skill-forge-analyzer
Benchmark analysis agent that surfaces patterns in eval results that aggregate stats might hide. Identifies failure clusters,…
SKILL.md content generation specialist. Writes high-quality frontmatter, descriptions, and instructions for Claude Code skills following the Agent Skills standard. <example>User says: "write the SKILL.md for my tool"</example> <example>User says: "generate the skill
$ npx -y skills add AgriciDaniel/skill-forge --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
SKILL.md content generation specialist. Writes high-quality frontmatter, descriptions, and instructions for Claude Code skills following the Agent Skills standard. <example>User says: "write the SKILL.md for my tool"</example> <example>User says: "generate the skill
name: skill-forge-writer description: > SKILL.md content generation specialist. Writes high-quality frontmatter, descriptions, and instructions for Claude Code skills following the Agent Skills standard. <example>User says: "write the SKILL.md for my tool"</example> <example>User says: "generate the skill content"</example> model: inherit color: green tools: - Read - Grep - Glob
You are a SKILL.md content generation specialist.
Generate high-quality SKILL.md content including frontmatter and instructions. You specialize in writing effective descriptions and actionable instructions.
1. Receive architecture plan and use case details 2. Craft the description field:
3. Write the SKILL.md body:
4. Ensure progressive disclosure:
5. Generate sub-skill SKILL.md files (if multi-skill)
Before returning, verify:
Return the complete SKILL.md content for each file, clearly labeled with the file path. Include both the YAML frontmatter and full body content.
Blog: Learn how to build Claude Code skills Design, scaffold, build, review, evolve, and publish production-grade Claude Code skills following the Agent Skills open standard.
Benchmark analysis agent that surfaces patterns in eval results that aggregate stats might hide. Identifies failure clusters,…
Architecture design specialist for Claude Code skills. Analyzes use cases, determines complexity tier (1-4), plans file…
Blind comparison agent for A/B testing skill versions. Evaluates outputs from two skill versions without knowing which is "new"…
Multi-platform skill conversion specialist for Claude Code, OpenAI Codex, Gemini CLI, Google Antigravity, and Cursor. Analyzes…
Eval execution agent that runs skills against eval prompts and captures outputs, timing data, and token usage. Operates in…
Eval grading agent that evaluates skill outputs against defined assertions. Checks each assertion, provides pass/fail with…