[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72A67RMPC4ZWB7TKFP3Z0WT":3,"skill-same:01M72A67RMPC4ZWB7TKFP3Z0WT":46},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":13,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M72A67RMPC4ZWB7TKFP3Z0WT","simplify-code",null,"Review a diff for clarity and safe simplifications, then optionally apply low-risk fixes.","Sansar35\u002Fclaude-agent","Sansar35","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F145020281?v=4","01M724CQ2SCC86MGNSD87D0D4K","01M724CQ3965G9WJ3QXE3AJ5YY",1,"MIT","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fantigravity\u002Fsimplify-code\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: simplify-code\ndescription: \"Review a diff for clarity and safe simplifications, then optionally apply low-risk fixes.\"\nrisk: safe\nsource: \"Dimillian\u002FSkills (MIT)\"\ndate_added: \"2026-03-25\"\n---\n\n# Simplify Code\n\nReview changed code for reuse, quality, efficiency, and clarity issues. Use Codex sub-agents to review in parallel, then optionally apply only high-confidence, behavior-preserving fixes.\n\n## When to Use\n- When the user asks to simplify, clean up, refactor, or review changed code.\n- When you want high-confidence, behavior-preserving improvements on a scoped diff.\n\n## Modes\n\nChoose the mode from the user's request:\n\n- `review-only`: user asks to review, audit, or check the changes\n- `safe-fixes`: user asks to simplify, clean up, or refactor the changes\n- `fix-and-validate`: same as `safe-fixes`, but also run the smallest relevant validation after edits\n\nIf the user does not specify, default to:\n\n- `review-only` for \"review\", \"audit\", or \"check\"\n- `safe-fixes` for \"simplify\", \"clean up\", or \"refactor\"\n\n## Step 1: Determine the Scope and Diff Command\n\nPrefer this scope order:\n\n1. Files or paths explicitly named by the user\n2. Current git changes\n3. Files edited earlier in the current Codex turn\n4. Most recently modified tracked files, only if the user asked for a review but there is no diff\n\nIf there is no clear scope, stop and say so briefly.\n\nWhen using git changes, determine the smallest correct diff command based on the repo state:\n\n- unstaged work: `git diff`\n- staged work: `git diff --cached`\n- branch or commit comparison explicitly requested by the user: use that exact diff target\n- mixed staged and unstaged work: review both\n\nDo not assume `git diff HEAD` is the right default when a smaller diff is available.\n\nBefore reviewing standards or applying fixes, read the repo's local instruction files and relevant project docs for the touched area. Prefer the closest applicable guidance, such as:\n\n- `AGENTS.md`\n- repo workflow docs\n- architecture or style docs for the touched module\n\nUse those instructions to distinguish real issues from intentional local patterns.\n\n## Step 2: Launch Four Review Sub-Agents in Parallel\n\nUse Codex sub-agents when the scope is large enough for parallel review to help. For a tiny diff or one very small file, it is acceptable to review locally instead.\n\nWhen spawning sub-agents:\n\n- give each sub-agent the same scope\n- tell each sub-agent to inspect only its assigned review role\n- ask for concise, structured findings only\n- ask each sub-agent to report file, line or symbol, problem, recommended fix, and confidence\n\nUse four review roles.\n\n### Sub-Agent 1: Code Reuse Review\n\nReview the changes for reuse opportunities:\n\n1. Search for existing helpers, utilities, or shared abstractions that already solve the same problem.\n2. Flag duplicated functions or near-duplicate logic introduced in the change.\n3. Flag inline logic that should call an existing helper instead of re-implementing it.\n\nRecommended sub-agent role: `explorer` for broad codebase lookup, or `reviewer` if a stronger review pass is more useful than wide search.