[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73DRSP3D4GAPGX3E8KM0M5X":3,"skill-same:01M73DRSP3D4GAPGX3E8KM0M5X":52},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M73DRSP3D4GAPGX3E8KM0M5X","memory-review",null,"Review all memory layers, detect stale\u002Fduplicate\u002Fconflicting entries, and propose promotions between layers. Use when the user says \"clean up memory\", \"review what I've saved\", \"memory is getting messy\", \"what's in my memory\", \"organize my notes\", \"promote this to CLAUDE.md\", \"memory audit\", or after a long session with many \u002Fremember calls. Do NOT modify any files without explicit user approval.","Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"MIT","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fmemory-review\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: memory-review\ndescription: >\n  Review all memory layers, detect stale\u002Fduplicate\u002Fconflicting entries,\n  and propose promotions between layers. Use when the user says \"clean up memory\",\n  \"review what I've saved\", \"memory is getting messy\", \"what's in my memory\",\n  \"organize my notes\", \"promote this to CLAUDE.md\", \"memory audit\",\n  or after a long session with many \u002Fremember calls.\n  Do NOT modify any files without explicit user approval.\norigin: adapted:NanmiCoder\u002Fcc-haha (remember.ts)\nlicense: MIT\nversion: 1.0.0\ncompatibility: \"yana-ai >= 0.14.0. Reads: CLAUDE.md, CLAUDE.local.md, auto-memory, L1\u002FL2.\"\n---\n\n\u003C!-- Adapted from cc-haha\u002Fsrc\u002Fskills\u002Fbundled\u002Fremember.ts (MIT). Core pattern: collect → classify → propose → await approval. Changes: adapted to yamtam memory layers (L1\u002FL2\u002Fauto-memory), added Anti-Fake-Pass. -->\n\n## When to Use\n\n- Use when: auto-memory has grown large and needs pruning\n- Use when: user wants to know what's been remembered across sessions\n- Use when: entries feel stale or contradictory\n- Use when: something important should move from auto-memory to CLAUDE.md\n- Do NOT use: to auto-apply changes — this skill proposes only, never modifies\n\n## Memory Layers (yamtam)\n\n```\nL1 atomic    core\u002Fmemory\u002FL1_atomic\u002F       Permanent facts — highest trust\nL2 session   core\u002Fmemory\u002FL2_session\u002F      Session-scoped, auto-expires\nAuto-memory  ~\u002F.claude\u002Fprojects\u002F...\u002Fmemory\u002F  Claude Code auto-memory\nCLAUDE.md    Project-level instructions\n```\n\n## Process\n\n### Step 1 — Collect all layers\n\n```bash\n# Auto-memory\ncat ~\u002F.claude\u002Fprojects\u002F*\u002Fmemory\u002FMEMORY.md 2>\u002Fdev\u002Fnull\nls ~\u002F.claude\u002Fprojects\u002F*\u002Fmemory\u002F*.md 2>\u002Fdev\u002Fnull | head -20\n\n# L1 atomic\nls core\u002Fmemory\u002FL1_atomic\u002F*.md 2>\u002Fdev\u002Fnull | head -20\n\n# L2 session\nls core\u002Fmemory\u002FL2_session\u002F*.md 2>\u002Fdev\u002Fnull | head -10\n\n# Project-level\nhead -50 CLAUDE.md 2>\u002Fdev\u002Fnull\n```\n\n### Step 2 — Classify each entry\n\nFor each entry, assign one of:\n- **PROMOTE** — important enough to move up (e.g., auto-memory → CLAUDE.md)\n- **DEMOTE** — too specific to stay at this level (e.g., CLAUDE.md → auto-memory)\n- **ARCHIVE** — outdated, no longer relevant\n- **MERGE** — duplicate of another entry, should be combined\n- **CONFLICT** — contradicts another entry, needs resolution\n- **OK** — no action needed\n\n### Step 3 — Generate the report\n\nFormat:\n```\nMEMORY REVIEW — [date]\n━━━━━━━━━━━━━━━━━━━━━\nTotal entries: X across Y layers\n\nPROMOTIONS (N)\n  ↑ [entry summary] — auto-memory → CLAUDE.md\n    Reason: used in 3+ sessions, project-level fact\n\nCLEANUP (N)\n  🗑 [entry] — outdated (references v0.13, current is v0.16)\n  ⊕  [entry A] + [entry B] — duplicates, merge into one\n\nCONFLICTS (N)\n  ⚠ [entry A]: \"use \u002Ftmp for builds\" vs [entry B]: \"builds go to target\u002F\"\n    Needs resolution: which is current?\n\nAMBIGUOUS (N)\n  ? [entry] — unclear if still relevant, ask user\n\nNO ACTION (N entries)\n```\n\n### Step 4 — Await explicit approval\n\nPresent the full report. Do not modify any files.\n\nAsk: \"Which of these should I apply? (all \u002F list numbers \u002F skip)\"\n\nOnly after confirmation: apply the approved changes.\n\n## Anti-Fake-Pass\n\n```\n❌ Modifying CLAUDE.md or any memory file without user approval\n❌ Marking entries as stale without evidence (check dates\u002Fcontext)\n❌ Promoting entries to CLAUDE.md that are session-specific\n❌ Skipping the conflict detection step\n✅ Report shown in full before any change\n✅ User explicitly approved each action before it was applied\n✅ Conflicts flagged — never silently resolved\n```\n","\u003C!-- Adapted from cc-haha\u002Fsrc\u002Fskills\u002Fbundled\u002Fremember.ts (MIT). Core pattern: collect → classify → propose → await approval. Changes: adapted to yamtam memory layers (L1\u002FL2\u002Fauto-memory), added Anti-Fake-Pass. -->\n\n## When to Use\n\n- Use when: auto-memory has grown large and needs pruning\n- Use when: user wants to know what's been remembered across sessions\n- Use when: entries feel stale or contradictory\n- Use when: something important should move from auto-memory to CLAUDE.md\n- Do NOT use: to auto-apply changes — this skill proposes only, never modifies\n\n## Memory Layers (yamtam)\n\n```\nL1 atomic    core\u002Fmemory\u002FL1_atomic\u002F       Permanent facts — highest trust\nL2 session   core\u002Fmemory\u002FL2_session\u002F      Session-scoped, auto-expires\nAuto-memory  ~\u002F.claude\u002Fprojects\u002F...