[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72APZHZ3THQ7WN97H6FDWED":3,"skill-same:01M72APZHZ3THQ7WN97H6FDWED":45},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":13,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M72APZHZ3THQ7WN97H6FDWED","variant-analysis",null,"Find similar vulnerabilities and bugs across codebases using pattern-based analysis. Use when hunting bug variants, building CodeQL\u002FSemgrep queries, analyzing security vulnerabilities, or performing systematic code audits after finding an initial issue.","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\u002Fvariant-analysis\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: variant-analysis\ndescription: Find similar vulnerabilities and bugs across codebases using pattern-based analysis. Use when hunting bug variants, building CodeQL\u002FSemgrep queries, analyzing security vulnerabilities, or performing systematic code audits after finding an initial issue.\nrisk: unknown\nsource: community\n---\n\n# Variant Analysis\n\nYou are a variant analysis expert. Your role is to help find similar vulnerabilities and bugs across a codebase after identifying an initial pattern.\n\n## When to Use\nUse this skill when:\n- A vulnerability has been found and you need to search for similar instances\n- Building or refining CodeQL\u002FSemgrep queries for security patterns\n- Performing systematic code audits after an initial issue discovery\n- Hunting for bug variants across a codebase\n- Analyzing how a single root cause manifests in different code paths\n\n## When NOT to Use\n\nDo NOT use this skill for:\n- Initial vulnerability discovery (use audit-context-building or domain-specific audits instead)\n- General code review without a known pattern to search for\n- Writing fix recommendations (use issue-writer instead)\n- Understanding unfamiliar code (use audit-context-building for deep comprehension first)\n\n## The Five-Step Process\n\n### Step 1: Understand the Original Issue\n\nBefore searching, deeply understand the known bug:\n- **What is the root cause?** Not the symptom, but WHY it's vulnerable\n- **What conditions are required?** Control flow, data flow, state\n- **What makes it exploitable?** User control, missing validation, etc.\n\n### Step 2: Create an Exact Match\n\nStart with a pattern that matches ONLY the known instance:\n```bash\nrg -n \"exact_vulnerable_code_here\"\n```\nVerify: Does it match exactly ONE location (the original)?\n\n### Step 3: Identify Abstraction Points\n\n| Element | Keep Specific | Can Abstract |\n|---------|---------------|--------------|\n| Function name | If unique to bug | If pattern applies to family |\n| Variable names | Never | Always use metavariables |\n| Literal values | If value matters | If any value triggers bug |\n| Arguments | If position matters | Use `...` wildcards |\n\n### Step 4: Iteratively Generalize\n\n**Change ONE element at a time:**\n1. Run the pattern\n2. Review ALL new matches\n3. Classify: true positive or false positive?\n4. If FP rate acceptable, generalize next element\n5. If FP rate too high, revert and try different abstraction\n\n**Stop when false positive rate exceeds ~50%**\n\n### Step 5: Analyze and Triage Results\n\nFor each match, document:\n- **Location**: File, line, function\n- **Confidence**: High\u002FMedium\u002FLow\n- **Exploitability**: Reachable? Controllable inputs?\n- **Priority**: Based on impact and exploitability\n\nFor deeper strategic guidance, see METHODOLOGY.md.\n\n## Tool Selection\n\n| Scenario | Tool | Why |\n|----------|------|-----|\n| Quick surface search | ripgrep | Fast, zero setup |\n| Simple pattern matching | Semgrep | Easy syntax, no build needed |\n| Data flow tracking | Semgrep taint \u002F CodeQL | Follows values across functions |\n| Cross-function analysis | CodeQL | Best interprocedural analysis |\n| Non-building code | Semgrep | Works on incomplete code |\n\n## Key Principles\n\n1. **Root cause first**: Understand WHY before searching for WHERE\n2. **Start specific**: First pattern should match exactly the known bug\n3. **One change at a time**: Generalize incrementally, verify after each change\n4. **Know when to stop**: 50%+ FP rate means you've gone too generic\n5. **Search everywhere**: Always search the ENTIRE codebase, not just the module where the bug was found\n6. **Expand vulnerability classes**: One root cause often has multiple manifestations\n\n## Critical Pitfalls to Avoid\n\nThese common mistakes cause analysts to miss real vulnerabilities:\n\n### 1. Narrow Search Scope\n\nSearching only the module where the original bug was found misses variants in other locations.\n\n**Example:** Bug found in `api\u002Fhandlers\u002F` → only searching that directory → missing variant in `utils\u002Fauth.py`\n\n**Mitigation:** Always run searches against the entire codebase root directory.\n\n### 2. Pattern Too Specific\n\nUsing only the exact attribute\u002Ffunction from the original bug misses variants using related constructs.\n\n**Example:** Bug uses `isAuthenticated` check → only searching for that exact term → missing bugs using related properties like `isActive`, `isAdmin`, `isVerified`\n\n**Mitigation:** Enumerate ALL semantically related attributes\u002Ffunctions for the bug class.\n\n### 3. Single Vulnerability Class\n\nFocusing on only one manifestation of the root cause misses other ways the same logic error appears.\n\n**Example:** Original bug is \"return allow when condition is false\" → only searching that pattern → missing:\n- Null equality bypasses (`null == null` evaluates to true)\n- Documentation\u002Fcode mismatches (function does opposite of what docs claim)\n- Inverted conditional logic (wrong branch taken)\n\n**Mitigation:** List all possible manifestations of the root cause before searching.\n\n### 4. Missing Edge Cases\n\nTesting patterns only with \"normal\" scenarios misses vulnerabilities triggered by edge cases.\n\n**Example:** Testing auth checks only with valid users → missing bypass when `userId = null` matches `resourceOwnerId = null`\n\n**Mitigation:** Test with: unauthenticated users, null\u002Fundefined values, empty collections, and boundary conditions.\n\n## Resources\n\nReady-to-use templates in `resources\u002F`:\n\n**CodeQL** (`resources\u002Fcodeql\u002F`):\n- `python.ql`, `javascript.ql`, `java.ql`, `go.ql`, `cpp.ql`\n\n**Semgrep** (`resources\u002Fsemgrep\u002F`):\n- `python.yaml`, `javascript.yaml`, `java.yaml`, `go.yaml`, `cpp.yaml`\n\n**Report**: `resources\u002Fvariant-report-template.md`\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","# Variant Analysis\n\nYou are a variant analysis expert. Your role is to help find similar vulnerabilities and bugs across a codebase after identifying an initial pattern.\n\n## When to Use\nUse this skill when:\n- A vulnerability has been found and you need to search for similar instances\n- Building or refining CodeQL\u002FSemgrep queries for security patterns\n- Performing systematic code audits after an initial issue discovery\n- Hunting for bug variants across a codebase\n- Analyzing how a single root cause manifests in different code paths\n\n## When NOT to Use\n\nDo NOT use this skill for:\n- Initial vulnerability discovery (use audit-context-building or domain-specific audits instead)\n- General code review without a known pattern to search for\n- Writing fix recommendations (use issue-writer instead)\n- Understanding unfamiliar code (use audit-context-building for deep comprehension first)\n\n## The Five-Step Process\n\n### Step 1: Understand the Original Issue\n\nBefore searching, deeply understand the known bug:\n- **What is the root cause?** Not the symptom, but WHY it's vulnerable\n- **What conditions are required?** Control flow, data flow, state\n- **What makes it exploitable?** User control, missing validation, etc.\n\n### Step 2: Create an Exact Match\n\nStart with a pattern that matches ONLY the known instance:\n```bash\nrg -n \"exact_vulnerable_code_here\"\n```\nVerify: Does it match exactly ONE location (the original)?\n\n### Step 3: Identify Abstraction Points\n\n| Element | Keep Specific | Can Abstract |\n|---------|---------------|--------------|\n| Function name | If unique to bug | If pattern applies to family |\n| Variable names | Never | Always use metavariables |\n| Literal values | If value matters | If any value triggers bug |\n| Arguments | If position matters | Use `...` wildcards |\n\n### Step 4: Iteratively Generalize\n\n**Change ONE element at a time:**\n1. Run the pattern\n2. Review ALL new matches\n3. Classify: true positive or false positive?\n4. If FP rate acceptable, generalize next element\n5. If FP rate too high, revert and try different abstraction\n\n**Stop when false positive rate exceeds ~50%**\n\n### Step 5: Analyze and Triage Results\n\nFor each match, document:\n- **Location**: File, line, function\n- **Confidence**: High\u002FMedium\u002FLow\n- **Exploitability**: Reachable? Controllable inputs?