CommunityResearch & Data Analysisgithub.com

alchaincyf/darwin-skill

Darwin Skill 2.0 (达尔文.skill 2.0): autonomous skill optimizer integrating Microsoft Research SkillLens 9-dim rubric + SkillOpt validation-gated design + human-in-the-loop checkpoints. Evaluates SKILL.md files, runs hill-climbing with git version control, uses independent judge agents, validates improvements, and generates visual result cards.

What is darwin-skill?

Darwin Skill 2.0 is an autonomous skill optimizer designed for AI agent platforms such as Claude Code, Cursor, and Codex. It evaluates and improves SKILL.md files using a 9-dimension rubric from Microsoft Research SkillLens (arXiv 2605.23899) covering structure, effectiveness, and meta-skill blacklists. The optimizer employs a hill-climbing algorithm with git version control, spawning independent judge agents for blind evaluation, and validating improvements through test prompts with auto-break on diminishing returns. It generates visual result cards to summarize findings, and supports human-in-the-loop checkpoints for safe, iterative optimization. This tool is ideal for developers who need to automatically refine their AI agent skills, improve quality, and ensure adherence to best practices.

Works with✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/alchaincyf/darwin-skill/tree/main/skills/darwin-skill

Installed? Explore more Research & Data Analysis skills: affaan-m/uspto-database, affaan-m/scholar-evaluation, affaan-m/literature-review · View all 6 →

View original→Browse all skills

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Documentation

What does darwin-skill do?

Darwin Skill 2.0 (达尔文.skill 2.0): autonomous skill optimizer, v2.0 integrates Microsoft Research SkillLens (arXiv 2605.23899) 9-dim rubric + SkillOpt (arXiv 2605.23904) validation-gated design + human-in-the-loop checkpoints. Evaluates SKILL.md files using a 9-dimension rubric (structure + effectiveness + meta-skill blacklists), runs hill-climbing with git version control, spawns independent judge agents for blind evaluation, validates improvements through test prompts with auto-break on diminishing returns, and generates visual result cards. Use when user mentions "优化skill", "skill评分", "自动优化", "auto optimize", "skill质量检查", "达尔文", "darwin", "帮我改改skill", "skill怎么样", "提升skill质量", "skill review", "skill打分".

Related Skills

affaan-m/uspto-database

USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.

community

affaan-m/scholar-evaluation

Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.

community

affaan-m/literature-review

Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.

community

affaan-m/everything-claude-code

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

community

forrestchang/andrej-karpathy-skills

Agent skill repository discovered by 10x-chat research.

community

langgenius/backend-code-review

Review backend code for quality, security, maintainability, and best practices based on established checklist rules. Use when the user requests a review, analysis, or improvement of backend files (e.g., `.py`) under the `api/` directory. Do NOT use for frontend files (e.g., `.tsx`, `.ts`, `.js`). Supports pending-change review, code snippets review, and file-focused review.

community
← More Research & Data Analysis skills