AgriciDaniel/skill-forge

Multi-Skill Orchestrator provides a template for routing a broad domain into focused sub-skills with shared references and command-based entry points. Use it when one Claude Code skill needs multiple workflows, context detection, and consistent orchestration.

Skill Forge creates, reviews, and evolves Claude Code skills using the Agent Skills open standard and 3-layer architecture. Use it when you need to create a new skill, scaffold a multi-skill system, test, benchmark, or publish a skill.

Skill Forge scaffolds Claude Code skills from a plan or description. Use it to generate SKILL.md files, sub-skills, scripts, references, agents, and templates for the Agent Skills standard.

Skill Forge Benchmark measures Claude Code skill performance across multiple trials with pass rate, token usage, duration, and variance analysis. Use it to compare versions, detect regressions, and generate benchmark.json reports.

Skill Forge Convert ports Claude Code skills to Codex, Gemini CLI, Antigravity, and Cursor. Use it to analyze compatibility, generate platform-specific files, adapt frontmatter, and convert MCP config.

Skill Forge Eval runs evaluation pipelines for Claude Code skills to check triggering accuracy, workflow correctness, and output quality. It creates eval metadata, runs executor and grading agents, and produces benchmark and feedback reports.

Skill Forge Evolve improves existing Claude Code skills using feedback, logs, or test results. Use it to fix triggering problems, refine instructions, add sub-skills, or evolve the skill’s architecture.

Skill Forge Plan guides the design of new Claude Code skills by defining use cases, selecting a complexity tier, and planning sub-skills and file structure. Use it when planning a skill architecture or decomposing workflows.

Skill Forge Publish packages Claude Code skills for sharing through install scripts, repository layouts, and .skill zip files. Use it when preparing a skill to publish, distribute, or deploy to Claude.ai or a team workspace.

Skill Forge Review audits existing Claude Code skills for quality, structure compliance, and trigger accuracy. It is used to score a skill and identify prioritized fixes when reviewing or validating a skill.