Skill Improvement

The meta-skill that improves your skills, including itself. Turns the corrections, judgement calls and repeated workflows of your sessions (autonomous or human-led) into small skill updates and new skill candidates, each with its evidence and reason. Nothing touches a skill until you approve it. Augmented Expertise in practice. CC BY 4.0.

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.

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Improve how you work with AI. Portable Claude Code and Codex skill with evidence-based assessment and evaluation.

Harness self-evolution: update targets, theory, evaluation, and reported evidence. Bilingual reading list and project website.

达尔文.skill —— 一个让你的Skill无限进化的系统：评估→改进→测试→保留或回滚 | Autoresearch-inspired autonomous skill optimization for Claude Code. Evaluate, improve, test, keep or revert.

Privacy-first AI project and Skill feedback loop for Codex and Claude Code—turn corrections into traceable requirements and verified repair plans.

The missing runtime for Agent Skills — health monitoring, self-improvement, and dependency management for any AI agent framework. Zero dependencies.

A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects. | evomap.ai

Auto AI improver. Cost and token burn reducer, turn saver, and focus keeper for Claude Code, Codex, Copilot, Gemini, and more: surgical read hints, PDF/Office/CSV/md file interception, 255+ filter & interception rules, compact manifest injection, image shrinking, cache and compact skills, cache MCPs, prompt injection protection, and much more.

This repository packages a skill that helps AI coding agents generate, review, and improve Hexabot v3 workflow YAML, action contracts, bindings, memory requirements, and agentic automation designs.Hexabot workflow skill

AI skill for personal weekly rpg-style retrospectives where you choose the story

Continuous improvement for AI coding agents: Penelopa analyzes real Codex and Claude Code sessions, finds repeated workflow patterns, and turns them into reusable skills, checks, prompts, and recommendations.

Public repository of AI coding skills, curated improved best-practice skills, and runtime surfaces for CLI, API, MCP, and A2A.

⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA

Claude Code skill that transforms vague prompts into structured, expert-level prompts using 7 research-backed frameworks (CO-STAR, RISEN, RISE, TIDD-EC, RTF, CoT, CoD)

Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.

mentor — a session-insights skill for AI coding agents. This skill reads your local Claude Code and OpenAI Codex history and writes an /insights-style HTML report on how you work: what you build, where you lose time, and concrete fixes. An agent skill for Claude Code, Codex, and any skills-capable agent.

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

A professional ChatGPT Skill for creating, editing, reviewing, extracting, validating, and visually improving production-ready PDF files.

The skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method.

A self-improving agent. Tested on DeepSeek, Qwen, Kimi, GLM models. Supports MCP, Skills.

Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems.

Curated, install-ready skills for Hermes Agent (v0.17.0). 72 built-in + 101 optional bundled skills + 85 community skills, plugins & tools for the self-improving AI agent from Nous Research. Cross-compatible with Claude Code, OpenClaw, Cursor, and Windsurf.