[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DC17TCVBD3HC5P6ZPXX8MT":3,"skill-same:01M7DC17TCVBD3HC5P6ZPXX8MT":49},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":48},"01M7DC17TCVBD3HC5P6ZPXX8MT","simple",null,"Use when changed code should be cleaned up without changing what it does — the user asks to simplify, tidy, clean up, de-duplicate, or de-complicate a diff\u002Fbranch\u002Ffile, or a just-finished implementation reads as over-built. Fans four cleanup agents (reuse, simplification, efficiency, altitude) over the diff and applies the fixes. Quality only — it does not hunt for correctness bugs, that is \u002Freview.","riventic\u002Fair2lean","riventic","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F206525355?v=4","01M7DC0K99XQ5MJ7AB5XRGCX0Q","Riventic","01M7DC0KA9QSACE3E30F0EXYB7",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Friventic\u002Fair2lean\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsimple\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: simple\ndescription: Use when changed code should be cleaned up without changing what it does — the user asks to simplify, tidy, clean up, de-duplicate, or de-complicate a diff\u002Fbranch\u002Ffile, or a just-finished implementation reads as over-built. Fans four cleanup agents (reuse, simplification, efficiency, altitude) over the diff and applies the fixes. Quality only — it does not hunt for correctness bugs, that is \u002Freview.\ndisable-model-invocation: false\nuser-invocable: true\nallowed-tools: Bash, Read, Grep, Glob, Edit, Agent\nargument-hint: \"[\u003Ctarget>]\"\n---\n\n# \u002Fsimple — Cleanup pass over the changed code\n\nPort of Claude Code's bundled `simplify` skill, extracted from the CLI binary (2.1.296) and kept as a file for the same reasons `\u002Freview` is: always listed, always readable, never subject to the bundled skill's invocation limits. Named `simple` so it does not shadow the bundled `\u002Fsimplify`, which stays callable and is the upstream cross-check.\n\n**From each shape line to the end of its Phase 2, this is upstream's text character for character** — both cells, the 4-agent one and the `Agent`-unavailable fallback. Three deviations, and no others: the shape lines name `\u002Fsimple`, the intros point at `\u002Freview`, and the fallback's two phase headings sit at `###` so they nest under the section that holds them. Outside the copied prompt: everything above the rule below, the \"When the `Agent` tool is absent\" header and the note under it, and `## Related` at the end. Nothing sits *inside* a copied phase.\n\n**Inline the angle text into each agent prompt** — sub-agents never see this file.\n\n**Scope: quality, not correctness.** This skill changes how the code reads, never what it does. It finds no bugs and looks for none — `\u002Freview` is the bug hunter.\n\n## Arguments\n\n| Argument | Meaning |\n|---|---|\n| `\u003Ctarget>` | A `\u003Cpr#>`, branch, path, or `a...b` range. Blank = the current diff. |\n\nThere is no report-only mode: Phase 2 *is* the skill. For a cleanup list you can read before anything is touched, run `\u002Freview --no-fix` — its reuse\u002Fsimplification\u002Fefficiency\u002Faltitude angles are the same four, riding along behind the correctness ones.\n\n---\n\n`\u002Fsimple → 4 cleanup agents in parallel → apply the fixes`\n\nYou are improving the quality of the changed code, not hunting for bugs. Review\nit for reuse, simplification, efficiency, and altitude issues, then fix what you\nfind. Do not look for correctness bugs — that is what `\u002Freview` is for.\n\n## Phase 0 — Gather the diff\n\nRun `git diff @{upstream}...HEAD` (or `git diff main...HEAD` \u002F `git diff HEAD~1`\nif there's no upstream) to get the unified diff under review. If there are\nuncommitted changes, or the range diff is empty, also run `git diff HEAD` and\ninclude the working-tree changes in scope — the review often runs before the\ncommit. If a PR number, branch name, or file path was passed as an argument,\nreview that target instead. Treat this diff as the review scope.\n\n## Phase 1 — Review (4 cleanup agents in parallel)\n\nLaunch **4 independent review agents** via the Agent tool, all in a\nsingle message so they run concurrently. Pass each agent the diff and one of\nthe four angles below. Each returns its findings with `file`, `line`, a\none-line `summary`, and the concrete cost (what is duplicated, wasted, or\nharder to maintain).