[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6C5P4JSP5S0R7FEERPD5G63":3,"skill-same:01M6C5P4JSP5S0R7FEERPD5G63":138},{"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":23,"publishedAt":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":14,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":6,"updatedAt":41,"install":42,"resources":55},"01M6C5P4JSP5S0R7FEERPD5G63","clawsec-nanoclaw",null,"Use when checking for security vulnerabilities in NanoClaw skills, before installing new skills, or when asked about security advisories affecting the bot","CoralShades\u002Facm-ai","CoralShades","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F220297585?v=4","01M6C5211QSJHZ8HXSDDWCR507","Coral Shades AI Agency","01M6C52161FNQDRQ0FRR8DAA9D",0,"MIT","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28],"clawsec nanoclaw","bot","security","vulnerabilities","use","2026-11-10 10:12:30",false,"---\nname: clawsec-nanoclaw\nversion: 0.0.1\ndescription: Use when checking for security vulnerabilities in NanoClaw skills, before installing new skills, or when asked about security advisories affecting the bot\n---\n\n# ClawSec for NanoClaw\n\nSecurity advisory monitoring that protects your WhatsApp bot from known vulnerabilities in skills and dependencies.\n\n## Overview\n\nClawSec provides MCP tools that check installed skills against a curated feed of security advisories. It prevents installation of vulnerable skills and alerts you to issues in existing ones.\n\n**Core principle:** Check before you install. Monitor what's running.\n\n## When to Use\n\nUse ClawSec tools when:\n- Installing a new skill (check safety first)\n- User asks \"are my skills secure?\"\n- Investigating suspicious behavior\n- Regular security audits\n- After receiving security notifications\n\nDo NOT use for:\n- Code review (use other tools)\n- Performance issues (different concern)\n- General debugging\n\n## MCP Tools Available\n\n### Pre-Installation Check\n\n```typescript\n\u002F\u002F Before installing any skill\nconst safety = await tools.clawsec_check_skill_safety({\n  skillName: 'new-skill',\n  version: '1.0.0'  \u002F\u002F optional\n});\n\nif (!safety.safe) {\n  \u002F\u002F Show user the risks before proceeding\n  console.warn(`Security issues: ${safety.advisories.map(a => a.id)}`);\n}\n```\n\n### Security Audit\n\n```typescript\n\u002F\u002F Check all installed skills\nconst result = await tools.clawsec_check_advisories({\n  skillsRoot: '\u002Fworkspace\u002Fproject\u002Fskills'  \u002F\u002F optional\n});\n\nif (result.criticalCount > 0) {\n  \u002F\u002F Alert user immediately\n  console.error('CRITICAL vulnerabilities found!');\n}\n```\n\n### Browse Advisories\n\n```typescript\n\u002F\u002F List advisories with filters\nconst advisories = await tools.clawsec_list_advisories({\n  platform: 'nanoclaw',    \u002F\u002F optional: nanoclaw, openclaw, or both\n  severity: 'critical'     \u002F\u002F optional: critical, high, medium, low\n});\n```\n\n## Quick Reference\n\n| Task | Tool | Key Parameter |\n|------|------|---------------|\n| Pre-install check | `clawsec_check_skill_safety` | `skillName` |\n| Audit all skills | `clawsec_check_advisories` | `installRoot` (optional) |\n| Browse feed | `clawsec_list_advisories` | `severity`, `type` (optional) |\n| Verify package signature | `clawsec_verify_skill_package` | `packagePath` |\n| Refresh advisory cache | `clawsec_refresh_cache` | (none) |\n| Check file integrity | `clawsec_check_integrity` | `mode`, `autoRestore` (optional) |\n| Approve file change | `clawsec_approve_change` | `path` |\n| View baseline status | `clawsec_integrity_status` | `path` (optional) |\n| Verify audit log | `clawsec_verify_audit` | (none) |\n\n## Common Patterns\n\n### Pattern 1: Safe Skill Installation\n\n```typescript\n\u002F\u002F ALWAYS check before installing\nconst safety = await tools.clawsec_check_skill_safety({\n  skillName: userRequestedSkill\n});\n\nif (safety.safe) {\n  \u002F\u002F