\n\n### Sub-Agent 2: Code Quality Review\n\nReview the same changes for code quality issues:\n\n1. Redundant state, cached values, or derived values stored unnecessarily\n2. Parameter sprawl caused by threading new arguments through existing call chains\n3. Copy-paste with slight variation that should become a shared abstraction\n4. Leaky abstractions or ownership violations across module boundaries\n5. Stringly-typed values where existing typed contracts, enums, or constants already exist\n\nRecommended sub-agent role: `reviewer`\n\n### Sub-Agent 3: Efficiency Review\n\nReview the same changes for efficiency issues:\n\n1. Repeated work, duplicate reads, duplicate API calls, or unnecessary recomputation\n2. Sequential work that could safely run concurrently\n3. New work added to startup, render, request, or other hot paths without clear need\n4. Pre-checks for existence when the operation itself can be attempted directly and errors handled\n5. Memory growth, missing cleanup, or listener\u002Fsubscription leaks\n6. Overly broad reads or scans when the code only needs a subset\n\nRecommended sub-agent role: `reviewer`\n\n### Sub-Agent 4: Clarity and Standards Review\n\nReview the same changes for clarity, local standards, and balance:\n\n1. Violations of local project conventions or module patterns\n2. Unnecessary complexity, deep nesting, weak names, or redundant comments\n3. Overly compact or clever code that reduces readability\n4. Over-simplification that collapses separate concerns into one unclear unit\n5. Dead code, dead abstractions, or indirection without value\n\nRecommended sub-agent role: `reviewer`\n\nOnly report issues that materially improve maintainability, correctness, or cost. Do not churn code just to make it look different.\n\n## Step 3: Aggregate Findings\n\nWait for all review sub-agents to complete, then merge their findings.\n\nNormalize findings into this shape:\n\n1. File and line or nearest symbol\n2. Category: reuse, quality, efficiency, or clarity\n3. Why it is a problem\n4. Recommended fix\n5. Confidence: high, medium, or low\n\nDiscard weak, duplicative, or instruction-conflicting findings before editing.\n\n## Step 4: Fix Issues Carefully\n\nIn `review-only` mode, stop after reporting findings.\n\nIn `safe-fixes` or `fix-and-validate` mode:\n\n- Apply only high-confidence, behavior-preserving fixes\n- Skip subjective refactors that need product or architectural judgment\n- Preserve local patterns when they are intentional or instruction-backed\n- Keep edits scoped to the reviewed files unless a small adjacent change is required to complete the fix correctly\n\nPrefer fixes like:\n\n- replacing duplicated code with an existing helper\n- removing redundant state or dead code\n- simplifying control flow without changing behavior\n- narrowing overly broad operations\n- renaming unclear locals when the scope is contained\n\nDo not stage, commit, or push changes as part of this skill.\n\n## Step 5: Validate When Required\n\nIn `fix-and-validate` mode, run the smallest relevant validation for the touched scope after edits.\n\nExamples:\n\n- targeted tests for the touched module\n- typecheck or compile for the touched target\n- formatter or lint check if that is the project's real safety gate\n\nPrefer fast, scoped validation over full-suite runs unless the change breadth justifies more.\n\nIf validation is skipped because the user asked not to run it, say so explicitly.\n\n## Step 6: Summarize Outcome\n\nClose with a brief result:\n\n- what was reviewed\n- what was fixed, if anything\n- what was intentionally left alone\n- whether validation ran\n\nIf the code is already clean for this rubric, say that directly instead of manufacturing edits.\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","# Simplify Code\n\nReview changed code for reuse, quality, efficiency, and clarity issues. Use Codex sub-agents to review in parallel, then optionally apply only high-confidence, behavior-preserving fixes.\n\n## When to Use\n- When the user asks to simplify, clean up, refactor, or review changed code.\n- When you want high-confidence, behavior-preserving improvements on a scoped diff.\n\n## Modes\n\nChoose the mode from the user's request:\n\n- `review-only`: user asks to review, audit, or check the changes\n- `safe-fixes`: user asks to simplify, clean up, or refactor the changes\n- `fix-and-validate`: same as `safe-fixes`, but also run the smallest relevant validation after edits\n\nIf the user does not specify, default to:\n\n- `review-only` for \"review\", \"audit\", or \"check\"\n- `safe-fixes` for \"simplify\", \"clean up\", or \"refactor\"\n\n## Step 1: Determine the Scope and Diff Command\n\nPrefer this scope order:\n\n1. Files or paths explicitly named by the user\n2. Current git changes\n3. Files edited earlier in the current Codex turn\n4. Most recently modified tracked files, only if the user asked for a review but there is no diff\n\nIf there is no clear scope, stop and say so briefly.