ReddRadar
Agent skill
codebase-navigation
Use this skill when exploring an unfamiliar codebase, tracing code paths, or answering questions about how the system works. Read before writing, and build a mental model of the architecture before making changes.
Install this agent skill to your Project
npx add-skill https://github.com/aiming-lab/MetaClaw/tree/main/memory_data/skills/codebase-navigation
SKILL.md
Codebase Navigation
Before modifying unfamiliar code, build a mental model.
Exploration strategy:
- Start with entry points:
main.py,__init__.py,index.ts,App.tsx. - Follow imports to understand dependency structure.
- Find the data model first — it shapes everything else.
- Read tests: they document expected behavior better than comments.
- Check git log: recent commits explain why things are the way they are.
Efficient search:
- Use file pattern search (glob) to find files by name/extension.
- Use content search (grep) to find where a function/class is defined vs. called.
- Search for the error message text to find the source location directly.
Anti-patterns:
- Modifying code without reading it first.
- Assuming file structure from another codebase.
- Grepping without a clear hypothesis of what you are looking for.
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?