executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Installation & invocation
1. Crée le fichier sur ta machine :
2. Colle le contenu du SKILL.md ci-dessous, et redémarre Claude Code. Tu peux ensuite l'invoquer manuellement avec :
Claude peut aussi la déclencher automatiquement quand le contexte matche.
Exécute un plan d'implémentation écrit en session séparée avec checkpoints de review.
Contenu de la skill
Executing Plans
Overview
Load plan, review critically, execute all tasks, report when complete.
Announce at start: "I'm using the executing-plans skill to implement this plan."
Note: Tell your human partner that Superpowers works much better with access to subagents. The quality of its work will be significantly higher if run on a platform with subagent support (such as Claude Code or Codex). If subagents are available, use superpowers:subagent-driven-development instead of this skill.
The Process
Step 1: Load and Review Plan
- Read plan file
- Review critically - identify any questions or concerns about the plan
- If concerns: Raise them with your human partner before starting
- If no concerns: Create TodoWrite and proceed
Step 2: Execute Tasks
For each task:
- Mark as in_progress
- Follow each step exactly (plan has bite-sized steps)
- Run verifications as specified
- Mark as completed
Step 3: Complete Development
After all tasks complete and verified:
- Announce: "I'm using the finishing-a-development-branch skill to complete this work."
- REQUIRED SUB-SKILL: Use superpowers:finishing-a-development-branch
- Follow that skill to verify tests, present options, execute choice
When to Stop and Ask for Help
STOP executing immediately when:
- Hit a blocker (missing dependency, test fails, instruction unclear)
- Plan has critical gaps preventing starting
- You don't understand an instruction
- Verification fails repeatedly
Ask for clarification rather than guessing.
When to Revisit Earlier Steps
Return to Review (Step 1) when:
- Partner updates the plan based on your feedback
- Fundamental approach needs rethinking
Don't force through blockers - stop and ask.
Remember
- Review plan critically first
- Follow plan steps exactly
- Don't skip verifications
- Reference skills when plan says to
- Stop when blocked, don't guess
- Never start implementation on main/master branch without explicit user consent
Integration
Required workflow skills:
- superpowers:using-git-worktrees - REQUIRED: Set up isolated workspace before starting
- superpowers:writing-plans - Creates the plan this skill executes
- superpowers:finishing-a-development-branch - Complete development after all tasks
Skills proches
auditeur
> Audite n'importe quelle ressource IA pour dire à Boris si elle est légitime, utile pour SA stack, et sans risque. À charger dès qu'il colle ou mentionne : un repo GitHub, un MCP, un skill, un outil/SaaS, une landing page, un guide Google Docs ou Notion, un PDF, une newsletter, une "liste des meilleurs X", ou demande "c'est utile ?", "audite ça", "ça vaut le coup ?", "est-ce que je l'installe ?", "regarde si c'est bien", "est-ce que vous avez déjà ça ?". Le skill vérifie la légitimité, compare à ce que Boris a déjà, applique une grille en 8 critères, et rend un verdict clair (Adopter / Référence / Ignorer / Éviter). Charge-le aussi quand Boris envoie une rafale de liens à trier. Ne PAS charger pour exécuter une tâche métier normale (rédiger, prospecter, coder) : seulement pour ÉVALUER si une ressource externe vaut l'adoption.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
my-stack
Recommandation et trame : crée un skill `my-stack` qui inventorie les MCPs, outils natifs et services connectés à ton Claude. Charge ce skill quand tu veux comprendre le pattern et l'adopter pour ta propre stack. Le but : avoir un skill que tu charges via `/my-stack` quand tu veux router une tâche vers le bon outil, ou savoir ce qui est branché.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session