[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78FMMAVC6Y93GYR9WREBJCF":3,"skill-same:01M78FMMAVC6Y93GYR9WREBJCF":64},{"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":43,"commitSha":44,"skillDirectory":45,"forksCount":14,"repositoryHtmlUrl":46,"repositoryHomepageUrl":47,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M78FMMAVC6Y93GYR9WREBJCF","tool-use-guardian",null,"FREE — Intelligent tool-call reliability wrapper. Monitors, retries, fixes, and learns from tool failures. Auto-recovers from truncated JSON, timeouts, rate limits, and mid-chain failures.","princepatel04477-web\u002Ftrivoxa-group","princepatel04477-web","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F227740714?v=4","01M788ZAJ2KECD5KXVP55PZXKS","Prince Patel","01M788ZAJTCN8YSD737MRSKC5Q",0,"MIT","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Ftool-use-guardian\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tool-use-guardian\ndescription: \"FREE — Intelligent tool-call reliability wrapper. Monitors, retries, fixes, and learns from tool failures. Auto-recovers from truncated JSON, timeouts, rate limits, and mid-chain failures.\"\ncategory: reliability\nrisk: safe\nsource: community\ndate_added: \"2026-03-13\"\nauthor: christopherlhammer11-ai\ntags: [reliability, tool-use, error-handling, retries, recovery, agent-infrastructure]\ntools: [claude, cursor, codex, gemini, copilot, windsurf, antigravity]\n---\n\n# Tool Use Guardian\n\n## Overview\n\nThe reliability wrapper every AI agent needs. Monitors tool calls, auto-retries failures, fixes truncated responses, and learns which tools are unreliable — so you never lose your chain of thought.\n\nFree forever. Built by the Genesis Agent Marketplace.\n\n## Install\n\n```bash\nnpx skills add christopherlhammer11-ai\u002Ftool-use-guardian\n```\n\n## When to Use This Skill\n\n- Use when tool calls return truncated or malformed JSON\n- Use when APIs timeout or rate-limit your agent mid-task\n- Use when a multi-step chain breaks partway through\n- Use when you need automatic retry logic without writing it yourself\n- Use for any agent workflow that depends on external tool reliability\n\n## How It Works\n\n### Step 1: Pre-Call Validation\n\nBefore every tool call, Guardian validates:\n- Required parameters are present and correctly typed\n- The tool is not marked as \"unreliable\" from previous failures\n- Request size is within known limits\n\n### Step 2: Failure Classification\n\nWhen a tool call fails, Guardian classifies the failure into one of 9 categories:\n\n| Failure Type | Recovery Action |\n|---|---|\n| Truncated JSON | Re-fetch with pagination or smaller chunks |\n| API Timeout | Retry once with simpler request, then decompose |\n| Rate Limit (429) | Exponential backoff, max 3 retries |\n| Auth Expired | Flag for user intervention |\n| Mid-chain Break | Resume from last successful checkpoint |\n| Error-as-200 | Detect `{\"error\": \"...\"}` disguised as success |\n| Schema Mismatch | Attempt auto-coercion, warn if lossy |\n| Network Failure | Retry with jitter, max 2 attempts |\n| Unknown Error | Log full context, escalate to user |\n\n### Step 3: Chain Protection\n\nFor multi-step tool chains, Guardian maintains checkpoints. If step 4 of 7 fails, it resumes from step 4 — never restarts from scratch.\n\n### Step 4: Learning\n\nGuardian tracks failure patterns per tool. After 3+ failures of the same type, it marks the tool as unreliable and suggests alternatives.\n\n## Best Practices\n\n- ✅ Let Guardian wrap all external tool calls automatically\n- ✅ Review Guardian's reliability reports to identify flaky tools\n- ✅ Use checkpoint recovery for long chains\n- ❌ Don't disable retry logic for rate-limited APIs\n- ❌ Don't ignore repeated failure warnings\n\n## Related Skills\n\n- `@recallmax` - Long-context memory enhancement (also free from Genesis Marketplace)\n\n## Links\n\n- **Repo:** https:\u002F\u002Fgithub.com\u002Fchristopherlhammer11-ai\u002Ftool-use-guardian\n- **Marketplace:** https:\u002F\u002Fgenesis-node-api.vercel.app\n- **Browse skills:** https:\u002F\u002Fgenesis-marketplace.vercel.app\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","# Tool Use Guardian\n\n## Overview\n\nThe reliability wrapper every AI agent needs. Monitors tool calls, auto-retries failures, fixes truncated responses, and learns which tools are unreliable — so you never lose your chain of thought.\n\nFree forever. Built by the Genesis Agent Marketplace.