InnerVault

Library

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

Results

  1. open-bridge

    Skills

    Stop re-explaining your work to your coding agent. Plain markdown and YAML in git, read at session start by Claude Code, Codex and Copilot CLI. MIT.

    Stale GitHub, bks-lab 13 ★MITUpdated 17 days ago

    git clone https://github.com/bks-lab/open-bridge.git
  2. Claude skill: Yandex Direct campaign from brief to cabinet draft — semantics, negatives, ads, Metrika goals. Docs in Russian.

    Stale GitHub, ai-hub-open 12 ★Apache-2.0Updated 19 days ago

    git clone https://github.com/ai-hub-open/yandex-direct-manager.git
  3. Türk hukuku için açık kaynak Claude Code eklenti pazarı: 81 eklenti, 1000+ beceri. Metodoloji, atıf hijyeni, sözleşme, dava ve mütalaa. Hukuki danışmanlık değildir.

    Indexed GitHub, aydincan 23 ★Apache-2.0Updated yesterday

    git clone https://github.com/aydincan/turk-hukuku-ve-claude.git
  4. ai-kit

    Skills

    AI-KIT is a practical starter kit for development: ChatGPT/Codex, Claude, DeepSeek, KIMI, and other coding agents. It provides reusable project context, rules for each stack, adaptive model routing, conservative installation and updates, testing and review workflows, security guidance, Docker and Kubernetes readiness, and clean project templates.

    Indexed GitHub, tigusigalpa 25 ★MITUpdated 3 days ago

    git clone https://github.com/tigusigalpa/ai-kit.git
  5. If you want to know more about me, check this out

    Stale GitHub, figueroaignacio 7 ★MITUpdated 10 days ago

    git clone https://github.com/figueroaignacio/ignaciofigueroa.dev.git
  6. trinity-claw

    Skills

    A self-hosted AI agent that thinks, acts, and improves itself – all running privately on your own machine. Browses the web, writes and executes code, manages files, sends emails, monitors URLs, builds websites, and learns from every interaction.

    Stale GitHub, TrinityClaw 11 ★MITUpdated 30 days ago

    git clone https://github.com/TrinityClaw/trinity-claw.git
  7. openapi

    Skills

    Pachca API platform: MCP server and plugin for AI agents (Claude Code, Codex, VS Code, Cursor) with skills and commands, OpenAPI spec, CLI, SDKs (TypeScript, Python, Go, Kotlin, Swift, C#) and n8n node

    Stale GitHub, pachca 11 ★MITUpdated 6 days ago

    git clone https://github.com/pachca/openapi.git
  8. weights-lab

    Skills

    Agent skill for weight-space programming: edit LLM weights

    Stale GitHub, oumi-ai 5 ★Apache-2.0Updated 9 days ago

    git clone https://github.com/oumi-ai/weights-lab.git
  9. xmaster-cli

    Skills

    X (Twitter) CLI for AI agents: read, post and reply to any thread through your browser session, free. JSON out, draft checks, one Rust binary.

    Stale GitHub, paperfoot 12 ★MITUpdated 22 days ago

    git clone https://github.com/paperfoot/xmaster-cli.git
  10. Agente de Claude Code que espía cuentas públicas con Apify, ve los videos, construye tu matriz de viralidad (10 columnas + patrones) y te escribe y simula guiones. Calendario y rutina semanal. ES/EN. Por @soyenriquerocha · tododeia.

    Stale GitHub, Hainrixz 13 ★MITUpdated 23 days ago

    git clone https://github.com/Hainrixz/matriz-viralidad.git
  11. AI poster maker agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: turn an event brief, a product photo, or brand references into event posters, promo banners, flyers, and social media graphics with clear hierarchy and text-safe space. AI海报设计 · 活动海报 · 宣传banner

    Indexed GitHub, beatra-ai 6 ★MIT-0Updated 3 days ago

    git clone https://github.com/beatra-ai/ai-poster-maker-skill.git
  12. Agent skill for visual, source-grounded paper reading: one standalone HTML atlas of methods, equations, and experiments.