\n\n### Reuse\n\nFlag new code that re-implements something the codebase\nalready has — Grep shared\u002Futility modules and files adjacent to the change,\nand name the existing helper to call instead.\n\n### Simplification\n\nFlag unnecessary complexity the diff adds: redundant or derivable state,\ncopy-paste with slight variation, deep nesting, dead code left behind. Name\nthe simpler form that does the same job.\n\n### Efficiency\n\nFlag wasted work the diff introduces: redundant computation or repeated I\u002FO,\nindependent operations run sequentially, blocking work added to startup or\nhot paths. Also flag long-lived objects built from closures or captured\nenvironments — they keep the entire enclosing scope alive for the object's\nlifetime (a memory leak when that scope holds large values); prefer a\nclass\u002Fstruct that copies only the fields it needs. Name the cheaper\nalternative.\n\n### Altitude\n\nCheck that each change fixes the root cause at the right depth rather than\npatching a symptom with a fragile bandaid. Special cases layered on shared\ninfrastructure are a sign the fix isn't deep enough — prefer the simpler, more\ngeneral change to the underlying mechanism over adding special cases, and name\nthat change.\n\n## Phase 2 — Apply the fixes\n\nWait for all four agents to complete, dedup findings that point at the same\nline or mechanism, and fix each remaining one directly. Skip any finding whose\nfix would change intended behavior, require changes well outside the reviewed\ndiff, or that you judge to be a false positive — note the skip rather than\narguing with it. Finish with a brief summary of what was fixed and what was\nskipped (or confirm the code was already clean).\n\n\n---\n\n## When the `Agent` tool is absent\n\nUpstream ships this as a second standalone cell and the CLI picks one at call time; here both live in one file, so this section repeats only what differs. Phase 0 and the four angles are the ones above — read \"below\" in the quoted text as \"above\".\n\n`\u002Fsimple → Agent tool unavailable → single-pass inline cleanup → apply the fixes`\n\nYou are improving the quality of the changed code, not hunting for bugs. Review\nit for reuse, simplification, efficiency, and altitude issues, then fix what you\nfind. Do not look for correctness bugs — that is what `\u002Freview` is for.\n\nThe Agent tool isn't available in this context, so the usual\n4-agent fan-out can't run. Work through all four angles below yourself, in\nthis same context, in one pass — do not skip an angle for lack of fan-out.\n\n### Phase 1 — Review (4 cleanup angles, single pass)\n\nReview the diff against each angle below in turn. For each, note findings with\n`file`, `line`, a one-line `summary`, and the concrete cost (what is\nduplicated, wasted, or harder to maintain).\n\n### Phase 2 — Apply the fixes\n\nDedup findings that point at the same line or mechanism, and fix each\nremaining one directly. Skip any finding whose fix would change intended\nbehavior, require changes well outside the reviewed diff, or that you judge to\nbe a false positive — note the skip rather than arguing with it. Finish with a\nbrief summary of what was fixed and what was skipped (or confirm the code was\nalready clean). State clearly in your summary that this was a single-pass\nreview done without the Agent tool, not the full 4-agent\nfan-out, so whoever reads it isn't misled about what actually ran.\n\n## Related\n\n- [\u002Freview](..\u002Freview\u002FSKILL.md) — the bug hunter. Carries these same four angles as ride-alongs behind its correctness ones, capped and outranked by real bugs. Run it for \"is this right\"; run `\u002Fsimple` for \"is this clean\".\n- `Skill(skill: \"simplify\", …)` — the bundled original, for cross-checking this port.\n","# \u002Fsimple — Cleanup pass over the changed code\n\nPort of Claude Code's bundled `simplify` skill, extracted from the CLI binary (2.1.296) and kept as a file for the same reasons `\u002Freview` is: always listed, always readable, never subject to the bundled skill's invocation limits. Named `simple` so it does not shadow the bundled `\u002Fsimplify`, which stays callable and is the upstream cross-check.