agricidaniel/skill-forge
9 skills · 33 total installs
$npx skills add agricidaniel/skill-forgeSkillInstalls
skill-forgeUltimate Claude Code skill creator and architect. Designs, scaffolds, builds, reviews, evolves, and publishes production-grade Claude Code skills following the Agent Skills open standard and 3-layer askill-forge-benchmarkBenchmark Claude Code skill performance with variance analysis, tracking pass rate, execution time, and token usage across iterations. Runs multiple trials per eval for statistical reliability, aggregskill-forge-buildScaffold and build Claude Code skills from plans or descriptions. Generates SKILL.md files, sub-skills, scripts, references, agents, and templates following the Agent Skills standard. Use when user saskill-forge-convertConvert Claude Code skills to work on OpenAI Codex, Google Gemini CLI, Google Antigravity, and Cursor. Analyzes platform-specific features, generates target files (openai.yaml, AGENTS.md, GEMINI.md, .skill-forge-evalRun evaluation pipelines on Claude Code skills to test triggering accuracy, workflow correctness, and output quality. Spawns executor, grader, comparator, and analyzer sub-agents for parallel evaluatiskill-forge-evolveImprove and iterate on existing Claude Code skills based on usage feedback, test results, or changing requirements. Handles under/over-triggering fixes, instruction refinement, new sub-skill addition,skill-forge-planArchitecture and design planning for new Claude Code skills. Guides through use case definition, complexity tier selection, sub-skill decomposition, and file structure planning. Use when user says "plskill-forge-publishPackage and distribute Claude Code skills for sharing via GitHub, Claude.ai uploads, or team deployment. Creates install scripts, documentation, and .skill packages. Use when user says "publish skill"skill-forge-reviewAudit and validate existing Claude Code skills for quality, triggering accuracy, structure compliance, and best practices. Scores skills on a 0-100 scale and provides prioritized improvement recommend