Skip to content
← Volver al catálogo
Fiabilidadsegurocommunity

tool-use-guardian

GRATIS — Envoltorio inteligente de confiabilidad en llamadas de herramientas. Monitorea, reintenta, corrige y aprende de fallos de herramientas. Recuperación automática de JSON truncado, timeouts, límites de velocidad y fallos en cadena.

El contenido de este skill está en su idioma original (a menudo inglés).

Tool Use Guardian

Overview

The 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.

Free forever. Built by the Genesis Agent Marketplace.

Install

npx skills add christopherlhammer11-ai/tool-use-guardian

When to Use This Skill

  • Use when tool calls return truncated or malformed JSON
  • Use when APIs timeout or rate-limit your agent mid-task
  • Use when a multi-step chain breaks partway through
  • Use when you need automatic retry logic without writing it yourself
  • Use for any agent workflow that depends on external tool reliability

How It Works

Step 1: Pre-Call Validation

Before every tool call, Guardian validates:

  • Required parameters are present and correctly typed
  • The tool is not marked as "unreliable" from previous failures
  • Request size is within known limits

Step 2: Failure Classification

When a tool call fails, Guardian classifies the failure into one of 9 categories:

Failure TypeRecovery Action
Truncated JSONRe-fetch with pagination or smaller chunks
API TimeoutRetry once with simpler request, then decompose
Rate Limit (429)Exponential backoff, max 3 retries
Auth ExpiredFlag for user intervention
Mid-chain BreakResume from last successful checkpoint
Error-as-200Detect {"error": "..."} disguised as success
Schema MismatchAttempt auto-coercion, warn if lossy
Network FailureRetry with jitter, max 2 attempts
Unknown ErrorLog full context, escalate to user

Step 3: Chain Protection

For multi-step tool chains, Guardian maintains checkpoints. If step 4 of 7 fails, it resumes from step 4 — never restarts from scratch.

Step 4: Learning

Guardian tracks failure patterns per tool. After 3+ failures of the same type, it marks the tool as unreliable and suggests alternatives.

Best Practices

  • ✅ Let Guardian wrap all external tool calls automatically
  • ✅ Review Guardian's reliability reports to identify flaky tools
  • ✅ Use checkpoint recovery for long chains
  • ❌ Don't disable retry logic for rate-limited APIs
  • ❌ Don't ignore repeated failure warnings

Related Skills

  • @recallmax - Long-context memory enhancement (also free from Genesis Marketplace)

Links

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
— Field Manual

Las 1.441 skills, desmitificadas en un PDF.

Una guía editorial gratuita que escribimos para Skills Atlas: taxonomía, las 25 skills imprescindibles, antipatrones, rutas de aprendizaje por perfil.

  • 70+ páginas, índice, lista para imprimir.
  • Enviado por email — enlace válido 7 días.
  • Cancela suscripción en un clic cuando quieras.

Sin spam. Nunca compartimos tu email. Cancelación en un clic.