\n\n**From each shape line to the end of its Phase 2, this is upstream's text character for character** — both cells, the 4-agent one and the `Agent`-unavailable fallback. Three deviations, and no others: the shape lines name `\u002Fsimple`, the intros point at `\u002Freview`, and the fallback's two phase headings sit at `###` so they nest under the section that holds them. Outside the copied prompt: everything above the rule below, the \"When the `Agent` tool is absent\" header and the note under it, and `## Related` at the end. Nothing sits *inside* a copied phase.\n\n**Inline the angle text into each agent prompt** — sub-agents never see this file.\n\n**Scope: quality, not correctness.** This skill changes how the code reads, never what it does. It finds no bugs and looks for none — `\u002Freview` is the bug hunter.\n\n## Arguments\n\n| Argument | Meaning |\n|---|---|\n| `\u003Ctarget>` | A `\u003Cpr#>`, branch, path, or `a...b` range. Blank = the current diff. |\n\nThere is no report-only mode: Phase 2 *is* the skill. For a cleanup list you can read before anything is touched, run `\u002Freview --no-fix` — its reuse\u002Fsimplification\u002Fefficiency\u002Faltitude angles are the same four, riding along behind the correctness ones.\n\n---\n\n`\u002Fsimple → 4 cleanup agents in parallel → apply the fixes`\n\nYou are improving the quality of the changed code, not hunting for bugs. Review\nit for reuse, simplification, efficiency, and altitude issues, then fix what you\nfind. Do not look for correctness bugs — that is what `\u002Freview` is for.\n\n## Phase 0 — Gather the diff\n\nRun `git diff @{upstream}...HEAD` (or `git diff main...HEAD` \u002F `git diff HEAD~1`\nif there's no upstream) to get the unified diff under review. If there are\nuncommitted changes, or the range diff is empty, also run `git diff HEAD` and\ninclude the working-tree changes in scope — the review often runs before the\ncommit. If a PR number, branch name, or file path was passed as an argument,\nreview that target instead. Treat this diff as the review scope.\n\n## Phase 1 — Review (4 cleanup agents in parallel)\n\nLaunch **4 independent review agents** via the Agent tool, all in a\nsingle message so they run concurrently. Pass each agent the diff and one of\nthe four angles below. Each returns its findings with `file`, `line`, a\none-line `summary`, and the concrete cost (what is duplicated, wasted, or\nharder to maintain).\n\n### Reuse\n\nFlag new code that re-implements something the codebase\nalready has — Grep shared\u002Futility modules and files adjacent to the change,\nand name the existing helper to call instead.\n\n### Simplification\n\nFlag unnecessary complexity the diff adds: redundant or derivable state,\ncopy-paste with slight variation, deep nesting, dead code left behind. Name\nthe simpler form that does the same job.\n\n### Efficiency\n\nFlag wasted work the diff introduces: redundant computation or repeated I\u002FO,\nindependent operations run sequentially, blocking work added to startup or\nhot paths. Also flag long-lived objects built from closures or captured\nenvironments — they keep the entire enclosing scope alive for the object's\nlifetime (a memory leak when that scope holds large values); prefer a\nclass\u002Fstruct that copies only the fields it needs. Name the cheaper\nalternative.\n\n### Altitude\n\nCheck that each change fixes the root cause at the right depth rather than\npatching a symptom with a fragile bandaid. Special cases layered on shared\ninfrastructure are a sign the fix isn't deep enough — prefer the simpler, more\ngeneral change to the underlying mechanism over adding special cases, and name\nthat change.\n\n## Phase 2 — Apply the fixes\n\nWait for all four agents to complete, dedup findings that point at the same\nline or mechanism, and fix each remaining one directly. Skip any finding whose\nfix would change intended behavior, require changes well outside the reviewed\ndiff, or that you judge to be a false positive — note the skip rather than\narguing with it. Finish with a brief summary of what was fixed and what was\nskipped (or confirm the code was already clean).\n\n\n---\n\n## When the `Agent` tool is absent\n\nUpstream ships this as a second standalone cell and the CLI picks one at call time; here both live in one file, so this section repeats only what differs. Phase 0 and the four angles are the ones above — read \"below\" in the quoted text as \"above\".