Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

codebase-navigation

Étoiles3 458

Forks443

Mis à jour10 mars 2026 à 18:04

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.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

aiming-lab

aiming-lab/MetaClaw

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	codebase-navigation
description	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.
category	coding

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.

Plus depuis ce dépôt

même dépôt

agent-task-handoff

aiming-lab/MetaClaw

Use this skill when delegating a subtask to a sub-agent, spawning a parallel worker, or handing off work across sessions. Write a self-contained task description so the receiving agent needs no prior context.

2026-03-103.5k

async-communication-etiquette

aiming-lab/MetaClaw

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.

2026-03-103.5k

audience-aware-communication

aiming-lab/MetaClaw

Use this skill when writing any explanation, documentation, or response that will be read by someone else. Match vocabulary, depth, and format to the audience's expertise level before writing.

2026-03-103.5k

auth-and-authorization-patterns

aiming-lab/MetaClaw

Use this skill when implementing authentication (login, token issuance) or authorization (access control, permissions). Apply whenever the task involves login flows, JWT, OAuth2, session management, or RBAC.

2026-03-103.5k

avoid-acting-on-assumptions

aiming-lab/MetaClaw

Common mistake — proceeding with assumptions about ambiguous requirements instead of asking a clarifying question first. This skill reminds you to stop and ask before acting on uncertain interpretations.

2026-03-103.5k

avoid-hallucinating-specifics

aiming-lab/MetaClaw

Common mistake — stating specific facts (API endpoints, library versions, config options, function signatures) with false confidence when uncertain. Always flag uncertainty rather than guessing specifics.

2026-03-103.5k

name	codebase-navigation
description	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.
category	coding

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.