[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73AW1YYXZDNXXTP7ATZHH7C":3,"skill-same:01M73AW1YYXZDNXXTP7ATZHH7C":46},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M73AW1YYXZDNXXTP7ATZHH7C","review",null,"Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics.","kalash33\u002Fkstack","kalash33","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F90259149?v=4","01M7365X8Q0B73NYHA730SMZWN","Kalash Poddar","01M7365X9D0JK47C3Q0YCCK9Z2",0,"MIT","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fnginity-self-improving-agent\u002Fskills\u002Freview\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: \"review\"\ndescription: \"Analyze auto-memory for promotion candidates, stale entries, consolidation opportunities, and health metrics.\"\n---\n\n# \u002Fsi:review — Analyze Auto-Memory\n\nPerforms a comprehensive audit of Claude Code's auto-memory and produces actionable recommendations.\n\n## Usage\n\n```\n\u002Fsi:review                    # Full review\n\u002Fsi:review --quick            # Summary only (counts + top 3 candidates)\n\u002Fsi:review --stale            # Focus on stale\u002Foutdated entries\n\u002Fsi:review --candidates       # Show only promotion candidates\n```\n\n## What It Does\n\n### Step 1: Locate memory directory\n\n```bash\n# Find the project's auto-memory directory\nMEMORY_DIR=\"$HOME\u002F.claude\u002Fprojects\u002F$(pwd | sed 's|\u002F|%2F|g; s|%2F|\u002F|; s|^\u002F||')\u002Fmemory\"\n\n# Fallback: check common path patterns\n# ~\u002F.claude\u002Fprojects\u002F\u003Cuser>\u002F\u003Cproject>\u002Fmemory\u002F\n# ~\u002F.claude\u002Fprojects\u002F\u003Cabsolute-path>\u002Fmemory\u002F\n\n# List all memory files\nls -la \"$MEMORY_DIR\"\u002F\n```\n\nIf memory directory doesn't exist, report that auto-memory may be disabled. Suggest checking with `\u002Fmemory`.\n\n### Step 2: Read and analyze MEMORY.md\n\nRead the full `MEMORY.md` file. Count lines and check against the 200-line startup limit.\n\nAnalyze each entry for:\n\n1. **Recurrence indicators**\n   - Same concept appears multiple times (different wording)\n   - References to \"again\" or \"still\" or \"keeps happening\"\n   - Similar entries across topic files\n\n2. **Staleness indicators**\n   - References files that no longer exist (`find` to verify)\n   - Mentions outdated tools, versions, or commands\n   - Contradicts current CLAUDE.md rules\n\n3. **Consolidation opportunities**\n   - Multiple entries about the same topic (e.g., three lines about testing)\n   - Entries that could merge into one concise rule\n\n4. **Promotion candidates** — entries that meet ALL criteria:\n   - Appeared in 2+ sessions (check wording patterns)\n   - Not project-specific trivia (broadly useful)\n   - Actionable (can be written as a concrete rule)\n   - Not already in CLAUDE.md or `.claude\u002Frules\u002F`\n\n### Step 3: Read topic files\n\nIf `MEMORY.md` references or the directory contains additional files (`debugging.md`, `patterns.md`, etc.):\n- Read each one\n- Cross-reference with MEMORY.md for duplicates\n- Check for entries that belong in the main file (high value) vs. topic files (details)\n\n### Step 4: Cross-reference with CLAUDE.md\n\nRead the project's `CLAUDE.md` (if it exists) and compare:\n- Are there MEMORY.md entries that duplicate CLAUDE.md rules? (→ remove from memory)\n- Are there MEMORY.md entries that contradict CLAUDE.md? (→ flag conflict)\n- Are there MEMORY.md patterns not yet in CLAUDE.md that should be? (→ promotion candidate)\n\nAlso check `.claude\u002Frules\u002F` directory for existing scoped rules.\n\n### Step 5: Generate report\n\nOutput format:\n\n```\n📊 Auto-Memory Review\n\nMemory Health:\n  MEMORY.md:        {{lines}}\u002F200 lines ({{percent}}%)\n  Topic files:      {{count}} ({{names}})\n  CLAUDE.md:        {{lines}} lines\n  Rules:            {{count}} files in .claude\u002Frules\u002F\n\n🎯 Promotion Candidates ({{count}}):\n  1. \"{{pattern}}\" — seen {{n}}x, applies broadly\n     → Suggest: {{target}} (CLAUDE.md \u002F .claude\u002Frules\u002F{{name}}.md)\n  2. ...