations from judgement calls:\n  documented-standard breaches are hard, baseline smells are always judgement calls, and a\n  documented repo standard overrides the baseline. Skip anything tooling enforces.\n  Under 400 words.\"\n\n**Spec sub-agent** prompt must include:\n- The diff and commit list.\n- The spec contents (path or fetched issue body).\n- The brief: \"Report: (a) requirements the spec asked for that are missing or partial;\n  (b) behaviour in the diff that wasn't asked for (scope creep); (c) requirements that look\n  implemented but where the implementation looks wrong. Quote the spec line for each finding.\n  Under 400 words.\"\n\nIf no spec was found, skip the Spec sub-agent and note it in the final report.\n\n### 5. Aggregate\n\nPresent the two reports under `## Standards` and `## Spec` headings, verbatim or lightly\ncleaned. **Do not merge or rerank** — the axes are deliberately separate.\n\nEnd with a one-line summary: total findings per axis and the worst issue within each.\nDon't pick a single winner across axes.\n",{"name":5,"description":7,"allowed-tools":24,"user-invocable":25},"Read, Grep, Glob, Bash, Agent",true,"main","aec70683dacdf9512d27e04a1e04069bbd199b5e","skills\u002Ftwo-axis-review","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree","https:\u002F\u002Fgithub.com\u002Fdannybrown37","dannybrown.dev","Software Engineer","2026-11-12 15:25:14",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":25},[36,39,42],{"tool":37,"command":38},"npx","npx skills add dannybrown37\u002Fskill-tree --skill two-axis-review",{"tool":40,"command":41},"bunx","bunx skills add dannybrown37\u002Fskill-tree --skill two-axis-review",{"tool":43,"command":44},"pnpm","pnpm dlx skills add dannybrown37\u002Fskill-tree --skill two-axis-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Ftwo-axis-review\u002FSKILL.md",[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M79SQ7Z4DXMYJECV1NTEP9WY","wait-what","Stop. Your plan\u002Fidea did not land. Re-pitch it.","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M79SQ4WQB5YZ7Q2A87JVR219","verify","Verify before answering whether something works, still passes, is gone, is used, or is correct — and whenever the user says \"can you confirm\", \"are you sure\", \"did that actually work\", or reports something is \"still\" broken. Produces the answer plus the evidence that would have falsified it. A failed GitHub Actions run is skill-tree:debug-ci instead.","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M79SQ0GKSM5891DKPXE8J7TZ","ui-designer","Design or restyle a web UI — landing pages, dashboards, docs sites, app chrome — or when the user asks why a site \"looks generic\", \"looks like a template\", or wants it to feel intentional. A running list of design lessons learned, applied as rules rather than suggestions.","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fui-designer\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M79SPRT8GV1RPQ2VVR9K08BB","tui-screenshots","Use for generating or refreshing TUI screenshots for docs — \"regenerate the screenshots\", \"the README screenshots are stale\". Drives a Textual\u002FTUI app headlessly and exports SVG. Not for reading a user's screenshot — that is `screenshot`.","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Ftui-screenshots\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M79SPNVJQ0WNWH7PBEM5Y463","to-tickets","Break a spec, plan, or conversation into tracer-bullet vertical-slice tickets with blocking edges — \"turn this into tickets\", \"break this down\", \"what's the work?\". Pairs with skill-tree:to-spec upstream and skill-tree:handoff downstream.","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fto-tickets\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M79SPH2AAARBSV1VWZJCPMFA","to-spec","A conversation has settled on what to build and it's time to turn it into a written spec — \"turn this into a spec\", \"write this up\", \"spec this out\". Synthesis only: no interview. Pairs well with skill-tree:grill-for-planning, which is where the settled understanding usually comes from.","https:\u002F\u002Fgithub.com\u002Fdannybrown37\u002Fskill-tree\u002Fblob\u002Fmain\u002Fskills\u002Fto-spec\u002FSKILL.md",[],[]]