Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
pro-workflow
SkillsClaude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.
git clone https://github.com/rohitg00/pro-workflow.git -
skills
SkillsAgent skills to find and fix software bugs
git clone https://github.com/workersio/skills.git -
guardrail-forge
SkillsCorrect Claude once. It stays corrected. A Claude Code skill that turns corrections into tested, tamper-proof hook guardrails.
git clone https://github.com/MohammedAtya/guardrail-forge.git -
claude-reflect
SkillsA self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md.
git clone https://github.com/BayramAnnakov/claude-reflect.git -
skills
SkillsAgent skills for correctness-first engineering.
git clone https://github.com/CheckPickerUpper/skills.git -
gsd-skill-creator
SkillsIntroduces a comprehensive agent-based framework for guided software development (GSD)
git clone https://github.com/Tibsfox/gsd-skill-creator.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 -
Local user preferences with sourced corrections, scoped recall, and Codex/Cursor host adapters. / 本地保存带来源的偏好,支持更正、限定检索与 Codex/Cursor 适配。
git clone https://github.com/KarmenLoop/user-behavior-personalization.git -
ElevenPowers
Skills"make", but for correctness claims. Decides when a coding agent's work is actually done, and un-decides it when you edit the code.
git clone https://github.com/SatyamSingh-Git/ElevenPowers.git -
one-skill-to-rule-them-all
SkillsThe 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.
git clone https://github.com/rebelytics/one-skill-to-rule-them-all.git -
hermeneutic
SkillsTurn corrections from AI agent logs into guidance for similar tasks. Local memory with semantic retrieval, prompt-context hooks, and response checks.
git clone https://github.com/hermes-labs-ai/hermeneutic.git -
agami-core
SkillsThe trust layer between AI and your data. Turns your database schema - messy joins, undocumented tables, into a governed semantic model so AI answers with correct SQL and a receipt on every answer. Run it locally, or self-host a shared team server with Docker.
git clone https://github.com/AgamiAI/agami-core.git -
PeerHarness
SkillsYour team votes on how its AI coding agents behave. Correct Claude Code once, and PeerHarness turns it into a one-sentence rule (an Agent Skill) that a majority of your team votes in for every member's agent. Peer-to-peer, no server.
git clone https://github.com/aryehlev/PeerHarness.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.