\n\n🗑️ Stale Entries ({{count}}):\n  1. Line {{n}}: \"{{entry}}\" — {{reason}}\n  2. ...\n\n🔄 Consolidation ({{count}} groups):\n  1. Lines {{a}}, {{b}}, {{c}} all about {{topic}} → merge into 1 entry\n  2. ...\n\n⚠️ Conflicts ({{count}}):\n  1. MEMORY.md line {{n}} contradicts CLAUDE.md: {{detail}}\n\n💡 Recommendations:\n  - {{actionable suggestion}}\n  - {{actionable suggestion}}\n```\n\n## When to Use\n\n- After completing a major feature or debugging session\n- When `\u002Fsi:status` shows MEMORY.md is over 150 lines\n- Weekly during active development\n- Before starting a new project phase\n- After onboarding a new team member (review what Claude learned)\n\n## Tips\n\n- Run `\u002Fsi:review --quick` frequently (low overhead)\n- Full review is most valuable when MEMORY.md is getting crowded\n- Act on promotion candidates promptly — they're proven patterns\n- Don't hesitate to delete stale entries — auto-memory will re-learn if needed\n","# \u002Fsi:review — Analyze Auto-Memory\n\nPerforms a comprehensive audit of Claude Code's auto-memory and produces actionable recommendations.\n\n## Usage\n\n```\n\u002Fsi:review                    # Full review\n\u002Fsi:review --quick            # Summary only (counts + top 3 candidates)\n\u002Fsi:review --stale            # Focus on stale\u002Foutdated entries\n\u002Fsi:review --candidates       # Show only promotion candidates\n```\n\n## What It Does\n\n### Step 1: Locate memory directory\n\n```bash\n# Find the project's auto-memory directory\nMEMORY_DIR=\"$HOME\u002F.claude\u002Fprojects\u002F$(pwd | sed 's|\u002F|%2F|g; s|%2F|\u002F|; s|^\u002F||')\u002Fmemory\"\n\n# Fallback: check common path patterns\n# ~\u002F.claude\u002Fprojects\u002F\u003Cuser>\u002F\u003Cproject>\u002Fmemory\u002F\n# ~\u002F.claude\u002Fprojects\u002F\u003Cabsolute-path>\u002Fmemory\u002F\n\n# List all memory files\nls -la \"$MEMORY_DIR\"\u002F\n```\n\nIf memory directory doesn't exist, report that auto-memory may be disabled. Suggest checking with `\u002Fmemory`.\n\n### Step 2: Read and analyze MEMORY.md\n\nRead the full `MEMORY.md` file. Count lines and check against the 200-line startup limit.\n\nAnalyze each entry for:\n\n1. **Recurrence indicators**\n   - Same concept appears multiple times (different wording)\n   - References to \"again\" or \"still\" or \"keeps happening\"\n   - Similar entries across topic files\n\n2. **Staleness indicators**\n   - References files that no longer exist (`find` to verify)\n   - Mentions outdated tools, versions, or commands\n   - Contradicts current CLAUDE.md rules\n\n3. **Consolidation opportunities**\n   - Multiple entries about the same topic (e.g., three lines about testing)\n   - Entries that could merge into one concise rule\n\n4. **Promotion candidates** — entries that meet ALL criteria:\n   - Appeared in 2+ sessions (check wording patterns)\n   - Not project-specific trivia (broadly useful)\n   - Actionable (can be written as a concrete rule)\n   - Not already in CLAUDE.md or `.claude\u002Frules\u002F`\n\n### Step 3: Read topic files\n\nIf `MEMORY.md` references or the directory contains additional files (`debugging.md`, `patterns.md`, etc.):\n- Read each one\n- Cross-reference with MEMORY.md for duplicates\n- Check for entries that belong in the main file (high value) vs. topic files (details)\n\n### Step 4: Cross-reference with CLAUDE.md\n\nRead the project's `CLAUDE.md` (if it exists) and compare:\n- Are there MEMORY.md entries that duplicate CLAUDE.md rules? (→ remove from memory)\n- Are there MEMORY.md entries that contradict CLAUDE.md? (→ flag conflict)\n- Are there MEMORY.md patterns not yet in CLAUDE.md that should be? (→ promotion candidate)\n\nAlso check `.claude\u002Frules\u002F` directory for existing scoped rules.