Skip to content

pyxl-dev/skillforge

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 

Repository files navigation

SkillForge — Skill Lifecycle Manager for Claude Code

Orchestrator for creating, improving, auditing, and benchmarking Claude Code skills.

Installation

  1. Clone or download this repo into your skills directory:

    git clone https://github.com/pyxl-dev/skillforge.git ~/.claude/skills/SkillForge
  2. Verify the structure:

    ~/.claude/skills/SkillForge/
    ├── SKILL.md              # Main entry point
    └── Workflows/
        ├── Create.md         # Create a skill from scratch
        ├── Improve.md        # Improve an existing skill
        ├── Audit.md          # Audit all skills
        └── Benchmark.md      # A/B compare skill versions
    

Dependencies

skill-creator (required for full functionality)

skill-creator is Anthropic's official plugin for the skill eval/improve cycle. SkillForge relies on it for creating, testing, improving, and benchmarking skills.

Install it from Claude Code:

/plugin skill-creator@claude-plugins-official

This registers the plugin and makes the skill-creator skill available. You can verify it's installed by running /plugin and checking that skill-creator appears in the list.

Without skill-creator, SkillForge still works in degraded mode — you can run Audit (structural validation) but Create, Improve, and Benchmark workflows won't have access to the eval pipeline.

Structural validator (optional)

Any skill that enforces structure conventions (TitleCase naming, flat folders, frontmatter format). Optional if you have your own conventions or want to skip canonicalization.

Workflows

Workflow Trigger Description
Create "forge a skill", "create and validate skill" Full pipeline: interview, draft, test, iterate, canonicalize
Improve "improve skill X", "fix skill X" Evaluate current state, improve via feedback, re-canonicalize
Audit "audit skills", "audit all skills" Scan all skills, produce quality report with scores
Benchmark "benchmark skill X" A/B comparison with metrics (pass rate, time, tokens)

Usage

In Claude Code, just say:

  • "Forge a skill for managing Docker stacks"
  • "Improve the Research skill"
  • "Audit all my skills"
  • "Benchmark the Parser skill"

How It Works

SkillForge is a pure orchestrator — it delegates everything and duplicates nothing:

  1. skill-creator handles the content lifecycle (drafting, testing, evaluating, improving)
  2. Structural validation handles conventions (naming, folder structure, frontmatter format)
  3. SkillForge routes to the right workflow and chains them in the correct order

License

MIT

About

Skill lifecycle manager for Claude Code — create, improve, audit, and benchmark skills

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors