AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Dev Tooling/
darwin-skill
darwin-skill logo

darwin-skill

Active·★ 7.0k·MIT·Updated 2026-11-14

Darwin Skill applies an experimental loop to improving agent skills. It compares actual task outputs, uses scripted keep-or-revert rules and includes human checkpoints before accepting changes.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-11-18.

License
MIT
Latest release
v3.0.1 · 2026-11-14
Last commit
2026-11-14
Contributors
6
Forks
719
Open issues and PRs
1
First published
2026-04-13

Source: GitHub, npm and PyPI public APIs.

#agent-skills#ai-agents#autoresearch#claude-code#claude-code-skills#claude-skills#codex#dev-tooling
↗ Visit site★ GitHub
01

Features

01Run structural health checks before paid evaluation.
02Compare skill-enabled runs against a bare-model baseline.
03Use blind output comparisons and scripted decisions.
04Separate development and held-out acceptance tasks.
02

Why choose it

+
+
+
+
03

Trade-offs

!
!
!
!
04

Maintenance check

ActiveChecked: 2026-11-18
Last commit
2026-11-14
Commits, last 90 days
12
Releases, last 90 days
2
Latest release
v3.0.1 (2026-11-14)
Open issues
1
Recent issues with at least one comment
9/13
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 5, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #31 单个skill跑40+个评委,5个小时左右0 comments · 2026-11-17

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Use cases

↳Inspect an existing skill collection for structural issues.
↳Evaluate whether a skill improves task results.
↳Optimize a skill and review the resulting diff.
06

Alternatives

⚡Top VS:
VSskills★1.5k→VStaste-skill★117.7k→VSpstack★4.4k→VSskills★4.0k→
skills logo
skills★ 1.5k
Reusable AI agent skills for software factories: explore ideas, write specs, implement, review, and run autonomous research. Works with Claude Code, Codex, and other skill-compatible agents.
VSCompare→
video-shotcraft logo
video-shotcraft★ 21.0k
AI video skill for Claude Code & Codex — cinematic, editable product promos with Remotion: 124 shot recipe cards, 150 motion previews, beat sync, sound design, Motion Workbench & JianYing (CapCut CN) export.
taste-skill logo
taste-skill★ 117.7k
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
VSCompare→
pstack logo
pstack★ 4.4k
Use pstack with claude, codex, pi - Skills and principles for rigorous AI-assisted engineering
VSCompare→
skills logo
skills★ 4.0k
Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.
VSCompare→
beautify-github-readme logo
beautify-github-readme★ 2.0k
README design skill for Claude Code & Codex. 帮你把 GitHub README 做得好看又好懂。
VSCompare→
claude-code-my-workflow logo
claude-code-my-workflow★ 1.7k
A ready-to-fork Claude Code template for academic research — papers, data analysis (R, Stata, Python), slides and teaching — with multi-agent review, enforced quality gates and replication protocols. Codex and Antigravity can use it too.
VSCompare→
open-steps logo
open-steps★ 1.3k
Plain-language agent skills for Claude Code, Codex, Cursor and Gemini CLI: honest session reports, straight verdicts, steps you can follow. MIT.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Use cases06Alternatives
alchaincyf /
darwin-skill
↗

Experimental evolution loop for iteratively improving agent skills with scripted keep-or-revert rules

7.0k719MIT
Last commit4d ago
StatusActive
CategoryDev Tooling
Contributors6
Latest releasev3.0.1
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.