\n\n### Step 5: Generate report\n\nOutput format:\n\n```\n📊 Auto-Memory Review\n\nMemory Health:\n  MEMORY.md:        {{lines}}\u002F200 lines ({{percent}}%)\n  Topic files:      {{count}} ({{names}})\n  CLAUDE.md:        {{lines}} lines\n  Rules:            {{count}} files in .claude\u002Frules\u002F\n\n🎯 Promotion Candidates ({{count}}):\n  1. \"{{pattern}}\" — seen {{n}}x, applies broadly\n     → Suggest: {{target}} (CLAUDE.md \u002F .claude\u002Frules\u002F{{name}}.md)\n  2. ...\n\n🗑️ Stale Entries ({{count}}):\n  1. Line {{n}}: \"{{entry}}\" — {{reason}}\n  2. ...\n\n🔄 Consolidation ({{count}} groups):\n  1. Lines {{a}}, {{b}}, {{c}} all about {{topic}} → merge into 1 entry\n  2. ...\n\n⚠️ Conflicts ({{count}}):\n  1. MEMORY.md line {{n}} contradicts CLAUDE.md: {{detail}}\n\n💡 Recommendations:\n  - {{actionable suggestion}}\n  - {{actionable suggestion}}\n```\n\n## When to Use\n\n- After completing a major feature or debugging session\n- When `\u002Fsi:status` shows MEMORY.md is over 150 lines\n- Weekly during active development\n- Before starting a new project phase\n- After onboarding a new team member (review what Claude learned)\n\n## Tips\n\n- Run `\u002Fsi:review --quick` frequently (low overhead)\n- Full review is most valuable when MEMORY.md is getting crowded\n- Act on promotion candidates promptly — they're proven patterns\n- Don't hesitate to delete stale entries — auto-memory will re-learn if needed\n",{"name":5,"description":7},"main","b30820b3248f6676d5389f0ccabd4e5250c9c536","skills\u002Fnginity-self-improving-agent\u002Fskills\u002Freview","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack","https:\u002F\u002Fgithub.com\u002Fkalash33","kalashpoddar.me","Tech-savvy Full Stack Developer 🚀 | Cybersecurity enthusiast 🔒 | Passionate about innovation and securing the digital world 🌐 | Let's code securely! 💻🔐","2026-05-20 04:11:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add kalash33\u002Fkstack --skill review",{"tool":38,"command":39},"bunx","bunx skills add kalash33\u002Fkstack --skill review",{"tool":41,"command":42},"pnpm","pnpm dlx skills add kalash33\u002Fkstack --skill review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fnginity-self-improving-agent\u002Fskills\u002Freview\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M73CFERCR43JCAP606E41EFB","zustand-store-ts","Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state\u002Faction separation. Use when building React state management, creating global stores, or implementing reacti...","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\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":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M73CFCMFVTAQEMTZ5HR10X8V","zoom-automation","Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-automation\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M73CFAA7EBWXJVXDQ1X555MB","zoho-crm-automation","Automate Zoho CRM tasks via Rube MCP (Composio): create\u002Fupdate records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzoho-crm-automation\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M73CF80XCM9K81567MJ8QZFW","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\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzod-validation-expert\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M73CF4YPMF3RA8ZJDXZSMD93","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M73CF2S25EN3XNAMKY47XHPS","zendesk-automation","Automate Zendesk tasks via Rube MCP (Composio): tickets, users, organizations, replies. Always search tools first for current schemas.","https:\u002F\u002Fgithub.com\u002Fkalash33\u002Fkstack\u002Fblob\u002Fmain\u002Fskills\u002Fzendesk-automation\u002FSKILL.md",[],[]]