[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7359XZ5SAX0T4H9VCZ7GDY3":3,"skill-same:01M7359XZ5SAX0T4H9VCZ7GDY3":51},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":35,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":37,"install":38,"resources":50},"01M7359XZ5SAX0T4H9VCZ7GDY3","simplify",null,"Prune dead code paths and logic.","Morrison-Lab\u002Fai-config","Morrison-Lab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F104235520?v=4","01M734G0451S2G35MN4HFQK7XP","Morrison Lab","01M734G059BYFDFQA8YTPDGPMH",4,"MIT","https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fsimplify\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: simplify\ndescription: \"Prune dead code paths and logic.\"\nuser-invocable: true\nallowed-tools:\n  - Bash\n  - Read\n  - Edit\n  - Write\n---\n\n# simplify\n\nAfter any change that narrows the invocation context (e.g., a job now only\nruns under branch pipelines, a function is only called from one site, a\nconfig option is removed), sweep for dead code that the change made\nunreachable.\n\n## When this fires\n\n- Automatically after any refactor that changes how code is invoked\n- When asked to \"simplify\", \"clean up\", \"prune dead code\"\n- During review when spotting unreachable paths\n- After removing a feature flag or configuration option\n\n## What to look for\n\n1. **Dead branches** — `if` conditions that can never be true given the new\n   invocation context. Example: checking for `merge_request_event` when the\n   job only runs on branch pipelines.\n\n2. **Unnecessary fallbacks** — `${VAR:-fallback}` where `VAR` is always set\n   in the current context. Simplify to just `$VAR`.\n\n3. **Redundant guards** — checks that duplicate a constraint already enforced\n   by the caller (e.g., a rule in the CI template already ensures an MR\n   exists, so the script's \"no MR found\" check is belt-and-suspenders — keep\n   it for defense-in-depth, but remove the *comment* claiming it's the\n   primary gate).\n\n4. **Vestigial comments** — comments describing behavior that no longer\n   applies. Stale comments are worse than no comments.\n\n5. **Collapsed conditionals** — an `if\u002Felse` where one branch is now\n   unreachable can be collapsed to just the reachable branch.\n\n6. **Unused variables** — assignments whose values are never read downstream.\n\n## Decision criteria\n\n| Situation | Action |\n|-----------|--------|\n| Code is unreachable AND no consumer could reach it | Remove |\n| Code is unreachable under shipped config but a consumer *could* override | Keep with a comment explaining why |\n| Fallback value is never used but adds clarity | Keep (readability > minimalism) |\n| Comment describes removed behavior | Remove or rewrite |\n| Defense-in-depth guard (redundant but safe) | Keep the guard, update the comment |\n\n## Process\n\n1. Identify the narrowed context (what changed about how this code is called)\n2. Trace each conditional\u002Ffallback to determine if it's still reachable\n3. For each dead path: remove it or document why it's retained\n4. Run syntax checks \u002F tests after pruning\n5. Note the simplification in the commit message (e.g., \"remove unreachable\n   merge_request_event path — job now only runs on branch pipelines\")\n\n## Principle\n\n> The best code is code that doesn't exist. Every line is a liability —\n> it must be read, understood, maintained, and tested. Remove what you can;\n> document what you keep.\n\n## Relationship to other skills\n\n- **`shared\u002Fworkflow\u002Fchallenge-unnecessary-complexity.md`** — the standing\n  review-time counterpart. This skill only prunes *dead* code made\n  unreachable by a narrowed invocation context, triggered after a specific\n  refactor; the fragment is the broader \"flag complexity in\n  otherwise-correct, reachable content\" rule folded into every review pass\n  (prose and math too, not just code). Run this skill when code just\n  became unreachable; the fragment's check applies continuously, to code\n  that is fully reachable but more complex than it needs to be.\n- **`tidy`** — the broader on-demand code audit (5 axes, one of which is\n  \"Simplify\"); this skill is narrower and specifically about dead-code\n  removal after a context change.\n- **`prune-dead-code`** (`pdc`) — the whole-repo audit counterpart for finding\n  and deleting provably unreferenced functions, files, configs, and stale docs\n  across the codebase, whereas this skill specifically sweeps unreachable paths\n  locally after a context-narrowing change.\n- **`code-editor` agent** ([`.claude\u002Fagents\u002Fcode-editor.md`](..\u002F..\u002F.claude\u002Fagents\u002Fcode-editor.md)) --- the dedicated code editor subagent that enforces coding style guidelines and refactors implementations cleanly.\n\n","# simplify\n\nAfter any change that narrows the invocation context (e.g., a job now only\nruns under branch pipelines, a function is only called from one site, a\nconfig option is removed), sweep for dead code that the change made\nunreachable.\n\n## When this fires\n\n- Automatically after any refactor that changes how code is invoked\n- When asked to \"simplify\", \"clean up\", \"prune dead code\"\n- During review when spotting unreachable paths\n- After removing a feature flag or configuration option\n\n## What to look for\n\n1. **Dead branches** — `if` conditions that can never be true given the new\n   invocation context. Example: checking for `merge_request_event` when the\n   job only runs on branch pipelines.