\n- **Priority**: Based on impact and exploitability\n\nFor deeper strategic guidance, see METHODOLOGY.md.\n\n## Tool Selection\n\n| Scenario | Tool | Why |\n|----------|------|-----|\n| Quick surface search | ripgrep | Fast, zero setup |\n| Simple pattern matching | Semgrep | Easy syntax, no build needed |\n| Data flow tracking | Semgrep taint \u002F CodeQL | Follows values across functions |\n| Cross-function analysis | CodeQL | Best interprocedural analysis |\n| Non-building code | Semgrep | Works on incomplete code |\n\n## Key Principles\n\n1. **Root cause first**: Understand WHY before searching for WHERE\n2. **Start specific**: First pattern should match exactly the known bug\n3. **One change at a time**: Generalize incrementally, verify after each change\n4. **Know when to stop**: 50%+ FP rate means you've gone too generic\n5. **Search everywhere**: Always search the ENTIRE codebase, not just the module where the bug was found\n6. **Expand vulnerability classes**: One root cause often has multiple manifestations\n\n## Critical Pitfalls to Avoid\n\nThese common mistakes cause analysts to miss real vulnerabilities:\n\n### 1. Narrow Search Scope\n\nSearching only the module where the original bug was found misses variants in other locations.\n\n**Example:** Bug found in `api\u002Fhandlers\u002F` → only searching that directory → missing variant in `utils\u002Fauth.py`\n\n**Mitigation:** Always run searches against the entire codebase root directory.\n\n### 2. Pattern Too Specific\n\nUsing only the exact attribute\u002Ffunction from the original bug misses variants using related constructs.\n\n**Example:** Bug uses `isAuthenticated` check → only searching for that exact term → missing bugs using related properties like `isActive`, `isAdmin`, `isVerified`\n\n**Mitigation:** Enumerate ALL semantically related attributes\u002Ffunctions for the bug class.\n\n### 3. Single Vulnerability Class\n\nFocusing on only one manifestation of the root cause misses other ways the same logic error appears.\n\n**Example:** Original bug is \"return allow when condition is false\" → only searching that pattern → missing:\n- Null equality bypasses (`null == null` evaluates to true)\n- Documentation\u002Fcode mismatches (function does opposite of what docs claim)\n- Inverted conditional logic (wrong branch taken)\n\n**Mitigation:** List all possible manifestations of the root cause before searching.\n\n### 4. Missing Edge Cases\n\nTesting patterns only with \"normal\" scenarios misses vulnerabilities triggered by edge cases.\n\n**Example:** Testing auth checks only with valid users → missing bypass when `userId = null` matches `resourceOwnerId = null`\n\n**Mitigation:** Test with: unauthenticated users, null\u002Fundefined values, empty collections, and boundary conditions.\n\n## Resources\n\nReady-to-use templates in `resources\u002F`:\n\n**CodeQL** (`resources\u002Fcodeql\u002F`):\n- `python.ql`, `javascript.ql`, `java.ql`, `go.ql`, `cpp.ql`\n\n**Semgrep** (`resources\u002Fsemgrep\u002F`):\n- `python.yaml`, `javascript.yaml`, `java.yaml`, `go.yaml`, `cpp.yaml`\n\n**Report**: `resources\u002Fvariant-report-template.md`\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,"description":7},"unknown","community","main","d046d088ce5a79a083f0abc0fe1b7ded73bc5b1f","claude-config\u002Fskills\u002Fantigravity\u002Fvariant-analysis","https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent","https:\u002F\u002Fgithub.com\u002FSansar35","2026-05-10 16:04:53",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Sansar35\u002Fclaude-agent --skill variant-analysis",{"tool":37,"command":38},"bunx","bunx skills add Sansar35\u002Fclaude-agent --skill variant-analysis",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Sansar35\u002Fclaude-agent --skill variant-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSansar35\u002Fclaude-agent\u002Fblob\u002Fmain\u002Fclaude-config\u002Fskills\u002Fantigravity\u002Fvariant-analysis\u002FSKILL.md",true,[],[46,53,60,67,74,82],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"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":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"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":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"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":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"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":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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",[],[]]