Proceed with installation\n  await installSkill(userRequestedSkill);\n} else {\n  \u002F\u002F Show user the risks and get confirmation\n  await showSecurityWarning(safety.advisories);\n  if (await getUserConfirmation()) {\n    await installSkill(userRequestedSkill);\n  }\n}\n```\n\n### Pattern 2: Periodic Security Check\n\n```typescript\n\u002F\u002F Add to scheduled tasks\nschedule_task({\n  prompt: \"Check for security advisories using clawsec_check_advisories and alert if any critical issues found\",\n  schedule_type: \"cron\",\n  schedule_value: \"0 9 * * *\"  \u002F\u002F Daily at 9am\n});\n```\n\n### Pattern 3: User Security Query\n\n```\nUser: \"Are my skills secure?\"\n\nYou: I'll check installed skills for known vulnerabilities.\n[Use clawsec_check_advisories]\n\nResponse:\n✅ No critical issues found.\n- 2 low-severity advisories (not urgent)\n- All skills up to date\n```\n\n## Common Mistakes\n\n### ❌ Installing without checking\n```typescript\n\u002F\u002F DON'T\nawait installSkill('untrusted-skill');\n```\n\n```typescript\n\u002F\u002F DO\nconst safety = await tools.clawsec_check_skill_safety({\n  skillName: 'untrusted-skill'\n});\nif (safety.safe) await installSkill('untrusted-skill');\n```\n\n### ❌ Ignoring platform filters\n```typescript\n\u002F\u002F DON'T: Check OpenClaw advisories on NanoClaw\nconst advisories = await tools.clawsec_list_advisories({\n  platform: 'openclaw'  \u002F\u002F Wrong platform!\n});\n```\n\n```typescript\n\u002F\u002F DO: Use correct platform or let it auto-filter\nconst advisories = await tools.clawsec_list_advisories({\n  platform: 'nanoclaw'  \u002F\u002F Correct\n});\n```\n\n### ❌ Skipping critical severity\n```typescript\n\u002F\u002F DON'T: Only check low severity\nif (result.lowCount > 0) alert();\n```\n\n```typescript\n\u002F\u002F DO: Prioritize critical and high\nif (result.criticalCount > 0 || result.highCount > 0) {\n  \u002F\u002F Alert immediately\n}\n```\n\n## Implementation Details\n\n**Feed Source**: https:\u002F\u002Fclawsec.prompt.security\u002Fadvisories\u002Ffeed.json\n\n**Update Frequency**: Every 6 hours (automatic)\n\n**Signature Verification**: Ed25519 signed feeds\n\n**Cache Location**: `\u002Fworkspace\u002Fproject\u002Fdata\u002Fclawsec-cache.json`\n\nSee [INSTALL.md](.\u002FINSTALL.md) for setup and [docs\u002F](.\u002Fdocs\u002F) for advanced usage.\n\n## Real-World Impact\n\n- Prevents installation of skills with known RCE vulnerabilities\n- Alerts to supply chain attacks in dependencies\n- Provides actionable remediation steps\n- Zero false positives (curated feed only)\n","# ClawSec for NanoClaw\n\nSecurity advisory monitoring that protects your WhatsApp bot from known vulnerabilities in skills and dependencies.\n\n## Overview\n\nClawSec provides MCP tools that check installed skills against a curated feed of security advisories. It prevents installation of vulnerable skills and alerts you to issues in existing ones.\n\n**Core principle:** Check before you install. Monitor what's running.\n\n## When to Use\n\nUse ClawSec tools when:\n- Installing a new skill (check safety first)\n- User asks \"are my skills secure?\"\n- Investigating suspicious behavior\n- Regular security audits\n- After receiving security notifications\n\nDo NOT use for:\n- Code review (use other tools)\n- Performance issues (different concern)\n- General debugging\n\n## MCP Tools Available\n\n### Pre-Installation Check\n\n```typescript\n\u002F\u002F Before installing any skill\nconst safety = await tools.clawsec_check_skill_safety({\n  skillName: 'new-skill',\n  version: '1.0.0'  \u002F\u002F optional\n});\n\nif (!safety.safe) {\n  \u002F\u002F Show user the risks before proceeding\n  console.warn(`Security issues: ${safety.advisories.map(a => a.id)}`);\n}\n```\n\n### Security Audit\n\n```typescript\n\u002F\u002F Check all installed skills\nconst result = await tools.clawsec_check_advisories({\n  skillsRoot: '\u002Fworkspace\u002Fproject\u002Fskills'  \u002F\u002F optional\n});\n\nif (result.criticalCount > 0) {\n  \u002F\u002F Alert user immediately\n  console.error('CRITICAL vulnerabilities found!');\n}\n```\n\n### Browse Advisories\n\n```typescript\n\u002F\u002F List advisories with filters\nconst advisories = await tools.clawsec_list_advisories({\n  platform: 'nanoclaw',    \u002F\u002F optional: nanoclaw, openclaw, or both\n  severity: 'critical'     \u002F\u002F optional: critical, high, medium, low\n});\n```\n\n## Quick Reference\n\n| Task | Tool | Key Parameter |\n|------|------|---------------|\n| Pre-install check | `clawsec_check_skill_safety` | `skillName` |\n| Audit all skills | `clawsec_check_advisories` | `installRoot` (optional) |\n| Browse feed | `clawsec_list_advisories` | `severity`, `type` (optional) |\n| Verify package signature | `clawsec_verify_skill_package` | `packagePath` |\n| Refresh advisory cache | `clawsec_refresh_cache` | (none) |\n| Check file integrity | `clawsec_check_integrity` | `mode`, `autoRestore` (optional) |\n| Approve file change | `clawsec_approve_change` | `path` |\n| View baseline status | `clawsec_integrity_status` | `path` (optional) |\n| Verify audit log | `clawsec_verify_audit` | (none) |\n\n## Common Patterns\n\n### Pattern 1: Safe Skill Installation\n\n```typescript\n\u002F\u002F ALWAYS check before installing\nconst safety = await tools.clawsec_check_skill_safety({\n  skillName: userRequestedSkill\n});\n\nif (safety.safe) {\n  \u002F\u002F Proceed with installation\n  await installSkill(userRequestedSkill);\n} else {\n  \u002F\u002F Show user the risks and get confirmation\n  await showSecurityWarning(safety.advisories);\n  if (await getUserConfirmation()) {\n    await installSkill(userRequestedSkill);\n  }\n}\n```\n\n### Pattern 2: Periodic Security Check\n\n```typescript\n\u002F\u002F Add to scheduled tasks\nschedule_task({\n  prompt: \"Check for security advisories using clawsec_check_advisories and alert if any critical issues found\",\n  schedule_type: \"cron\",\n  schedule_value: \"0 9 * * *\"  \u002F\u002F Daily at 9am\n});\n```\n\n### Pattern 3: User Security Query\n\n```\nUser: \"Are my skills secure?\"\n\nYou: I'll check installed skills for known vulnerabilities.\n[Use clawsec_check_advisories]\n\nResponse:\n✅ No critical issues found.\n- 2 low-severity advisories (not urgent)\n- All skills up to date\n```\n\n## Common Mistakes\n\n### ❌ Installing without checking\n```typescript\n\u002F\u002F DON'T\nawait installSkill('untrusted-skill');\n```\n\n```typescript\n\u002F\u002F DO\nconst safety = await tools.clawsec_check_skill_safety({\n  skillName: 'untrusted-skill'\n});\nif (safety.safe) await installSkill('untrusted-skill');\n```\n\n### ❌ Ignoring platform filters\n```typescript\n\u002F\u002F DON'T: Check OpenClaw advisories on NanoClaw\nconst advisories = await tools.clawsec_list_advisories({\n  platform: 'openclaw'  \u002F\u002F Wrong platform!\n});\n```\n\n```typescript\n\u002F\u002F DO: Use correct platform or let it auto-filter\nconst advisories = await tools.clawsec_list_advisories({\n  platform: 'nanoclaw'  \u002F\u002F Correct\n});\n```\n\n### ❌ Skipping critical severity\n```typescript\n\u002F\u002F DON'T: Only check low severity\nif (result.lowCount > 0) alert();\n```\n\n```typescript\n\u002F\u002F DO: Prioritize critical and high\nif (result.criticalCount > 0 || result.highCount > 0) {\n  \u002F\u002F Alert immediately\n}\n```\n\n## Implementation Details\n\n**Feed Source**: https:\u002F\u002Fclawsec.prompt.security\u002Fadvisories\u002Ffeed.json\n\n**Update Frequency**: Every 6 hours (automatic)\n\n**Signature Verification**: Ed25519 signed feeds\n\n**Cache Location**: `\u002Fworkspace\u002Fproject\u002Fdata\u002Fclawsec-cache.json`\n\nSee [INSTALL.md](.\u002FINSTALL.md) for setup and [docs\u002F](.\u002Fdocs\u002F) for advanced usage.