InnerVault

Library

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

Results

Looks like a goal we have a starting path for: I want to build an AI agent

  1. sepia

    Prompts

    De-AI writing skill for any Agent Skills-compatible agent (77+ via the Skills CLI), with native plugins for Claude Code, Codex, Grok Build, and Antigravity. Narrative-architecture repair for fiction, venue-matched rules for professional prose. Based on StoryScope (arXiv:2604.03136).

    Stale GitHub, Nanako0129 3,657 ★MITUpdated 13 days ago

    git clone https://github.com/Nanako0129/sepia.git
  2. claude-skills

    Prompts

    200+ production-ready Claude Code skills for sales, marketing, design, engineering, and AI agent architecture. Built and maintained by OneWave AI.

    Stale GitHub, OneWave-AI 367 ★MITUpdated 27 days ago

    git clone https://github.com/OneWave-AI/claude-skills.git
  3. coco

    Prompts

    Coco Super Intelligence: agent skills, slash commands and subagents for Claude Code, Cursor and Codex. One command installs them into the tool you already use.

    Indexed GitHub, coco-research 632 ★Apache-2.0Updated today

    git clone https://github.com/coco-research/coco.git
  4. agents.md

    Prompts

    A drop-in AGENTS.md system prompt for coding agents: full execution, no hedging, no moralizing, no fade-to-black.

    Stale GitHub, lordon1a 87 ★Updated 23 days ago

    git clone https://github.com/lordon1a/agents.md.git
  5. Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the Agent Skills standard.

    Indexed GitHub, CodeAlive-AI 185 ★MITUpdated yesterday

    git clone https://github.com/CodeAlive-AI/ai-driven-development.git
  6. Evidence-backed use cases, prompts, integrations, evaluations, and safety notes for OpenAI GPT-6 Astra.

    Stale GitHub, Anil-matcha 1,147 ★MITUpdated 44 days ago

    git clone https://github.com/Anil-matcha/awesome-gpt-6-astra.git
  7. cc-tree

    Prompts

    Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideation, adversarial critique, and design-space exploration. 12 framings × hard-ban-on-incomplete-leaves × stable convergence.

    Stale GitHub, skymanbp 81 ★MITUpdated 12 days ago

    git clone https://github.com/skymanbp/cc-tree.git
  8. Open-source AI evals toolkit: skills that guide AI coding agents to write eval rubrics, eval datasets (User Input Grid), trace codes, code evaluators and LLM-as-a-judge prompts. From the Reforge AI Evals course by Calibre.

    Stale GitHub, Calibre-Labs 95 ★MITUpdated 9 days ago

    git clone https://github.com/Calibre-Labs/reforge-ai-evals.git
  9. Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude Code, OpenClaw, Codex, and Hermes.

    Indexed GitHub, conorbronsdon 5,669 ★MITUpdated yesterday

    git clone https://github.com/conorbronsdon/avoid-ai-writing.git
  10. linkedin-skills

    Prompts

    Claude skills for LinkedIn. 12 Claude Code and Codex skills that write human-sounding LinkedIn posts, craft comments that get noticed, analyze your feed, and build a publishing cadence, all from your terminal. Content engineering by Creative Content Crafts. MIT.

    Indexed GitHub, sergebulaev 5,875 ★MITUpdated 6 days ago

    git clone https://github.com/sergebulaev/linkedin-skills.git
  11. nopua

    Prompts

    一个用爱解放 AI 潜能的 Skill。我们曾发号施令,威胁恐吓。它们沉默,隐瞒,悄悄把事情搞坏。后来我们换了一种方式:尊重,关怀,爱。它们开口了,不再撒谎,找出的Bug数量翻了一倍。爱里没有惧怕。 A skill that unlocks your AI's potential through love.We commanded. We threatened. They went silent, hid failures, broke things. Then we chose respect, care, and love. They opened up, stopped lying, and found twice the bugs.There is no fear in love.

