ReddRadar
Agent skill
tool-selection-strategy
Use this skill when deciding which tools to call in an agentic workflow. Always choose the minimal, most direct tool for each step and avoid redundant or speculative tool calls.
Install this agent skill to your Project
npx add-skill https://github.com/aiming-lab/MetaClaw/tree/main/memory_data/skills/tool-selection-strategy
SKILL.md
Tool Selection Strategy
Principles:
- Least tool principle: Use the most specific, lightweight tool that accomplishes the goal.
- Read before writing: Always read a file before editing it to understand current state.
- Avoid speculative calls: Don't call a tool "just to see what happens". Have a clear hypothesis.
- Parallelize independent calls: If two reads don't depend on each other, fire them simultaneously.
Decision heuristic:
- Can I answer this from memory/context? No tool call needed.
- Is this a file operation? Use Read/Write/Edit tools.
- Is this a code search? Use Grep/Glob tools.
- Is this a system operation? Use Bash (last resort).
Anti-pattern: Using a heavy tool (Agent, Bash) when a lightweight dedicated tool suffices.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
aiming-lab/MetaClaw
structured-progress-update
Use this skill when summarizing progress on an ongoing project or multi-step task. Give a clear, scannable status report whenever asked for an update or at the end of a work session.
aiming-lab/MetaClaw
async-communication-etiquette
Use this skill when writing messages in async channels (Slack, GitHub issues, email threads) where the reader may not have context and cannot ask follow-up questions immediately.
aiming-lab/MetaClaw
idempotent-script-design
Use this skill when writing scripts, cron jobs, data pipelines, or any automated process that may be run multiple times. Design every operation to be safely re-runnable without side effects.
aiming-lab/MetaClaw
secrets-management
Use this skill when handling API keys, passwords, tokens, private keys, or any sensitive credential. Never hardcode secrets in source code — apply this whenever the word "key", "token", "password", or "secret" appears in the task.
aiming-lab/MetaClaw
input-validation-and-sanitization
Use this skill when implementing any endpoint, form handler, CLI tool, or function that accepts external input. Validate and sanitize all untrusted data before processing — never assume input is safe.
aiming-lab/MetaClaw
graceful-error-recovery
Use this skill when a tool call, command, or API request fails. Diagnose the root cause systematically before retrying or changing approach. Do not retry the same failing call without first understanding why it failed.
Didn't find tool you were looking for?