InnerVault

Library

86,802 resources from 11 public sources. 49 checked by hand; the rest are unreviewed.

Results

2,026 results Clear search and filters

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

  1. Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.

    Stale GitHub, wanshuiyin 180 ★MITUpdated 12 days ago

    git clone https://github.com/wanshuiyin/Anti-Autoresearch.git
  2. agent-skills

    Skills

    Reusable agent skills for battle-tested engineering judgment. Works with Claude Code, Cursor, and 10+ AI tools...

    Stale GitHub, sayeed1999 6 ★MITUpdated 8 days ago

    git clone https://github.com/sayeed1999/agent-skills.git
  3. Open Claude Code skills for data product managers: discover user needs, define quality, govern healthcare data, and carry evidence into decisions.

    Stale GitHub, hollandkevint 5 ★MITUpdated 15 days ago

    git clone https://github.com/hollandkevint/data-product-operator.git
  4. Turn GPT-generated GIFs into short films. A Codex and Claude Code skill for reviewing cuts, reshooting scenes, and exporting MP4. Includes a no-key demo.

    Indexed GitHub, antropos17 5 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/antropos17/chatgpt-gif-cinema.git
  5. Harness engineering applied to knowledge production: a self-evolving multi-agent newsroom that turns your documents into a cross-linked markdown wiki. A "reground" loop pulls published pages back in before they go stale — writer ≠ reviewer, local-first, a structured alternative to RAG.

    Indexed GitHub, alfadur7 175 ★MITUpdated 3 days ago

    git clone https://github.com/alfadur7/llm-wiki-newsroom.git
  6. 29 drop-in Claude Code skills: cost-tier model routing, debugging (rubber-duck, test-first-bugfix, trust-but-verify), and 24 laws-of-software reference skills. Install with: npx skills add The-Artificer-of-Ciphers-LLC/skills-from-the-artificer --all

    Stale GitHub, The-Artificer-of-Ciphers-LLC 6 ★MITUpdated 7 days ago

    git clone https://github.com/The-Artificer-of-Ciphers-LLC/skills-from-the-artificer.git
  7. Agent Skill for Chinese fortune-telling grounded in classical texts: BaZi, personal date selection, luck cycles and years, Zi Wei, Liu Yao, almanac. Plain-language answers with sources. Works with Claude Code, Codex, Cursor, Gemini CLI · MIT

    Stale GitHub, ShousenZHANG 20 ★MITUpdated 10 days ago

    git clone https://github.com/ShousenZHANG/chinese-fortune.git
  8. as-skill

    Skills

    Multi-domain collection of rules, skills, and agents for Claude Code: dev-loop harness, Git workflow, DevOps/Kubernetes, content, and Obsidian PKB. Installable into any project via the CLI.

    Indexed GitHub, alexeyshishin 6 ★MITUpdated yesterday

    git clone https://github.com/alexeyshishin/as-skill.git
  9. skills

    Skills

    AI agent skill for the Zinc API. Search, buy, track, and return across Amazon, Walmart, Target, and 50+ US retailers. Buy anything with a URL.

    Stale GitHub, zincio 7 ★MITUpdated 22 days ago

    git clone https://github.com/zincio/skills.git
  10. meoo-cli

    Skills

    meoo cli 是秒悟(Meoo)官方推出的命令行工具,让 Claude Code、Codex、Cursor、Qoder等本地 agent 在帮你写完前端代码后,能直接接管「数据库、用户登录、文件存储、部署上线」的所有云端工作——你只需要在终端跑一条命令,剩下的交给 AI。

    Stale GitHub, ali-meoo 27 ★Updated 30 days ago

    git clone https://github.com/ali-meoo/meoo-cli.git
  11. Agent skill: your AI coding logs as a gamified character sheet — Claude Code, Codex, OpenCode, Gemini, Copilot. 74 achievements, fixed-scale metrics, LLM-written chronicle, research-backed advice. 100% local, RU/EN.

    Indexed GitHub, timoncool 26 ★MITUpdated 3 days ago

    git clone https://github.com/timoncool/prompt-warrior.git
  12. superpowers

    Skills

    Jesse Vincent's Superpowers skills (brainstorm, plan, TDD, debug, verify, review) adapted for GitHub Copilot agent mode, with project-scoped installers. MIT, adapted from obra/superpowers.