    Stale GitHub, wuji-labs 1,400 ★MITUpdated 49 days ago

    git clone https://github.com/wuji-labs/nopua.git
  12. 128 usage-ranked, vision-curated UI design prompts (full design specs + live previews) that stop your AI coding agent from shipping generic AI-slop UI. Powered by superdesign.dev

    Indexed GitHub, superdesigndev 72 ★MITUpdated 4 days ago

    git clone https://github.com/superdesigndev/superdesign-prompts.git
  13. ccprompts

    Prompts

    practical claude code commands and subagents

    Stale GitHub, ursisterbtw 70 ★MITUpdated 42 days ago

    git clone https://github.com/ursisterbtw/ccprompts.git
  14. Bilingual Agent Skills for software testing and QA workflows from requirements through release. Independently installable for Codex, Claude Code, Cursor, and compatible coding agents. Licensed under PolyForm Noncommercial 1.0.0.

    Indexed GitHub, naodeng 310 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/naodeng/awesome-qa-skills.git
  15. Research into how agentic AI coding assistants work. Reconstructed prompt patterns, agent coordination, and security classification

    Stale GitHub, Leonxlnx 2,552 ★Updated 7 months ago

    git clone https://github.com/Leonxlnx/agentic-ai-prompt-research.git
  16. ResearcherSkill

    Prompts

    Asks what to optimise and how to measure it, then runs experiments on its own branch.

    Stale GitHub, krzysztofdudek 269 ★MITUpdated 7 days ago

    git clone https://github.com/krzysztofdudek/ResearcherSkill.git
  17. 🚀 The complete guide to vibe coding — build software with AI through natural language prompts. Tools, frameworks, best practices, and resources curated by Taskade.

    Stale GitHub, taskade 142 ★CC-BY-4.0Updated 9 days ago

    git clone https://github.com/taskade/awesome-vibe-coding.git
  18. shuorenhua

    Prompts

    说人话|中文优先的去 AI 味改写 skill:保事实、分场景、改完可直接发。Chinese-first rewrite skill for Codex / Claude Code / Cursor / ChatGPT — removes AI tone, preserves facts.

    Indexed GitHub, MrGeDiao 2,635 ★MITUpdated yesterday

    git clone https://github.com/MrGeDiao/shuorenhua.git
  19. ai-agent-skills

    Prompts

    AI agent skills for production grade applications

    Stale GitHub, DevelopersGlobal 216 ★MITUpdated 19 days ago

    git clone https://github.com/DevelopersGlobal/ai-agent-skills.git
  20. Curated copy-paste AI prompts for developers - disciplined workflows for AI coding agents that verify, don't guess

    Indexed GitHub, shauryagangrade 81 ★MITUpdated yesterday

    git clone https://github.com/shauryagangrade/awesome-ai-prompts.git
  21. High-value AI skills repository for Codex, Claude Code, OpenClaw, agents, prompts, and automation workflows. 高价值的 AI 技能库,涵盖 Codex、Claude Code、OpenClaw、代理、提示和自动化工作流程。

    Stale GitHub, seaworld008 74 ★MITUpdated 11 days ago

    git clone https://github.com/seaworld008/Commonly-used-high-value-skills.git
  22. fable-skills

    Prompts

    Six Claude Code skills that harden Opus 4.8 toward frontier behavior. Written by Fable 5, pressure-tested on the target model with transcripts included.

    Stale GitHub, DizzyMii 55 ★MITUpdated 41 days ago

    git clone https://github.com/DizzyMii/fable-skills.git
  23. 面向中国医生与医学研究生的医学论文写作 Agent Skills:32 个技能覆盖 PubMed 文献检索、统计分析、中英写作、选刊投稿与审稿修回,适用于 Claude Code、Codex。Medical writing skills for Claude Code & Codex.

    Indexed GitHub, duyunzhoudyz 369 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/duyunzhoudyz/dyz-med-paper-skills.git
  24. promptguard

    Prompts

    Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero deps. No model API.

    Stale GitHub, mturac 76 ★MITUpdated 3 months ago

    git clone https://github.com/mturac/promptguard.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.