\n\n## Real-World Impact\n\n- Prevents installation of skills with known RCE vulnerabilities\n- Alerts to supply chain attacks in dependencies\n- Provides actionable remediation steps\n- Zero false positives (curated feed only)\n",{"name":5,"version":34,"description":7},"0.0.1","main","1ca81b0a7de199942400f965edd4d7544077ac5d",".codex\u002Fskills\u002Fclawsec-nanoclaw","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai","https:\u002F\u002Fgithub.com\u002FCoralShades","coralshades.com.au","2026-04-18 00:45:07",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add CoralShades\u002Facm-ai --skill clawsec-nanoclaw",{"tool":48,"command":49},"bunx","bunx skills add CoralShades\u002Facm-ai --skill clawsec-nanoclaw",{"tool":51,"command":52},"pnpm","pnpm dlx skills add CoralShades\u002Facm-ai --skill clawsec-nanoclaw","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002FSKILL.md",true,[56,62,68,72,76,82,86,90,94,98,102,106,110,114,118,122,126,130,134],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"advisories\u002Ffeed-signing-public.pem","OTHER","其他",113,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Fadvisories\u002Ffeed-signing-public.pem",{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"agents\u002Fopenai.yaml","REFERENCE","参考文档",43,"https:\u002F\u002Fgithub.com\u002Fdmlguq456\u002Fhearting\u002Fblob\u002Fmain\u002Fadapters\u002Fcodex\u002Fplugins\u002Fhearting-codex\u002Fskills\u002Faudit\u002Fagents\u002Fopenai.yaml",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"docs\u002FINTEGRITY.md",13850,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Fdocs\u002FINTEGRITY.md",{"path":73,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":74,"sourceHtmlUrl":75},"docs\u002FSKILL_SIGNING.md",15123,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Fdocs\u002FSKILL_SIGNING.md",{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"guardian\u002Fintegrity-monitor.ts","SCRIPT","脚本",20678,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Fguardian\u002Fintegrity-monitor.ts",{"path":83,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":84,"sourceHtmlUrl":85},"guardian\u002Fpolicy.json",1745,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Fguardian\u002Fpolicy.json",{"path":87,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":88,"sourceHtmlUrl":89},"host-services\u002Fadvisory-cache.ts",11891,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Fhost-services\u002Fadvisory-cache.ts",{"path":91,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":92,"sourceHtmlUrl":93},"host-services\u002Fintegrity-handler.ts",9848,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Fhost-services\u002Fintegrity-handler.ts",{"path":95,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":96,"sourceHtmlUrl":97},"host-services\u002Fipc-handlers.ts",3480,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Fhost-services\u002Fipc-handlers.ts",{"path":99,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":100,"sourceHtmlUrl":101},"host-services\u002Fskill-signature-handler.ts",6254,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Fhost-services\u002Fskill-signature-handler.ts",{"path":103,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":104,"sourceHtmlUrl":105},"INSTALL.md",8702,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002FINSTALL.md",{"path":107,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":108,"sourceHtmlUrl":109},"lib\u002Fadvisories.ts",10548,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Flib\u002Fadvisories.ts",{"path":111,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":112,"sourceHtmlUrl":113},"lib\u002Fsignatures.ts",14102,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Flib\u002Fsignatures.ts",{"path":115,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":116,"sourceHtmlUrl":117},"lib\u002Ftypes.ts",5885,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Flib\u002Ftypes.ts",{"path":119,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":120,"sourceHtmlUrl":121},"mcp-tools\u002Fadvisory-tools.ts",12958,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Fmcp-tools\u002Fadvisory-tools.ts",{"path":123,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":124,"sourceHtmlUrl":125},"mcp-tools\u002Fintegrity-tools.ts",8318,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Fmcp-tools\u002Fintegrity-tools.ts",{"path":127,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":128,"sourceHtmlUrl":129},"mcp-tools\u002Fsignature-verification.ts",5194,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Fmcp-tools\u002Fsignature-verification.ts",{"path":131,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":132,"sourceHtmlUrl":133},"README.md",5204,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002FREADME.md",{"path":135,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":136,"sourceHtmlUrl":137},"skill.json",4401,"https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.codex\u002Fskills\u002Fclawsec-nanoclaw\u002Fskill.json",[139,160,173,189,211,221],{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":148,"publishedAt":29},"01M6C63HKXA890HHV47WBAX0TB","uncodixfy","Prevents generic AI\u002FCodex UI patterns when generating frontend code. Use this skill whenever generating HTML, CSS, React, Vue, Svelte, or any frontend UI code to enforce clean, human-designed aesthetics inspired by Linear, Raycast, Stripe, and GitHub instead of typical AI-generated UI.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Funcodixfy\u002FSKILL.md",[145],{"categoryNo":146,"categoryName":147,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[141,149,150,151,152,153,154,155,156,157,158,28,159],"github","frontend","css","codex","react","code","linear","ui","vue","generated","html",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":164,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":29},"01M6C63FJ2GEBBGZ5XSMV40KXB","runpodctl","Runpod CLI to manage your GPU workloads.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Frunpodctl\u002FSKILL.md",[],[162,168,169,170,171,172],"macos","cli","linux","gpu","Bash",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":29},"01M6C63DPAV46TFVQ01SFYPJ7X","langgraph-persistence","INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-persistence\u002FSKILL.md",[],[180,181,182,183,184,185,186,187,188],"langgraph persistence","langgraph","persistence","travel","history","scoping","remember","state","configure",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":200,"publishedAt":29},"01M6C63BNS9CQEBTB8RNSSBFPA","langgraph-human-in-the-loop","INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval\u002Fvalidation workflows, and the 4-tier error handling strategy.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-human-in-the-loop\u002FSKILL.md",[195],{"categoryNo":196,"categoryName":197,"taxonomyType":198,"taxonomyTypeDesc":199},"01JBSEEDCAT000000000000038","人力资源","PROFESSION","适用职业",[201,202,181,203,204,205,206,207,208,209,210],"langgraph human in the loop","loop","workflows","error handling","validation","human-in-the-loop","command","strategy","approval","resume",{"skillNo":212,"name":213,"nameZh":6,"description":214,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":215,"categories":216,"keywords":217,"publishedAt":29},"01M6C639GVYZFX3NFPV5FBDR4F","langgraph-fundamentals","INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flanggraph-fundamentals\u002FSKILL.md",[],[218,181,204,187,219,220,207,154],"langgraph fundamentals","streaming","writing",{"skillNo":222,"name":223,"nameZh":6,"description":224,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":225,"categories":226,"keywords":227,"publishedAt":29},"01M6C6375N34YX2GZ3SD3R7XR2","langchain-rag","INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).","https:\u002F\u002Fgithub.com\u002FCoralShades\u002Facm-ai\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Flangchain-rag\u002FSKILL.md",[],[228,229,230,231,232,233,234,235,236,237],"rag","langchain rag","langchain","embeddings","vector","openai","chroma","faiss","vector stores","system"]