Darwin Skill 2.0

Name: Darwin Skill 2.0
Author: alchaincyf

Autonomous skill optimizer that uses a 9-dimension rubric to evaluate and improve SKILL.md files through an iterative, validation-gated loop.

triggers:优化skillskill评分自动优化auto optimizeskill质量检查达尔文darwin帮我改改skillskill怎么样提升skill质量skill reviewskill打分

Darwin Skill 2.0 is an autonomous system for optimizing agent skills. Inspired by Karpathy's autoresearch, it implements a rigorous "Evaluate → Improve → Test → Keep/Revert" cycle.

Key Features:

9-Dimension Rubric: Based on Microsoft Research SkillLens, it evaluates structure (frontmatter, workflow, failure modes, checkpoints, specificity, resource integration), effectiveness (overall architecture, real-world test performance), and meta-skills (anti-patterns and blacklists).
Validation-Gated Design: Uses independent judge agents to prevent self-bias and ensures that improvements are strictly measured against a baseline.
Hill-Climbing Optimization: Iteratively targets the lowest-scoring dimensions to raise overall skill quality while avoiding over-engineering.
Runtime Neutrality: Automatically scans for and removes runtime-specific language (e.g., "Claude Code only") to ensure skills work across all compatible environments.
Visual Reporting: Generates professional result cards (Swiss, Terminal, or Newspaper styles) to document performance gains.

Not yet audited

This skill has not been reviewed by our automated audit pipeline yet.

Information

Repository: alchaincyf

Related Skills

Development Worktree

Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

Bounty Hunter — Atlas

Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.

Junshi — Research Advisor

Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.

Full Stack Builder

End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Feishu Voice Sender

Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.

Claw Bench

Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.

Back to Skills

Darwin Skill 2.0

from alchaincyf

Autonomous skill optimizer that uses a 9-dimension rubric to evaluate and improve SKILL.md files through an iterative, validation-gated loop.

triggers:优化skillskill评分自动优化auto optimizeskill质量检查达尔文darwin帮我改改skillskill怎么样提升skill质量skill reviewskill打分

Darwin Skill 2.0 is an autonomous system for optimizing agent skills. Inspired by Karpathy's autoresearch, it implements a rigorous "Evaluate → Improve → Test → Keep/Revert" cycle.

Key Features:

9-Dimension Rubric: Based on Microsoft Research SkillLens, it evaluates structure (frontmatter, workflow, failure modes, checkpoints, specificity, resource integration), effectiveness (overall architecture, real-world test performance), and meta-skills (anti-patterns and blacklists).
Validation-Gated Design: Uses independent judge agents to prevent self-bias and ensures that improvements are strictly measured against a baseline.
Hill-Climbing Optimization: Iteratively targets the lowest-scoring dimensions to raise overall skill quality while avoiding over-engineering.
Runtime Neutrality: Automatically scans for and removes runtime-specific language (e.g., "Claude Code only") to ensure skills work across all compatible environments.
Visual Reporting: Generates professional result cards (Swiss, Terminal, or Newspaper styles) to document performance gains.

Not yet audited

This skill has not been reviewed by our automated audit pipeline yet.

Information

Repository: alchaincyf

Related Skills

Development Worktree

Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

Bounty Hunter — Atlas

Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.

Junshi — Research Advisor

Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.

Full Stack Builder

End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Feishu Voice Sender

Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.

Claw Bench

Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.

Darwin Skill 2.0

Tags

Not yet audited

Information

Related Skills

Darwin Skill 2.0

Tags

Not yet audited

Information

Related Skills