InnerVault

Library

85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. 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 2 days ago

    git clone https://github.com/naodeng/awesome-qa-skills.git
  2. miyagi

    Prompts

    Sample to envision intelligent apps with Microsoft's Copilot stack for AI-infused product experiences.

    Stale GitHub, Azure-Samples 751 ★Custom licence (see repository)Updated 20 months ago

    git clone https://github.com/Azure-Samples/miyagi.git
  3. --- name: prompt-engineering-expert description: This skill equips Claude with deep expertise in prompt engineering, custom instructions design, and prompt optimization. It provides comprehensive guidance on crafting…

    Indexed prompts.chat (CC0 prompt collection), TomsTools11 CC0-1.0

  4. archetype

    Prompts

    A curated library of reusable LLM prompts for domain experts, personas, creative practice, structured workflows, and archetype generation.

    Indexed GitHub, 1arry1iu 59 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/1arry1iu/archetype.git
  5. mantis

    Prompts

    A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.

    Indexed GitHub, google 2,787 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/google/mantis.git
  6. AI agent skills for social media content strategy, creation, and analysis across text-first platforms

    Stale GitHub, blacktwist 636 ★MITUpdated 12 days ago

    git clone https://github.com/blacktwist/social-media-skills.git
  7. Prompt patterns for legible in-image text with GPT Image 2.6.

    Stale GitHub, fujc683 102 ★Custom licence (see repository)Updated 12 days ago

    git clone https://github.com/fujc683/gpt-image-2-6-text-rendering.git
  8. claude-banana

    Prompts

    AI agent that turns your rough ideas into perfect image generation prompts. 7-component formula, 70+ creative techniques, 9 domain modes.

    Stale GitHub, Hainrixz 107 ★MITUpdated 23 days ago

    git clone https://github.com/Hainrixz/claude-banana.git
  9. Growth Marketing OS | Mahmoud Omar — open-source AI marketing prompts, Claude skills, agents & growth playbooks (EN + AR)

    Stale GitHub, growthack88 119 ★MITUpdated 38 days ago

    git clone https://github.com/growthack88/growth-marketing-os.git
  10. zero-to-ai

    Prompts

    Free AI/ML course with 950+ Jupyter notebooks — Python, deep learning, LLMs, RAG, agents, prompt engineering, fine-tuning, MLOps

    Stale GitHub, PavanMudigonda 159 ★MITUpdated 16 days ago

    git clone https://github.com/PavanMudigonda/zero-to-ai.git
  11. MCP server for reusable prompt templates, multi-step workflow chains, and quality gates. Compose agentic workflows with an operator syntax; export as native skills to Claude Code, Cursor, OpenCode, and Gemini CLI.

    Indexed GitHub, minipuft 192 ★MITUpdated yesterday

    git clone https://github.com/minipuft/claude-prompts-mcp.git
  12. Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.

    Stale GitHub, pguso 1,047 ★MITUpdated 3 months ago

    git clone https://github.com/pguso/agents-from-scratch.git
  13. evalstats

    Prompts

    Statistical inference for AI evaluations, from model comparisons to corrections for LLM judge bias, optimized for small sample sizes. All defaults battle-tested in Monte Carlo simulations.

    Indexed GitHub, ianarawjo 134 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/ianarawjo/evalstats.git
  14. dsh-purge

    Prompts

    基于上游 1.1.71 维护的 dsh-purge 社区兼容包:只负责 DeepSeek Harness 的版本与本地 Windows 运行问题兼容。

    Stale GitHub, 555bbbAAA 68 ★MITUpdated 7 days ago

    git clone https://github.com/555bbbAAA/dsh-purge.git
  15. The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and production-ready templates. 430K+ lines.

    Indexed GitHub, FlorianBruniaux 6,450 ★CC-BY-SA-4.0Updated 3 days ago

    git clone https://github.com/FlorianBruniaux/claude-code-ultimate-guide.git
  16. Defend sound research against LLM reviewer bias through meaning-preserving rewrites.

    Stale GitHub, Michael-Jiahao-Zhang 210 ★MITUpdated 34 days ago

    git clone https://github.com/Michael-Jiahao-Zhang/game-the-llm-reviewer.git
  17. Vibe知识大赏风格 AI 知识视频 Skill — 纯代码生成电影感知识短视频(无配音·双语字幕·合成BGM·历史文献再现),风格规范逆向自 8 条抖音爆款原片(1091 帧逐秒分析)

    Stale GitHub, xiazhuo123456789 159 ★Custom licence (see repository)Updated 17 days ago

    git clone https://github.com/xiazhuo123456789/vibe-knowledge-video.git
  18. Evidence-backed use cases, prompts, integrations, evaluations, and safety notes for OpenAI GPT-6 Astra.

    Stale GitHub, Anil-matcha 1,147 ★MITUpdated 45 days ago

    git clone https://github.com/Anil-matcha/awesome-gpt-6-astra.git
  19. Claude Code Skill that turns any idea into a cinematic, model-ready video prompt — Sora · Kling · Veo · Seedance. 21 genre templates, 5-stage structure, eval-tested. Distilled from the AI short Hollywood director PJ Ace called "one of the best short films I've seen in years."

    Stale GitHub, jnMetaCode 530 ★MITUpdated 8 days ago

    git clone https://github.com/jnMetaCode/ai-shortfilm-prompts.git
  20. A curated catalog of 230+ semantic anchors: well-defined terms like arc42, TDD London School or tracer bullet that activate deep, consistent knowledge in LLMs. Use them in prompts, skills and agent instructions instead of spelling out methods yourself.

    Indexed GitHub, LLM-Coding 541 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/LLM-Coding/Semantic-Anchors.git
  21. 把你的网易云歌单与听歌排行变成一份深度自我画像 —— 支持 Windows / macOS 的本地数据采集与 AI 画像分析 Skill

    Stale GitHub, dragonknightk 135 ★MIT-0Updated 10 days ago

    git clone https://github.com/dragonknightk/ncm-listening-profile.git
  22. World Simulator v6 · Singulari-Tea Codex. GPT-based ChatGPT project package for dialogue-led narrative simulation, causal choices, GenUI, and cumulative saves. GPTs v6; GEM v5. Apache-2.0.

    Stale GitHub, lemos999 52 ★Apache-2.0Updated 30 days ago

    git clone https://github.com/lemos999/Singulari-Tea-Codex-Prompt.git
  23. unlazy

    Prompts

    Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.

    Stale GitHub, Leonxlnx 3,935 ★MITUpdated 2 months ago

    git clone https://github.com/Leonxlnx/unlazy.git
  24. trekker

    Prompts

    Simple opinionated issue tracker for AI Agents

    Stale GitHub, obsfx 84 ★MITUpdated 18 days ago

    git clone https://github.com/obsfx/trekker.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.