Automated summary
Generates a detailed implementation plan file in docs/specs/ based on the chosen architecture, using task management.
Strengths
- Creates structured, actionable plans with clear steps.
- Integrates with workflow state management.
- Specifies tests before implementation.
- Uses task tracking for user visibility.
Limitations
- Only works within the defined workflow phases (requires previous phases completed).
- Assumes specific directory structure (.claude/data).
- Plan generation may be too rigid for complex projects.
When you need a detailed, actionable implementation plan after architecture decisions are made.
When you need a quick, informal plan or the project does not follow this structured workflow.
Security analysis
SafeThe skill uses only allowed tools (Write, Read, Glob) and performs only local file operations: reading state, creating a directory with mkdir -p, and writing a spec file. There is no network access, code execution, or destructive commands, and no manipulation of sensitive data or agents.
No concerns found
How this analysis is madeExamples
Use dev:plan to create an implementation plan for adding a new /api/users endpoint.Generate a plan for implementing user authentication with JWT.name: dev:plan description: Générer plan d'implémentation dans docs/specs/ (Phase 4) model: sonnet allowed-tools: [Write, Read, Glob] version: 1.0.0 license: MIT
Objectif
Phase 4 du workflow de développement : générer un plan d'implémentation détaillé basé sur l'architecture choisie.
Instructions
Instructions à Exécuter
IMPORTANT : Exécute ce workflow étape par étape :
1. Créer les tâches de planification
Utiliser TaskCreate pour chaque étape :
TaskCreate #1: Lire le contexte du workflow
TaskCreate #2: Créer le répertoire docs/specs
TaskCreate #3: Générer le plan d'implémentation
TaskCreate #4: Afficher le résumé
TaskCreate #5: Mettre à jour le workflow state
Important :
- Utiliser
activeForm(ex: "Lisant le contexte", "Générant le plan") - Chaque tâche doit être marquée
in_progresspuiscompleted
Pattern d'exécution pour chaque étape :
TaskUpdate→ tâche enin_progress- Exécuter l'étape
TaskUpdate→ tâche encompleted
2. Lire le contexte
🔄 Progression : TaskUpdate → tâche #1 en in_progress
- Lire
.claude/data/.dev-workflow-state.jsonpour récupérer :- La feature description
- Les décisions de clarification
- L'architecture choisie
- Si phases précédentes non complétées, rediriger vers la phase manquante
🔄 Progression : TaskUpdate → tâche #1 en completed
3. Créer le répertoire si nécessaire
🔄 Progression : TaskUpdate → tâche #2 en in_progress
mkdir -p docs/specs
🔄 Progression : TaskUpdate → tâche #2 en completed
4. Générer le plan
🔄 Progression : TaskUpdate → tâche #3 en in_progress
Créer le fichier docs/specs/feature-{nom-kebab-case}.md avec la structure complète du plan
🔄 Progression : TaskUpdate → tâche #3 en completed
5. Afficher le résumé
🔄 Progression : TaskUpdate → tâche #4 en in_progress
Présenter le plan généré.
🔄 Progression : TaskUpdate → tâche #4 en completed
6. Mettre à jour le workflow state
🔄 Progression : TaskUpdate → tâche #5 en in_progress
Mettre à jour .claude/data/.dev-workflow-state.json
🔄 Progression : TaskUpdate → tâche #5 en completed
Task Management
Progression du workflow :
- 5 tâches créées à l'initialisation
- Chaque étape suit le pattern :
in_progress→ exécution →completed - La tâche #3 (génération du plan) est la plus importante
- Utiliser
TaskListpour voir la progression - Les tâches permettent à l'utilisateur de suivre la création du plan d'implémentation
Prochaine étape
✅ Plan généré : docs/specs/feature-{nom}.md
Prochaine étape : /dev:code docs/specs/feature-{nom}.md
⚠️ L'implémentation nécessite ton approbation explicite.
Règles
- Le plan doit être actionnable (pas de descriptions vagues)
- Chaque étape doit avoir des fichiers et des tâches clairs
- Les tests doivent être spécifiés avant l'implémentation
- Respecter les conventions du projet (CLAUDE.md)
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/implementation-planning-phase-4-mm5t8all/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/implementation-planning-phase-4-mm5t8all' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/implementation-planning-phase-4-mm5t8all/download' --output '.skill-downloads/implementation-planning-phase-4-mm5t8all/SKILL.md.part' && mv '.skill-downloads/implementation-planning-phase-4-mm5t8all/SKILL.md.part' '.skill-downloads/implementation-planning-phase-4-mm5t8all/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/implementation-planning-phase-4-mm5t8all/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.