Automated summary
This skill automatically explores a codebase to understand existing patterns related to a feature, launching parallel agents without user interaction.
Strengths
- Fully automated exploration phase requiring no user interaction
- Parallel analysis with 2-3 specialized agents covering different aspects (similar features, architecture, integrations)
- Structured consolidation of results and workflow state updates
Limitations
- Requires a pre-existing workflow state file to be present
- Depends on the quality of underlying exploration agents
- Does not handle cases where exploration requires human decisions
When you need to quickly and reproducibly analyze a codebase to understand patterns and key files before implementing a new feature.
When exploration requires creative choices or contextual understanding that agents cannot provide, or when the codebase is too small to justify automated exploration.
Security analysis
SafeThe skill only uses read-only tools (Read, Glob, Grep) and a task-launching tool for code exploration agents. It does not download, execute arbitrary commands, modify system state destructively, or exfiltrate data. No risky patterns detected.
No concerns found
How this analysis is madeExamples
Run dev:auto:explore for feature 'user authentication' in the current codebase, using the existing workflow state from issue #42.Execute the automated code exploration workflow for feature 'payment integration', focusing on finding similar features and mapping the architecture.Launch the auto-explore skill for feature 'notification system', with emphasis on integration points and event communication patterns.name: dev:auto:explore description: Explorer le codebase automatiquement - Mode AUTO (Phase 2) model: sonnet allowed-tools:
- Task
- Read
- Glob
- Grep output-style: bullet-points version: 1.0.0 license: MIT
Objectif
Instructions à Exécuter
IMPORTANT : Exécute ce workflow étape par étape :
Phase 2 du workflow automatisé : explorer le codebase pour comprendre les patterns existants SANS interaction.
Instructions
1. Lire le contexte
Déterminer le chemin du workflow state :
workflow_state_file=".claude/data/workflows/issue-${issue_number}-dev-workflow-state.json"
- Lire le workflow state pour connaître la feature en cours
- Si le fichier n'existe pas, exit avec erreur code 1
2. Lancer les agents d'exploration
Lancer 2-3 agents code-explorer en parallèle avec des focus différents :
Agent 1 : Features similaires
Trouve des features similaires à "{feature}" dans le codebase.
Trace leur implémentation de bout en bout.
Retourne les 5-10 fichiers clés à lire.
Agent 2 : Architecture
Mappe l'architecture et les abstractions pour la zone concernée par "{feature}".
Identifie les patterns utilisés (repositories, services, events, etc.).
Retourne les 5-10 fichiers clés à lire.
Agent 3 : Intégrations (si pertinent)
Analyse les points d'intégration existants (APIs, events, commands).
Identifie comment les features communiquent entre elles.
Retourne les 5-10 fichiers clés à lire.
3. Consolider les résultats
- Fusionner les listes de fichiers identifiés
- Lire les fichiers clés pour construire une compréhension profonde
- Identifier les patterns récurrents
4. Mettre à jour le workflow state
{
"currentPhase": 2,
"phases": {
"2": {
"status": "completed",
"completedAt": "{ISO timestamp}",
"durationMs": {durée},
"keyFiles": ["{liste des fichiers clés}"],
"patterns": ["{patterns identifiés}"],
"findings": "{résumé des découvertes}"
}
}
}
Règles
- ✅ Mode automatique : aucune interaction
- ✅ Lancer agents en parallèle si disponibles
- ✅ Documenter les patterns trouvés
- ❌ Jamais demander confirmation (exit 1 si erreur, continuer sinon)
- ✅ Consolider les résultats pour Phase 3
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/automated-codebase-exploration-mmk3ni1d/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/automated-codebase-exploration-mmk3ni1d' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/automated-codebase-exploration-mmk3ni1d/download' --output '.skill-downloads/automated-codebase-exploration-mmk3ni1d/SKILL.md.part' && mv '.skill-downloads/automated-codebase-exploration-mmk3ni1d/SKILL.md.part' '.skill-downloads/automated-codebase-exploration-mmk3ni1d/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/automated-codebase-exploration-mmk3ni1d/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.