InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. pro-workflow

    Skills

    Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested skills.

    Stale GitHub, rohitg00 2,916 ★Updated 48 days ago

    git clone https://github.com/rohitg00/pro-workflow.git
  2. skills

    Skills

    Agent skills to find and fix software bugs

    Stale GitHub, workersio 204 ★MITUpdated 3 months ago

    git clone https://github.com/workersio/skills.git
  3. Correct Claude once. It stays corrected. A Claude Code skill that turns corrections into tested, tamper-proof hook guardrails.

    Stale GitHub, MohammedAtya 7 ★MITUpdated 32 days ago

    git clone https://github.com/MohammedAtya/guardrail-forge.git
  4. A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md.

    Stale GitHub, BayramAnnakov 1,801 ★MITUpdated 44 days ago

    git clone https://github.com/BayramAnnakov/claude-reflect.git
  5. skills

    Skills

    Agent skills for correctness-first engineering.

    Stale GitHub, CheckPickerUpper 8 ★MITUpdated 21 days ago

    git clone https://github.com/CheckPickerUpper/skills.git
  6. Introduces a comprehensive agent-based framework for guided software development (GSD)

    Stale GitHub, Tibsfox 71 ★Custom licence (see repository)Updated 4 months ago

    git clone https://github.com/Tibsfox/gsd-skill-creator.git
  7. Continual Learning & Self-improving skills system for Claude Code - learn from corrections, never repeat mistakes

    Stale GitHub, haddock-development 382 ★Updated 10 months ago

    git clone https://github.com/haddock-development/claude-reflect-system.git
  8. 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。

    Stale GitHub, KarmenLoop 21 ★Apache-2.0Updated 23 days ago

    git clone https://github.com/KarmenLoop/user-behavior-personalization.git
  9. 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.

    Stale GitHub, SatyamSingh-Git 15 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/SatyamSingh-Git/ElevenPowers.git
  10. 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.

    Indexed GitHub, rebelytics 3,925 ★CC-BY-4.0Updated yesterday

    git clone https://github.com/rebelytics/one-skill-to-rule-them-all.git
  11. hermeneutic

    Skills

    Turn corrections from AI agent logs into guidance for similar tasks. Local memory with semantic retrieval, prompt-context hooks, and response checks.

    Stale GitHub, hermes-labs-ai 9 ★Apache-2.0Updated 27 days ago

    git clone https://github.com/hermes-labs-ai/hermeneutic.git
  12. agami-core

    Skills

    The 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.

    Indexed GitHub, AgamiAI 30 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/AgamiAI/agami-core.git
  13. PeerHarness

    Skills

    Your 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.

    Stale GitHub, aryehlev 10 ★Apache-2.0Updated 4 days ago

    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.