InnerVault

Library

85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.

Results

71 results with any of your words Clear search and filters
  1. ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

    Indexed GitHub, wanshuiyin 19.3k ★MITUpdated 2 days ago

    git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git
  2. repro-lens

    Skills

    Static reproducibility checks, experiment replay, and verification for ML pipelines.

    Stale GitHub, 00200200 45 ★MITUpdated 31 days ago

    git clone https://github.com/00200200/repro-lens.git
  3. 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 10 days ago

    git clone https://github.com/wanshuiyin/Anti-Autoresearch.git
  4. Nineteen Claude Code plugins I run every day across a Python backend, a React web app, a SwiftUI client and an ML pipeline: SDLC and ML skills, per-stack reviewer subagents, blocking safety hooks, content and SEO agents, LSP and monitors. One marketplace instead of a copy per repo.

    Indexed GitHub, kulykivska 6 ★MITUpdated 3 days ago

    git clone https://github.com/kulykivska/claude-plugins.git
  5. AI-Rig

    Skills

    A collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.

    Indexed GitHub, Borda 31 ★Apache-2.0Updated today

    git clone https://github.com/Borda/AI-Rig.git
  6. researchforge

    Skills

    A lab protocol for coding agents. Freeze baselines, run hypotheses in isolated worktrees, reject failures and validate improvements from Claude Code, Cursor or a direct API key (Gemini/Anthropic/openAI).

    Indexed GitHub, forger-labs-hq 9 ★Apache-2.0Updated yesterday

    git clone https://github.com/forger-labs-hq/researchforge.git
  7. podlite

    Skills

    Implementation of Podlite markup language

    Stale GitHub, podlite 55 ★MITUpdated 29 days ago

    git clone https://github.com/podlite/podlite.git
  8. open-steps

    Skills

    Plain-language agent skills for Claude Code, Codex, Cursor and Gemini CLI: honest session reports, straight verdicts, steps you can follow. MIT.

    Indexed GitHub, kharmanskyi 1,284 ★MITUpdated yesterday

    git clone https://github.com/kharmanskyi/open-steps.git
  9. 76 audit-ready Claude skills automating the industrial robot, cobot, AMR, ROS2, V&V, AI/ML, and IEC 62443 lifecycle. 38 builder + reviewer pairs anchored to ISO 10218, 13849, 62061, 12100, 9283, 15066, 3691-4, and IEC 62443.

    Stale GitHub, jherrodthomas 247 ★MITUpdated 46 days ago

    git clone https://github.com/jherrodthomas/robotics-skills-suite.git
  10. SkillOpt

    Skills

    SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.

    Stale GitHub, microsoft 18.9k ★MITUpdated 12 days ago

    git clone https://github.com/microsoft/SkillOpt.git
  11. iso-24495

    Skills

    ISO 24495 Plain Language skills and plugin

    Indexed GitHub, GaZmagik 210 ★MITUpdated today

    git clone https://github.com/GaZmagik/iso-24495.git
  12. Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

    Indexed GitHub, alibaba 52.4k ★Apache-2.0Updated today

    git clone https://github.com/alibaba/open-code-review.git
  13. An Agent Skill that makes an LLM write in ASD-STE100 Simplified Technical English. Rules, approved word list, and a check tool.

    Stale GitHub, 0xpili 987 ★Custom licence (see repository)Updated 3 months ago

    git clone https://github.com/0xpili/simplified-technical-english.git
  14. xiaoyaosearch

    Skills

    小遥搜索,听懂你的话、看懂你的图,用AI找到本地任何文件。让搜索像聊天一样简单。XiaoyaoSearch: Understands your words, reads your images, finds any local file with AI. Making search as easy as chatting.

    Stale GitHub, dtsola 1,035 ★Custom licence (see repository)Updated 45 days ago

    git clone https://github.com/dtsola/xiaoyaosearch.git
  15. langfuse-docs

    Skills

    🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

    Stale GitHub, langfuse 253 ★MITUpdated 4 days ago

    git clone https://github.com/langfuse/langfuse-docs.git
  16. AI Research Writing Skill (AI论文写作技能) is an agent skill for ML / AI / CV / NLP researchers. Point your coding agent at code, experiment logs, notes, and a venue template; it helps you produce an auditable, evidence-backed LaTeX draft and submission package — not a polished fiction.

    Stale GitHub, jin-s13 52 ★MITUpdated 29 days ago

    git clone https://github.com/jin-s13/ai-research-writing-skill.git
  17. STE80 Humanizer: agent skill that removes AI tells and rewrites text 80% of the way to ASD-STE100 (Simplified Technical English), the method Andrej Karpathy shared.

    Indexed GitHub, Dodaios 627 ★MITUpdated 2 days ago

    git clone https://github.com/Dodaios/ste80-humanizer.git
  18. Veldra — talk an agent into existence, then watch it grow. A self-hostable, local-first agent platform: describe what you need in plain language and it compiles a working agent tools, MCP, RAG, teams. The more you use it, the better it gets agents learn from your feedback and reshape as you talk.

    Stale GitHub, shamspias 406 ★Updated 5 months ago

    git clone https://github.com/shamspias/customizable-gpt-chatbot.git
  19. OpenCreator

    Skills

    Formerly KrillinAI, VideoTranslation and Dubbing Tool for 120+ Languages. Open-source AI workspace for creators, powered by Codex. Video downloader, video translation, create videos, images, audios, and edits with Agents in one place. For your Social Media like YouTube, TikTok, Instagram, etc.

    Indexed GitHub, krillinai 14.4k ★Apache-2.0Updated today

    git clone https://github.com/krillinai/OpenCreator.git
  20. Evidence-first genealogy skill for AI agents (Codex, Claude Code): church books, civil, military, deportation and repression records across the former USSR. Replies in your language.

    Stale GitHub, DenisSergeevitch 2,073 ★MITUpdated 10 days ago

    git clone https://github.com/DenisSergeevitch/ex-ussr-kinship-research.git
  21. [dsh]为纯文本模型设计更强大的视觉工具箱:一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.

    Stale GitHub, Anionex 896 ★MITUpdated 34 days ago

    git clone https://github.com/Anionex/dsh-vision-toolkit.git
  22. humanizer-ru

    Skills

    Правит русский текст после нейросети и сверяет цифры, даты и имена. Навык для Claude Code, Codex, Cursor и Claude.ai

    Stale GitHub, Vladimir-Human 144 ★MITUpdated 6 days ago

    git clone https://github.com/Vladimir-Human/humanizer-ru.git
  23. 为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

    Stale GitHub, Anionex 1,232 ★MITUpdated 34 days ago

    git clone https://github.com/Anionex/agent-vision-toolkit.git
  24. claude-skills

    Skills

    Indexed GitHub, alexgorby 5 ★MITUpdated 2 days ago

    git clone https://github.com/alexgorby/claude-skills.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.