\u002Fmemory\u002F  Claude Code auto-memory\nCLAUDE.md    Project-level instructions\n```\n\n## Process\n\n### Step 1 — Collect all layers\n\n```bash\n# Auto-memory\ncat ~\u002F.claude\u002Fprojects\u002F*\u002Fmemory\u002FMEMORY.md 2>\u002Fdev\u002Fnull\nls ~\u002F.claude\u002Fprojects\u002F*\u002Fmemory\u002F*.md 2>\u002Fdev\u002Fnull | head -20\n\n# L1 atomic\nls core\u002Fmemory\u002FL1_atomic\u002F*.md 2>\u002Fdev\u002Fnull | head -20\n\n# L2 session\nls core\u002Fmemory\u002FL2_session\u002F*.md 2>\u002Fdev\u002Fnull | head -10\n\n# Project-level\nhead -50 CLAUDE.md 2>\u002Fdev\u002Fnull\n```\n\n### Step 2 — Classify each entry\n\nFor each entry, assign one of:\n- **PROMOTE** — important enough to move up (e.g., auto-memory → CLAUDE.md)\n- **DEMOTE** — too specific to stay at this level (e.g., CLAUDE.md → auto-memory)\n- **ARCHIVE** — outdated, no longer relevant\n- **MERGE** — duplicate of another entry, should be combined\n- **CONFLICT** — contradicts another entry, needs resolution\n- **OK** — no action needed\n\n### Step 3 — Generate the report\n\nFormat:\n```\nMEMORY REVIEW — [date]\n━━━━━━━━━━━━━━━━━━━━━\nTotal entries: X across Y layers\n\nPROMOTIONS (N)\n  ↑ [entry summary] — auto-memory → CLAUDE.md\n    Reason: used in 3+ sessions, project-level fact\n\nCLEANUP (N)\n  🗑 [entry] — outdated (references v0.13, current is v0.16)\n  ⊕  [entry A] + [entry B] — duplicates, merge into one\n\nCONFLICTS (N)\n  ⚠ [entry A]: \"use \u002Ftmp for builds\" vs [entry B]: \"builds go to target\u002F\"\n    Needs resolution: which is current?\n\nAMBIGUOUS (N)\n  ? [entry] — unclear if still relevant, ask user\n\nNO ACTION (N entries)\n```\n\n### Step 4 — Await explicit approval\n\nPresent the full report. Do not modify any files.\n\nAsk: \"Which of these should I apply? (all \u002F list numbers \u002F skip)\"\n\nOnly after confirmation: apply the approved changes.\n\n## Anti-Fake-Pass\n\n```\n❌ Modifying CLAUDE.md or any memory file without user approval\n❌ Marking entries as stale without evidence (check dates\u002Fcontext)\n❌ Promoting entries to CLAUDE.md that are session-specific\n❌ Skipping the conflict detection step\n✅ Report shown in full before any change\n✅ User explicitly approved each action before it was applied\n✅ Conflicts flagged — never silently resolved\n```\n",{"name":5,"origin":24,"license":15,"version":25,"description":26,"compatibility":27},"adapted:NanmiCoder\u002Fcc-haha (remember.ts)","1.0.0","Review all memory layers, detect stale\u002Fduplicate\u002Fconflicting entries, and propose promotions between layers. Use when the user says \"clean up memory\", \"review what I've saved\", \"memory is getting messy\", \"what's in my memory\", \"organize my notes\", \"promote this to CLAUDE.md\", \"memory audit\", or after a long session with many \u002Fremember calls. Do NOT modify any files without explicit user approval.\n","yana-ai >= 0.14.0. Reads: CLAUDE.md, CLAUDE.local.md, auto-memory, L1\u002FL2.","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa","core\u002Fskills\u002Fmemory-review",2,"https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI","https:\u002F\u002Fyana.vutam.link\u002F","https:\u002F\u002Fgithub.com\u002FHoronomos-laps","https:\u002F\u002Fyana.vutam.link","An open-source governed runtime & execution environment for multi-agent AI systems.","2026-11-14 13:24:09",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill memory-review",{"tool":44,"command":45},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill memory-review",{"tool":47,"command":48},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill memory-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fmemory-review\u002FSKILL.md",true,[],[53,60,68,76,84,92],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M735GKET5YVYKAY62W2P5YXB","openai--sentry--sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fopenai--sentry--sentry\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M73DCAP83T17HY7SMGK7MGFE","ito-basket-compare","Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\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":64,"licenseFileUrl":72,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M734CYEMZFDR3KH6SW0JP8TD","implementing-network-traffic-baselining","Build network traffic baselines from NetFlow\u002FIPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly\u002Fdaily traffic pattern profiling","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M73ASZ6NJRJM44Z2P84NGQ3Q","detecting-evasion-techniques-in-endpoint-logs","Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M734AFNXD06Z78QRK0VKGT7Q","implementing-microsegmentation-with-guardicore","Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]