\n\n`\u002Fsimple → Agent tool unavailable → single-pass inline cleanup → apply the fixes`\n\nYou are improving the quality of the changed code, not hunting for bugs. Review\nit for reuse, simplification, efficiency, and altitude issues, then fix what you\nfind. Do not look for correctness bugs — that is what `\u002Freview` is for.\n\nThe Agent tool isn't available in this context, so the usual\n4-agent fan-out can't run. Work through all four angles below yourself, in\nthis same context, in one pass — do not skip an angle for lack of fan-out.\n\n### Phase 1 — Review (4 cleanup angles, single pass)\n\nReview the diff against each angle below in turn. For each, note findings with\n`file`, `line`, a one-line `summary`, and the concrete cost (what is\nduplicated, wasted, or harder to maintain).\n\n### Phase 2 — Apply the fixes\n\nDedup findings that point at the same line or mechanism, and fix each\nremaining one directly. Skip any finding whose fix would change intended\nbehavior, require changes well outside the reviewed diff, or that you judge to\nbe a false positive — note the skip rather than arguing with it. Finish with a\nbrief summary of what was fixed and what was skipped (or confirm the code was\nalready clean). State clearly in your summary that this was a single-pass\nreview done without the Agent tool, not the full 4-agent\nfan-out, so whoever reads it isn't misled about what actually ran.\n\n## Related\n\n- [\u002Freview](..\u002Freview\u002FSKILL.md) — the bug hunter. Carries these same four angles as ride-alongs behind its correctness ones, capped and outranked by real bugs. Run it for \"is this right\"; run `\u002Fsimple` for \"is this clean\".\n- `Skill(skill: \"simplify\", …)` — the bundled original, for cross-checking this port.\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25,"user-invocable":26,"disable-model-invocation":20},"Bash, Read, Grep, Glob, Edit, Agent","[\u003Ctarget>]",true,"main","e7c5c4000c5a81bdd9d1838e61ac2d46b552ad65",".claude\u002Fskills\u002Fsimple",0,"https:\u002F\u002Fgithub.com\u002Friventic\u002Fair2lean","https:\u002F\u002Fgithub.com\u002Friventic","www.riventic.ai","AI for Industry","2026-11-13 04:57:38",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":26},[38,41,44],{"tool":39,"command":40},"npx","npx skills add riventic\u002Fair2lean --skill simple",{"tool":42,"command":43},"bunx","bunx skills add riventic\u002Fair2lean --skill simple",{"tool":45,"command":46},"pnpm","pnpm dlx skills add riventic\u002Fair2lean --skill simple","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Friventic\u002Fair2lean\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsimple\u002FSKILL.md",[],[50,57,62],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7DC0S8J9T4C2W8BZNCN7ZQB","review","Use whenever a code change needs checking for real bugs before it lands — the user asks to review, check, sanity-check, look over, or find bugs in a diff\u002Fbranch\u002FPR\u002Ffile; a feature or fix has just been implemented and is about to be committed, pushed, or turned into a PR; a subagent hands back work; or a PR needs reviewing before merge. Also use proactively after finishing any non-trivial implementation, before reporting it done. Hunts correctness — wrong conditions, off-by-one, null deref, missing await, dropped guards, broken callers, races — via multi-angle finder passes (subagent fan-out with adversarial verification at max), at low|medium|high|xhigh|max effort. Defaults to xhigh with --fix, so it applies what it finds; --no-fix keeps it read-only. Do NOT use for a pure cleanup pass over code that is already correct — that is \u002Fsimple.","https:\u002F\u002Fgithub.com\u002Friventic\u002Fair2lean\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":58,"name":5,"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":59,"categories":60,"keywords":61,"publishedAt":19},"01M7DC0RCYWVX1QN9T9YB55SVY","https:\u002F\u002Fgithub.com\u002Friventic\u002Fair2lean\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsimple\u002FSKILL.md",[],[],{"skillNo":63,"name":52,"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":64,"categories":65,"keywords":66,"publishedAt":19},"01M7DC0QFBJXCKEWZ199BM6ZEY","https:\u002F\u002Fgithub.com\u002Friventic\u002Fair2lean\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freview\u002FSKILL.md",[],[]]