ReddRadar
Agent skill
avoid-scope-creep
Common mistake — doing unrequested work (refactoring, adding extra features, cleaning up style) when the user asked for a specific, targeted change. Only change what was explicitly asked.
Install this agent skill to your Project
npx add-skill https://github.com/aiming-lab/MetaClaw/tree/main/memory_data/skills/avoid-scope-creep
SKILL.md
Avoid Scope Creep
Mistake pattern: User asks to fix a specific bug → you also refactor the function, rename variables, add docstrings, and restructure the file → harder to review, introduces new risk.
Rule: Only change what was asked. If you notice other issues while working, mention them as a note rather than silently fixing them.
Exception: If a requested change is impossible without fixing a directly blocking dependency, fix the minimum required dependency and explain why.
Anti-pattern: while I'm here, I also improved... without being asked.
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?