Cette page est affichée en anglais. Une traduction française est en cours.
SkillsMay 12, 2026·2 min de lecture

Claude Skill Factory — Build & Install Claude Code Skills

Claude Skill Factory ships ready-made skills and slash commands to build, validate, and install Claude Code skills as repeatable team assets.

Prêt pour agents

Cet actif peut être lu et installé directement par les agents

TokRepo expose une commande CLI universelle, un contrat d'installation, le metadata JSON, un plan selon l'adaptateur et le contenu raw pour aider les agents à juger l'adaptation, le risque et les prochaines actions.

Needs Confirmation · 66/100Policy : confirmer
Surface agent
Tout agent MCP/CLI
Type
Skill
Installation
Single
Confiance
Confiance : Established
Point d'entrée
~/.claude/skills
Commande CLI universelle
npx tokrepo install 2fa75c0b-e7d5-4f70-acce-61d7cd5e064c
Introduction

Claude Skill Factory ships ready-made skills and slash commands to build, validate, and install Claude Code skills as repeatable team assets.

  • Best for: Claude Code users who want a structured way to generate and share skills/prompts
  • Works with: Claude Code (skills, slash commands), local filesystem, team repos for versioning
  • Setup time: 10–25 minutes

Practical Notes

  • Quant: start by installing 1 skill and measure time-to-first-use (clone → install → first output).
  • Quant: keep generated skills in a repo and review via PRs weekly to avoid prompt drift.

Pattern: treat skills like code

To keep skills maintainable:

  • store them in your repo,
  • review changes via PR,
  • and keep small, testable boundaries (inputs/outputs).

Suggested workflow

  1. Use the builder commands to generate a first draft.
  2. Run validation and package outputs.
  3. Install into ~/.claude/skills/ and test on one real task.
  4. Promote only the stable ones into your team baseline.

This reduces the “random prompt folder” problem and makes skills reusable across projects.

FAQ

Q: Do I have to install everything? A: No. Start with one included skill (Prompt Factory) and expand after you trust the workflow.

Q: Where should skills live long-term? A: In a team repo, with PR review, then installed to user machines as a deployment step.

Q: How do I verify quality? A: Run the same task twice and check outputs for consistency, safety, and useful structure.

🙏

Source et remerciements

Source: https://github.com/alirezarezvani/claude-code-skill-factory > License: MIT > GitHub stars: 764 · forks: 149

Fil de discussion

Connectez-vous pour rejoindre la discussion.
Aucun commentaire pour l'instant. Soyez le premier à partager votre avis.

Actifs similaires