\n\n2. **Unnecessary fallbacks** — `${VAR:-fallback}` where `VAR` is always set\n   in the current context. Simplify to just `$VAR`.\n\n3. **Redundant guards** — checks that duplicate a constraint already enforced\n   by the caller (e.g., a rule in the CI template already ensures an MR\n   exists, so the script's \"no MR found\" check is belt-and-suspenders — keep\n   it for defense-in-depth, but remove the *comment* claiming it's the\n   primary gate).\n\n4. **Vestigial comments** — comments describing behavior that no longer\n   applies. Stale comments are worse than no comments.\n\n5. **Collapsed conditionals** — an `if\u002Felse` where one branch is now\n   unreachable can be collapsed to just the reachable branch.\n\n6. **Unused variables** — assignments whose values are never read downstream.\n\n## Decision criteria\n\n| Situation | Action |\n|-----------|--------|\n| Code is unreachable AND no consumer could reach it | Remove |\n| Code is unreachable under shipped config but a consumer *could* override | Keep with a comment explaining why |\n| Fallback value is never used but adds clarity | Keep (readability > minimalism) |\n| Comment describes removed behavior | Remove or rewrite |\n| Defense-in-depth guard (redundant but safe) | Keep the guard, update the comment |\n\n## Process\n\n1. Identify the narrowed context (what changed about how this code is called)\n2. Trace each conditional\u002Ffallback to determine if it's still reachable\n3. For each dead path: remove it or document why it's retained\n4. Run syntax checks \u002F tests after pruning\n5. Note the simplification in the commit message (e.g., \"remove unreachable\n   merge_request_event path — job now only runs on branch pipelines\")\n\n## Principle\n\n> The best code is code that doesn't exist. Every line is a liability —\n> it must be read, understood, maintained, and tested. Remove what you can;\n> document what you keep.\n\n## Relationship to other skills\n\n- **`shared\u002Fworkflow\u002Fchallenge-unnecessary-complexity.md`** — the standing\n  review-time counterpart. This skill only prunes *dead* code made\n  unreachable by a narrowed invocation context, triggered after a specific\n  refactor; the fragment is the broader \"flag complexity in\n  otherwise-correct, reachable content\" rule folded into every review pass\n  (prose and math too, not just code). Run this skill when code just\n  became unreachable; the fragment's check applies continuously, to code\n  that is fully reachable but more complex than it needs to be.\n- **`tidy`** — the broader on-demand code audit (5 axes, one of which is\n  \"Simplify\"); this skill is narrower and specifically about dead-code\n  removal after a context change.\n- **`prune-dead-code`** (`pdc`) — the whole-repo audit counterpart for finding\n  and deleting provably unreferenced functions, files, configs, and stale docs\n  across the codebase, whereas this skill specifically sweeps unreachable paths\n  locally after a context-narrowing change.\n- **`code-editor` agent** ([`.claude\u002Fagents\u002Fcode-editor.md`](..\u002F..\u002F.claude\u002Fagents\u002Fcode-editor.md)) --- the dedicated code editor subagent that enforces coding style guidelines and refactors implementations cleanly.\n\n",{"name":5,"description":7,"allowed-tools":24,"user-invocable":29},[25,26,27,28],"Bash","Read","Edit","Write",true,"main","0f720481f8ce3b3d9fef485f6e230d8b3035748e","skills\u002Fsimplify",1,"https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config","https:\u002F\u002Fmorrison-lab.github.io\u002Fai-config\u002F","https:\u002F\u002Fgithub.com\u002FMorrison-Lab","2026-11-15 04:39:15",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":29},[40,43,46],{"tool":41,"command":42},"npx","npx skills add Morrison-Lab\u002Fai-config --skill simplify",{"tool":44,"command":45},"bunx","bunx skills add Morrison-Lab\u002Fai-config --skill simplify",{"tool":47,"command":48},"pnpm","pnpm dlx skills add Morrison-Lab\u002Fai-config --skill simplify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fsimplify\u002FSKILL.md",[],[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M735BVYCGR5VEC65AFDVSNKW","wrap-up","End-of-session verification and UMS.","https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M735BTH469T1CQ8G2Q9GENCR","workaround-watcher","Watch upstream issue for fix.","https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fworkaround-watcher\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"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},"01M735BRKZWFANSQ0GM380B4TD","wn","→ whats-next.","https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fwn\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},"01M735BPE9V830B3B6NGXQ56J6","whats-next","Recommend concrete next step or action.","https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fwhats-next\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},"01M735BMHQ60EAD5B7QAWXC5A0","wait-for-results","Wait for pipeline\u002FCI results.","https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fwait-for-results\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M735BKGZHPN1PEMJ7YBD5VJ8","wai","→ send-notes.","https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fwai\u002FSKILL.md",[],[]]