Skip to content
Back to search

skill-forge

Ultimate Claude Code skill creator — design, scaffold, build, review, evolve, and publish production-grade AI agent skills

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/agricidaniel--skill-forge/badge.svg)](/listings/agricidaniel--skill-forge)

HTML

<a href="/listings/agricidaniel--skill-forge"><img src="/api/listings/agricidaniel--skill-forge/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Unix / macOS / WSL

git clone https://github.com/AgriciDaniel/skill-forge.git
cd skill-forge
bash install.sh

Uninstall

bash install.sh --uninstall

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 151 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Skill Forge — Ultimate Claude Code Skill Creator
  2. ![Skill Forge](skill-forge-header.jpeg)
  3. > **Blog:** [Learn how to build Claude Code skills](https://agricidaniel.com/blog/skill-forge-build-claude-code-skills)
  4. Design, scaffold, build, review, evolve, and publish production-grade Claude Code skills following the [Agent Skills open standard](https://agentskills.io).
  5. ## Features
  6. - **Plan** — Analyze use cases, select complexity tier (1-4), design architecture with sub-skill decomposition
  7. - **Build** — Scaffold complete skill file trees with SKILL.md, sub-skills, scripts, references, and agents
  8. - **Review** — Audit any skill with a 0-100 health score across 6 quality categories
  9. - **Evolve** — Fix triggering issues, improve instructions, refine architecture based on feedback
  10. - **Publish** — Package as `.skill` files, generate install scripts, prepare for GitHub distribution
  11. - **Convert** — Port skills to OpenAI Codex, Google Gemini CLI, Google Antigravity, and Cursor
  12. - **Eval** — Run evaluation pipelines with assertions, grading, and multi-agent execution
  13. - **Benchmark** — Measure performance with variance analysis, multiple trials, and threshold gating
  14. ## Installation
  15. ### Unix / macOS / WSL
  16. ```bash
  17. git clone https://github.com/AgriciDaniel/skill-forge.git
  18. cd skill-forge
  19. bash install.sh
  20. ```
  21. ### Uninstall
  22. ```bash
  23. bash install.sh --uninstall
  24. ```
  25. ## Usage
  26. ### Commands
  27. | Command | Description |
  28. |---------|-------------|
  29. | `/skill-forge` | Interactive skill creation wizard |
  30. | `/skill-forge plan <domain>` | Architecture and design planning |
  31. | `/skill-forge build <name>` | Scaffold and build a skill |
  32. | `/skill-forge review <path>` | Audit an existing skill (0-100 score) |
  33. | `/skill-forge evolve <path>` | Improve a skill from feedback |
  34. | `/skill-forge publish <path>` | Package for distribution |
  35. | `/skill-forge eval <path>` | Run eval pipeline to test skill quality |
  36. | `/skill-forge benchmark <path>` | Benchmark skill with variance analysis |
  37. | `/skill-forge convert <path>` | Convert to Codex, Gemini, Antigravity, or Cursor |
  38. ### Examples
  39. Create a simple skill:
  40. ```
  41. /skill-forge build my-tool
  42. ```
  43. Design a complex skill ecosystem:
  44. ```
  45. /skill-forge plan "DevOps toolkit for Docker and Kubernetes management"
  46. ```
  47. Review an existing skill:
  48. ```
  49. /skill-forge review ~/.claude/skills/my-skill
  50. ```
  51. Convert a skill for other platforms:
  52. ```
  53. /skill-forge convert ~/.claude/skills/my-skill
  54. ```
  55. Quick scaffold with the CLI script:
  56. ```bash
  57. python skill-forge/scripts/init_skill.py devops-toolkit --tier 3 --sub docker,k8s,monitor
  58. ```
  59. ## Skill Complexity Tiers
  60. | Tier | Name | Structure | Best For |
  61. |------|------|-----------|----------|
  62. | 1 | Minimal | Single SKILL.md | Simple workflows, document generation |
  63. | 2 | Workflow | SKILL.md + scripts | Tasks needing deterministic validation |
  64. | 3 | Multi-Skill | Orchestrator + sub-skills | Complex domains with multiple workflows |
  65. | 4 | Ecosystem | Full system with agents | Enterprise-grade parallel analysis |
  66. ## Architecture
  67. ```
  68. skill-forge/ # Main orchestrator (Tier 4)
  69. SKILL.md # Entry point and routing
  70. references/ # On-demand knowledge (10 files)
  71. scripts/ # Execution scripts (8 files)
  72. assets/templates/ # Skill templates (4 tiers)
  73. skills/
  74. skill-forge-plan/ # Architecture planning
  75. skill-forge-build/ # Scaffolding and generation
  76. skill-forge-review/ # Quality auditing
  77. skill-forge-evolve/ # Improvement and iteration
  78. skill-forge-eval/ # Evaluation pipeline
  79. skill-forge-benchmark/ # Performance benchmarking
  80. skill-forge-publish/ # Distribution and packaging
  81. skill-forge-convert/ # Multi-platform conversion
  82. agents/
  83. skill-forge-architect.md # Architecture design agent
  84. skill-forge-writer.md # Content writing agent
  85. skill-forge-validator.md # Validation agent
  86. skill-forge-converter.md # Platform conversion agent
  87. skill-forge-executor.md # Eval execution agent
  88. skill-forge-grader.md # Eval grading agent
  89. skill-forge-analyzer.md # Benchmark analysis agent
  90. skill-forge-comparator.md # Blind A/B comparison agent
  91. ```
  92. ## Dependencies
  93. - **Python 3.10+** — Required for scaffolding, validation, packaging, conversion, eval, and benchmarking scripts
  94. - **Claude Code** — The CLI tool these skills are built for
  95. - No external Python packages required (stdlib only)
  96. ## Built With
  97. - [Agent Skills Standard](https://agentskills.io) — Open standard for AI agent skills
  98. - [3-Layer Architecture](skill-forge/references/pro-agent.md) — Directive + Orchestration + Execution
  99. - Inspired by [claude-seo](https://github.com/AgriciDaniel/claude-seo) and [Anthropic Skills](https://github.com/anthropics/skills)
  100. ## Support
  101. - **Issues**: [GitHub Issues](https://github.com/AgriciDaniel/skill-forge/issues)
  102. - **Discussions**: [GitHub Discussions](https://github.com/AgriciDaniel/skill-forge/discussions)
  103. ## License
  104. [MIT](LICENSE)
  105. ---
  106. ## Author
  107. Built by [Agrici Daniel](https://agricidaniel.com/about) - AI Workflow Architect.
  108. - [Blog](https://agricidaniel.com/blog) - Deep dives on AI marketing automation
  109. - [AI Marketing Hub](https://www.skool.com/ai-marketing-hub) - Free community, 2,800+ members
  110. - [YouTube](https://www.youtube.com/@AgriciDaniel) - Tutorials and demos
  111. - [All open-source tools](https://github.com/AgriciDaniel)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.