\n\nWhen using git changes, determine the smallest correct diff command based on the repo state:\n\n- unstaged work: `git diff`\n- staged work: `git diff --cached`\n- branch or commit comparison explicitly requested by the user: use that exact diff target\n- mixed staged and unstaged work: review both\n\nDo not assume `git diff HEAD` is the right default when a smaller diff is available.\n\nBefore reviewing standards or applying fixes, read the repo's local instruction files and relevant project docs for the touched area. Prefer the closest applicable guidance, such as:\n\n- `AGENTS.md`\n- repo workflow docs\n- architecture or style docs for the touched module\n\nUse those instructions to distinguish real issues from intentional local patterns.\n\n## Step 2: Launch Four Review Sub-Agents in Parallel\n\nUse Codex sub-agents when the scope is large enough for parallel review to help. For a tiny diff or one very small file, it is acceptable to review locally instead.\n\nWhen spawning sub-agents:\n\n- give each sub-agent the same scope\n- tell each sub-agent to inspect only its assigned review role\n- ask for concise, structured findings only\n- ask each sub-agent to report file, line or symbol, problem, recommended fix, and confidence\n\nUse four review roles.\n\n### Sub-Agent 1: Code Reuse Review\n\nReview the changes for reuse opportunities:\n\n1. Search for existing helpers, utilities, or shared abstractions that already solve the same problem.\n2. Flag duplicated functions or near-duplicate logic introduced in the change.\n3. Flag inline logic that should call an existing helper instead of re-implementing it.\n\nRecommended sub-agent role: `explorer` for broad codebase lookup, or `reviewer` if a stronger review pass is more useful than wide search.\n\n### Sub-Agent 2: Code Quality Review\n\nReview the same changes for code quality issues:\n\n1. Redundant state, cached values, or derived values stored unnecessarily\n2. Parameter sprawl caused by threading new arguments through existing call chains\n3. Copy-paste with slight variation that should become a shared abstraction\n4. Leaky abstractions or ownership violations across module boundaries\n5. Stringly-typed values where existing typed contracts, enums, or constants already exist\n\nRecommended sub-agent role: `reviewer`\n\n### Sub-Agent 3: Efficiency Review\n\nReview the same changes for efficiency issues:\n\n1. Repeated work, duplicate reads, duplicate API calls, or unnecessary recomputation\n2. Sequential work that could safely run concurrently\n3. New work added to startup, render, request, or other hot paths without clear need\n4. Pre-checks for existence when the operation itself can be attempted directly and errors handled\n5. Memory growth, missing cleanup, or listener\u002Fsubscription leaks\n6. Overly broad reads or scans when the code only needs a subset\n\nRecommended sub-agent role: `reviewer`\n\n### Sub-Agent 4: Clarity and Standards Review\n\nReview the same changes for clarity, local standards, and balance:\n\n1. Violations of local project conventions or module patterns\n2. Unnecessary complexity, deep nesting, weak names, or redundant comments\n3. Overly compact or clever code that reduces readability\n4. Over-simplification that collapses separate concerns into one unclear unit\n5. Dead code, dead abstractions, or indirection without value\n\nRecommended sub-agent role: `reviewer`\n\nOnly report issues that materially improve maintainability, correctness, or cost. Do not churn code just to make it look different.\n\n## Step 3: Aggregate Findings\n\nWait for all review sub-agents to complete, then merge their findings.\n\nNormalize findings into this shape:\n\n1. File and line or nearest symbol\n2. Category: reuse, quality, efficiency, or clarity\n3. Why it is a problem\n4. Recommended fix\n5. Confidence: high, medium, or low\n\nDiscard weak, duplicative, or instruction-conflicting findings before editing.