\n\n## Install\n\n```bash\nnpx skills add christopherlhammer11-ai\u002Ftool-use-guardian\n```\n\n## When to Use This Skill\n\n- Use when tool calls return truncated or malformed JSON\n- Use when APIs timeout or rate-limit your agent mid-task\n- Use when a multi-step chain breaks partway through\n- Use when you need automatic retry logic without writing it yourself\n- Use for any agent workflow that depends on external tool reliability\n\n## How It Works\n\n### Step 1: Pre-Call Validation\n\nBefore every tool call, Guardian validates:\n- Required parameters are present and correctly typed\n- The tool is not marked as \"unreliable\" from previous failures\n- Request size is within known limits\n\n### Step 2: Failure Classification\n\nWhen a tool call fails, Guardian classifies the failure into one of 9 categories:\n\n| Failure Type | Recovery Action |\n|---|---|\n| Truncated JSON | Re-fetch with pagination or smaller chunks |\n| API Timeout | Retry once with simpler request, then decompose |\n| Rate Limit (429) | Exponential backoff, max 3 retries |\n| Auth Expired | Flag for user intervention |\n| Mid-chain Break | Resume from last successful checkpoint |\n| Error-as-200 | Detect `{\"error\": \"...\"}` disguised as success |\n| Schema Mismatch | Attempt auto-coercion, warn if lossy |\n| Network Failure | Retry with jitter, max 2 attempts |\n| Unknown Error | Log full context, escalate to user |\n\n### Step 3: Chain Protection\n\nFor multi-step tool chains, Guardian maintains checkpoints. If step 4 of 7 fails, it resumes from step 4 — never restarts from scratch.\n\n### Step 4: Learning\n\nGuardian tracks failure patterns per tool. After 3+ failures of the same type, it marks the tool as unreliable and suggests alternatives.\n\n## Best Practices\n\n- ✅ Let Guardian wrap all external tool calls automatically\n- ✅ Review Guardian's reliability reports to identify flaky tools\n- ✅ Use checkpoint recovery for long chains\n- ❌ Don't disable retry logic for rate-limited APIs\n- ❌ Don't ignore repeated failure warnings\n\n## Related Skills\n\n- `@recallmax` - Long-context memory enhancement (also free from Genesis Marketplace)\n\n## Links\n\n- **Repo:** https:\u002F\u002Fgithub.com\u002Fchristopherlhammer11-ai\u002Ftool-use-guardian\n- **Marketplace:** https:\u002F\u002Fgenesis-node-api.vercel.app\n- **Browse skills:** https:\u002F\u002Fgenesis-marketplace.vercel.app\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":24,"tags":25,"tools":32,"author":40,"source":41,"category":26,"date_added":42,"description":7},"safe",[26,27,28,29,30,31],"reliability","tool-use","error-handling","retries","recovery","agent-infrastructure",[33,34,35,36,37,38,39],"claude","cursor","codex","gemini","copilot","windsurf","antigravity","christopherlhammer11-ai","community","2026-03-13","master","877653a671c51fae6476bd9f0d34ee6c408d68b9",".github\u002Fskills\u002Ftool-use-guardian","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group","https:\u002F\u002Ftrivoxa-group.vercel.app","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web","2026-08-01 17:29:31",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add princepatel04477-web\u002Ftrivoxa-group --skill tool-use-guardian",{"tool":56,"command":57},"bunx","bunx skills add princepatel04477-web\u002Ftrivoxa-group --skill tool-use-guardian",{"tool":59,"command":60},"pnpm","pnpm dlx skills add princepatel04477-web\u002Ftrivoxa-group --skill tool-use-guardian","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Ftool-use-guardian\u002FSKILL.md",true,[],[65,72,79,86,93,100],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M78G4Z5RFJ72G536XYPC77PG","zustand-store-ts","Create Zustand stores following established patterns with proper TypeScript types and middleware.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzustand-store-ts\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M78G4WQMHRST36KDP7AV3NR3","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\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzoom-automation\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M78G4T37F4SPS7M4KT0A8JJB","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\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzoho-crm-automation\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M78G4QAJMF71KD1G38MNDQYK","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\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzod-validation-expert\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M78G4MS3WE96MH5P561KFY95","zipai-optimizer","Adaptive token optimizer: intelligent filtering, surgical output, ambiguity-first, context-window-aware, VCS-aware, MCP-aware.","https:\u002F\u002Fgithub.com\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzipai-optimizer\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M78G4GZ0T47C6929V9CVH1AK","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\u002Fprincepatel04477-web\u002Ftrivoxa-group\u002Fblob\u002Fmaster\u002F.github\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[]]