    Stale GitHub, autovant 9 ★MITUpdated 33 days ago

    git clone https://github.com/autovant/superpowers.git
  13. 倪海厦讲义做成的 Agent Skill。伤寒论 129 条、金匮 23 篇、内经 53 篇、本草 345 种、医案 321 例,分层索引按需加载,触发仅 2.3k token,内置安全契约。

    Indexed GitHub, Tespera 9 ★MulanPSL-2.0Updated yesterday

    git clone https://github.com/Tespera/nihaisha-skill.git
  14. Claude Code skill that delegates summarisation, log triage, and bulk-text tasks to local models. Saves API tokens, keeps content on-device, hardware-aware model auditing.

    Stale GitHub, IsmaelMartinez 9 ★MITUpdated 11 days ago

    git clone https://github.com/IsmaelMartinez/delegate-local.git
  15. reel-studio

    Skills

    Agency-quality marketing reels, ads and posts made by Claude Code. Free and open source, no per-video fees. HTML on one clock → MP4.

    Stale GitHub, murathany7 5 ★MITUpdated 6 days ago

    git clone https://github.com/murathany7/reel-studio.git
  16. Telegram bot development skill for Claude Code, Codex, OpenCode and Cursor: build, review and debug Telegram bots and Mini Apps against the live Bot API, checking the official docs and your installed library (aiogram, grammY, python-telegram-bot, Telegraf) before any call.

    Stale GitHub, nyxandro 13 ★MITUpdated 13 days ago

    git clone https://github.com/nyxandro/telegram-bot-development-skill.git
  17. Skill para Claude Code que naturaliza texto en español generado por IA: 11 técnicas lingüísticas y detección de marcas técnicas/tipográficas (watermarking, caracteres invisibles), orientadas a calidad editorial, no a evasión de detectores.

    Indexed GitHub, dorelysm 6 ★MITUpdated 2 days ago

    git clone https://github.com/dorelysm/naturalizacion-texto-es.git
  18. Say the tone, the knobs turn themselves: an MCP server + agent skill that sets BOSS KATANA Gen 3 tones from Claude Code, Codex CLI or Gemini CLI, live in BOSS TONE STUDIO

    Stale GitHub, dogakocak 7 ★MITUpdated 25 days ago

    git clone https://github.com/dogakocak/boss-katana-mcp.git
  19. vetted

    Skills

    Agent skills that prove they work, plus a zero-dependency scanner that vets any skill before you install it.

    Stale GitHub, Xnadir 5 ★MITUpdated 19 days ago

    git clone https://github.com/Xnadir/vetted.git
  20. gtm-skill

    Skills

    77+ free, open-source GTM skills for Claude Code, Claude.ai, Codex, Cursor and every AI agent: ICP research, prospecting, buying signals, cold email, LinkedIn outreach, deliverability, reply handling, deals, RevOps, SEO and AEO.

    Stale GitHub, prosyo-ai 12 ★MITUpdated 23 days ago

    git clone https://github.com/prosyo-ai/gtm-skill.git
  21. Data video / animated infographic skills for Claude Code — turn a CSV into a chart that moves, with exact, accurate numbers on every frame.

    Stale GitHub, iart-ai 18 ★MITUpdated 7 days ago

    git clone https://github.com/iart-ai/data-animation-skills.git
  22. rote

    Skills

    Compile AI agent skills into cheap, fast, deterministic pipelines that run without an LLM in the loop

    Indexed GitHub, trevhud 8 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/trevhud/rote.git
  23. 22 composable, auto-triggering skills engineering documentation skills covering the complete software lifecycle: spec, feasibility, architecture, design, API, database, ADR, security, deployment, operations, and incident review

    Stale GitHub, fattain-naime 6 ★MITUpdated 23 days ago

    git clone https://github.com/fattain-naime/engineering-docs.git
  24. the-librarian

    Skills

    Skill librarian MCP server — every installed skill costs tokens; the librarian keeps your whole collection out of agent context. Agents ask, get the few right skills for the task, and their outcomes curate the collection. Fully local: Ollama + SQLite + optional Apple Intelligence.

    Stale GitHub, aka-kika 42 ★MITUpdated 33 days ago

    git clone https://github.com/aka-kika/the-librarian.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.