\n\n## Step 4: Fix Issues Carefully\n\nIn `review-only` mode, stop after reporting findings.\n\nIn `safe-fixes` or `fix-and-validate` mode:\n\n- Apply only high-confidence, behavior-preserving fixes\n- Skip subjective refactors that need product or architectural judgment\n- Preserve local patterns when they are intentional or instruction-backed\n- Keep edits scoped to the reviewed files unless a small adjacent change is required to complete the fix correctly\n\nPrefer fixes like:\n\n- replacing duplicated code with an existing helper\n- removing redundant state or dead code\n- simplifying control flow without changing behavior\n- narrowing overly broad operations\n- renaming unclear locals when the scope is contained\n\nDo not stage, commit, or push changes as part of this skill.\n\n## Step 5: Validate When Required\n\nIn `fix-and-validate` mode, run the smallest relevant validation for the touched scope after edits.\n\nExamples:\n\n- targeted tests for the touched module\n- typecheck or compile for the touched target\n- formatter or lint check if that is the project's real safety gate\n\nPrefer fast, scoped validation over full-suite runs unless the change breadth justifies more.\n\nIf validation is skipped because the user asked not to run it, say so explicitly.\n\n## Step 6: Summarize Outcome\n\nClose with a brief result:\n\n- what was reviewed\n- what was fixed, if anything\n- what was intentionally left alone\n- whether validation ran\n\nIf the code is already clean for this rubric, say that directly instead of manufacturing edits.\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n",{"name":5,"risk":23,"source":24,"date_added":25,"description":7},"safe","Dimillian\u002FSkills (MIT)","2026-03-25","main","d046d088ce5a79a083f0abc0fe1b7ded73bc5b1f","claude-config\u002Fskills\u002Fantigravity\u002Fsimplify-code","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent","https:\u002F\u002Fgithub.com\u002FSansar35","2026-05-10 16:04:53",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Sansar35\u002Fclaude-agent --skill simplify-code",{"tool":38,"command":39},"bunx","bunx skills add Sansar35\u002Fclaude-agent --skill simplify-code",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Sansar35\u002Fclaude-agent --skill simplify-code","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fantigravity\u002Fsimplify-code\u002FSKILL.md",true,[],[47,54,61,68,75,83],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":18},"01M72DVAN1JYEA302MT0C5MGD6","zustand-store-ts","Create Zustand stores following established patterns with proper TypeScript types and middleware.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":18},"01M72DV8J5NBRRM4RPDFRV95N7","zod-validation-expert","Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzod-validation-expert\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M72DV5EMHW0BHP9BZ167MDCB","zinc-database","Access ZINC (230M+ purchasable compounds). Search by ZINC ID\u002FSMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzinc-database\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M72DV216QY0E693ZPEVQ0DBS","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M72DTXQREMCRKA8NHCVKHN4W","zapier-workflows","Manage and trigger pre-built Zapier workflows and MCP tool orchestration. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to \"run\" any process. Also handles Perplexity-based research and Google Sheets data tracking.","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-workflows\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-workflows\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M72DTT17TBSJ0Y8J2XZ4C9TZ","zapier-make-patterns","No-code automation democratizes workflow building. Zapier and Make (formerly Integromat) let non-developers automate business processes without writing code. But no-code doesn't mean no-complexity - these platforms have their own patterns, pitfalls, and breaking points.  This skill covers when to use which platform, how to build reliable automations, and when to graduate to code-based solutions. Key insight: Zapier optimizes for simplicity and integrations (7000+ apps), Make optimizes for power","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fzapier-make-patterns\u002FSKILL.md",[],[]]