Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
paperthin
SkillsThe 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.
git clone https://github.com/LilMGenius/paperthin.git -
darwin-skill
Skills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.
git clone https://github.com/alchaincyf/darwin-skill.git -
wikimem
SkillsSelf-improving memory for agents: ingest anything, query everything.
git clone https://github.com/naman10parikh/wikimem.git -
ai-research-radar
SkillsAI Research Radar — Evidence-Grounded Trend Ledger for AI Systems
git clone https://github.com/Neetx/ai-research-radar.git -
ai-security-research-radar
SkillsAI Security Research Radar — AI for security and security for AI
git clone https://github.com/Neetx/ai-security-research-radar.git -
honey-stack
SkillsAlways-on workflow layer for Claude Code and Codex: right-sized tasks, smallest complete change, proof before done, plus RSI that learns from every session.
git clone https://github.com/umararshad4/honey-stack.git -
skillmaxxing
SkillsSelf-evolving skills for your coding agent — auto-create and auto-improve skills as you work, no trigger needed.
git clone https://github.com/Bennyoooo/skillmaxxing.git -
skill-evolution
SkillsSelf-improvement feedback loop for AI agent skills — analyzes past sessions, drafts structured improvement proposals, and gates auto-apply behind an evaluation framework. Host-agnostic (Hermes, Claude Code, and any HostAdapter).
git clone https://github.com/Carlo1911/skill-evolution.git -
TricorderKit
SkillsThe local-first second brain for your AI agents - measured, self-improving, and gated so it can't leak what you keep private. 13 Claude Code plugins, 21 skills, Ollama, Neo4j, Qdrant.
git clone https://github.com/GeekFamilyCorp/TricorderKit.git -
SkillHone
SkillsContinual agent skill evolution through persistent decision history. Whole-skill optimisation (SKILL.md + scripts + references) with every decision landing as a local Git issue / PR / wiki. Runs on any agentskills.io runtime — Claude Code, Codex, OpenClaw, Hermes.
git clone https://github.com/Tencent/SkillHone.git -
agentgrid
SkillsSpawn grids of coding agents (Claude, Codex, Gemini, Cursor) in one command.
git clone https://github.com/naman10parikh/agentgrid.git -
operator-memory
SkillsThe self-improving context engine for coding agents.
git clone https://github.com/aerovato/operator-memory.git -
claude-reflect-system
SkillsContinual Learning & Self-improving skills system for Claude Code - learn from corrections, never repeat mistakes
git clone https://github.com/haddock-development/claude-reflect-system.git -
skill-evolution
SkillsImprove Claude Code and OpenAI Codex skills from real feedback, with evidence, regression checks, and human review.
git clone https://github.com/rwang23/skill-evolution.git -
trace-to-practice
SkillsEvidence-backed retrospectives for AI coding-agent histories. Offline indexing, scoped workflow improvements, and bilingual documentation.
git clone https://github.com/wssfk12138/trace-to-practice.git -
Agent skill: examine a product you're authorised to rebuild, build your own, then test against the original and fix gaps until every must-have on a written checklist passes. Inspired by REA (@morluto), not affiliated. MIT.
git clone https://github.com/Speedrunlab/reverse-engineer-anything-self-learning-loop.git -
trinity-claw
SkillsA self-hosted AI agent that thinks, acts, and improves itself – all running privately on your own machine. Browses the web, writes and executes code, manages files, sends emails, monitors URLs, builds websites, and learns from every interaction.
git clone https://github.com/TrinityClaw/trinity-claw.git -
rundesk-cli
SkillsPersistent proactive self-improving AI teammates with memory, skills, and schedules.
git clone https://github.com/rundesk-ai/rundesk-cli.git -
synthadoc
SkillsSynthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.
git clone https://github.com/axoviq-ai/synthadoc.git -
prompt-potter-optimizer
SkillsLLM-driven evolution of prompts and pipelines. Evolves the prompt and the pipeline's parameters together against your labeled data, cuts losing candidates early, and shows every measurement behind the winner. Open source.
git clone https://github.com/PromptPotter/prompt-potter-optimizer.git -
recall
SkillsA self-improving memory layer for Claude Code: captures every session, distills them nightly into a versioned knowledge vault, and surfaces that knowledge back into new sessions — plus proposes skills from recurring patterns.
git clone https://github.com/maxdmyers/recall.git -
curated-claude-code
SkillsA small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.
git clone https://github.com/Sanexxxx777/curated-claude-code.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.