self-evolving-agents skills

microsoft/SkillOpt

Skill Claude CodeCodex ✓ vendor

Reference-only OpenClaw adaptation of SkillOpt-Sleep. Use it to study or port the contributed DeepSeek wrapper, not as a ready-to-run installation.

mims-harvard/AutoScientists

Skill Claude CodeCodex

Protocol for GPU agents to clone external GitHub repos, install their dependencies, download pretrained weights, and integrate them as featurizers or models inside a focus-area train.py. Use this when a proposal references a GitHub repo or pretrained checkpoint that is not already present in the focus-area workspace.

YunjueTech/Yunjue-Agent

Skill Claude CodeCodex

Complete MacBook optimization suite: monitoring, troubleshooting, cleanup, and performance tuning. Works on all Macs (Intel & Apple Silicon). No extra tools required.

OpenLAIR/OpenSkill

Skill Claude Code

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

bogdanbaciu21/skills

Skill Codex

Generate copy-paste agent prompts and a coordinator playbook from a pre-built parallel work plan, or turn a cheap design dispute into competing "code wins" implementation variants. Use when the user has decomposed a large task into independent, conflict-free parallel tracks and needs formatted prompts for multiple…