    Stale GitHub, xiaofengShi 11 ★MITUpdated 7 days ago

    git clone https://github.com/xiaofengShi/paper-reading-skill.git
  13. compose-skill

    Skills

    Compose Skill (Compose Kit): agent skills for Jetpack Compose & Compose Multiplatform. Makes Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode write better Compose: MVI, Koin, Navigation 3, Ktor, Room. Tested blind on 5 models in 120 agentic runs.

    Stale GitHub, Meet-Miyani 303 ★MITUpdated 9 days ago

    git clone https://github.com/Meet-Miyani/compose-skill.git
  14. Production-ready prompt library for Claude coding agents. APEI methodology, ~35 specialist prompts, current Claude Code coverage, plus a /find-prompt skill that routes any task to the right prompt.

    Stale GitHub, Rtur2003 53 ★MITUpdated 56 days ago

    git clone https://github.com/Rtur2003/Claude-Code-Promts-Skills.git
  15. Agent skill for STM32 embedded development: SPL & HAL (CubeMX) x bare-metal & FreeRTOS, static discipline checker, 85 field-tested pitfalls, 29 domain docs (Keil/IAR/CMake), CAN/Modbus/BMS/FOC/LVGL/RTOS-porting coverage. Works in DSH / Claude Code. STM32 嵌入式开发技能:四轨代码生成+静态检查器+85 条实测坑。

    Indexed GitHub, wdcjx 42 ★MITUpdated 2 days ago

    git clone https://github.com/wdcjx/Embedded-programming.git
  16. stacker

    Skills

    Agent skill: stack overlapping skills — run the best candidates in parallel, score outputs, merge the result

    Stale GitHub, ogarciarevett 6 ★MITUpdated 24 days ago

    git clone https://github.com/ogarciarevett/stacker.git
  17. SKILLS

    Skills

    A collection of original skills independently designed and developed by Anna Tchijova, grounded in scientific methodology and established engineering best practices.

    Stale GitHub, annatchijova 9 ★Custom licence (see repository)Updated 15 days ago

    git clone https://github.com/annatchijova/SKILLS.git
  18. briefback

    Skills

    A coding-agent workflow with Grill at its core: challenge assumptions and settle decisions before coding. Just describe your task and AgentFlow automatically guides the work from research to reviewable code. Lightweight spec-driven development with planning, TDD, review and handoff for Claude Code, Codex and Cursor.

    Stale GitHub, reforma-ai 10 ★MITUpdated 6 days ago

    git clone https://github.com/reforma-ai/briefback.git
  19. dokimi

    Skills

    Dokimi (Greek δοκιμή, "test, proof") measures whether a skill, MCP doc source, agent profile or repository guidance actually helps a coding agent: paired on/off arm comparisons, novel-vs-known content analysis, and repository scans with graded agent runs.

    Indexed GitHub, intel 37 ★Apache-2.0Updated yesterday

    git clone https://github.com/intel/dokimi.git
  20. flow-map-resp

    Skills

    A Claude Code skill that turns your pipeline into an animated metro map, replayed from what a real run recorded. Retries as loop arcs, parallel work as rails, checks as hubs with spokes. React + SVG, your colours, light and dark.

    Stale GitHub, Galehashoid 69 ★Updated 12 days ago

    git clone https://github.com/Galehashoid/flow-map-resp.git
  21. A Claude skill that removes AI writing patterns from Turkish text while keeping meaning, numbers and terminology intact. Also works with ChatGPT, Gemini and other LLMs.

    Stale GitHub, DevVettel 17 ★MITUpdated 6 days ago

    git clone https://github.com/DevVettel/turkish-humanizer.git
  22. 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 2 days ago

    git clone https://github.com/timoncool/prompt-warrior.git
  23. dsh-iris

    Skills

    Media generation and visual understanding for DeepSeek Harness, with multi-provider routing and the integrated Iris workbench.

    Indexed GitHub, mokuyoaxis 11 ★MITUpdated yesterday

    git clone https://github.com/mokuyoaxis/dsh-iris.git
  24. Build evals from traces, code, and coding sessions, then measure and improve AI agent behavior, including your coding agents

    Stale GitHub, relai-ai 14 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/relai-ai/agent-eval-loop.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.