InnerVault

Library

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

Results

  1. Claude Code and Codex CLI skill: an LLM router that delegates bulk, already-decided coding tasks to another model you already pay for (GPT via Codex, Gemini via agy, a Claude Opus subagent), on another subscription first. Benchmark-checked routes, cost per task measured on a bench, cross-model review. The host verifies every diff.

    Stale GitHub, pvjbuilds 33 ★MITUpdated 16 days ago

    git clone https://github.com/pvjbuilds/delegate-router.git
  2. The working rules (skills) the cross-model Neo.mjs agent team loads every session: ticket intake, PR review gates, lane coordination and guards, versioned as one package. For apps built on Neo.mjs, for contributors, and for anyone who wants to read them.

    Indexed GitHub, neomjs 11 ★MITUpdated 2 days ago

    git clone https://github.com/neomjs/neo-agent-skills.git
  3. 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 22 days ago

    git clone https://github.com/prosyo-ai/gtm-skill.git
  4. lsdsk

    Skills

    Groups disks by the controller they hang off, grades every link against what both ends could do, reads SMART wear and error counters, and reports what is worth acting on. Linux and Windows, no subprocesses, no network.

    Indexed GitHub, bitranox 6 ★MITUpdated 5 days ago

    git clone https://github.com/bitranox/lsdsk.git
  5. the-agency

    Skills

    Claude Code, fixed for everyone. Memory that survives sessions, agents that finish what they start, QA gates before 'done', the right model for each job. 235+ skills. Installs to ~/.claude/ — no cloud, no extra keys.

    Indexed GitHub, Tekkiiiii 7 ★MITUpdated 4 days ago

    git clone https://github.com/Tekkiiiii/the-agency.git
  6. lore-plugin

    Skills

    Stop explaining your project to the AI every morning. With your approval, Lore turns lessons into project criteria the AI can use next time. Provider-neutral and local-first.

    Stale GitHub, andresanemic 7 ★Apache-2.0Updated 7 days ago

    git clone https://github.com/andresanemic/lore-plugin.git
  7. agent-flow

    Skills

    Guardrails for AI coding agents: run Claude Code, Codex, Gemini CLI, Cursor or Copilot unattended and come back to a reviewed pull request. Implement, review and QA agents, a guard on protected paths, and a tamper-evident audit log.

    Stale GitHub, Drix10 12 ★MITUpdated 6 days ago

    git clone https://github.com/Drix10/agent-flow.git
  8. A visual dry-lab notebook for reproducible analysis. Build pipelines in a canvas or with your AI agent (skills for Claude Code and Codex); every result is recorded and exports as one file anyone can rerun.

    Stale GitHub, ddpoe 6 ★BSD-3-ClauseUpdated 6 days ago

    git clone https://github.com/ddpoe/workflow-canvas.git
  9. Reverseport

    Skills

    Reverse engineer anything. Port it anywhere. MCP server, CLI and Claude Code plugin for AI coding agents: read Godot .pck, Unity IL2CPP, .NET and native builds (via your own Ghidra, IDA or Hopper), compare builds, keep proof for every claim, and port games between Godot, Unity, Unreal and three.js with parity checks. Local, MIT.

    Indexed GitHub, laaielichter 22 ★MITUpdated 3 days ago

    git clone https://github.com/laaielichter/Reverseport.git
  10. icode-skill

    Skills

    AI coding workflow for Claude Code, Codex and CodeBuddy: ticket-based development, resumable steps, evidence-based verification and independent multi-model review. AI 编码工作流:工单管理、断点续接、证据化验证、跨模型设计与代码复评。

    Indexed GitHub, ayukyo 6 ★MITUpdated yesterday

    git clone https://github.com/ayukyo/icode-skill.git
  11. Turn YouTube videos, podcasts, meetings, papers, books, docs sites (llms.txt) and notes into agent skills for Claude Code, Codex, Cursor & Gemini CLI. Exact-second links, built-in evals, local Whisper, no API keys.

    Stale GitHub, michalstrnadel 8 ★MITUpdated 22 days ago

    git clone https://github.com/michalstrnadel/source-to-skill.git
  12. PeerHarness

    Skills

    Your team votes on how its AI coding agents behave. Correct Claude Code once, and PeerHarness turns it into a one-sentence rule (an Agent Skill) that a majority of your team votes in for every member's agent. Peer-to-peer, no server.

    Stale GitHub, aryehlev 10 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/aryehlev/PeerHarness.git
  13. Adaptive running and strength coaching for the long run — a hosted MCP server and Agent Skill that keeps one current 28-day plan in step with your Intervals.icu evidence. Independent project, not affiliated with Garmin or Intervals.icu.

    Stale GitHub, atomchung 5 ★MITUpdated 11 days ago

    git clone https://github.com/atomchung/long-run-hybrid-coach.git
  14. 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.

    Stale GitHub, kulykivska 6 ★MITUpdated 4 days ago

    git clone https://github.com/kulykivska/claude-plugins.git
  15. Connect Claude (or any MCP client) to your own Telegram in ~15 minutes: setup prompt for Claude Code/Codex, production patches (shared daemon, extra tools, multi-account), watchdog, and every gotcha that cost us hours. On top of chigwell/telegram-mcp.

    Indexed GitHub, tonydzi 6 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/tonydzi/telegram-mcp-kit.git
  16. Best-in-class, agent-ready product-lifecycle document templates. Every type ships as a researched, cited, gate-enforced bundle (blank shape, companion, guide, worked example, machine metadata), not just a blank file.

    Stale GitHub, product-on-purpose 5 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/product-on-purpose/product-lifecycle-templates.git
  17. 繁體中文(台灣)去 AI 味 skill:62 種 AI 寫作特徵、157 組兩岸用語在地化、事實保留檢查(--source)、33 案例 eval 對照實測(0.97 vs 0.78)。Traditional Chinese (Taiwan) humanizer for Claude Code / Codex / Cursor, with a measurable no-fabrication check.

    Indexed GitHub, acchuang 7 ★MITUpdated 4 days ago

    git clone https://github.com/acchuang/zh-tw-humanizer.git
  18. KhaosMCP is a local-first, agent-operated pentest platform using AI via MCP. It connects the external operator to the complete assessment cycle: scoping, supervised execution, integrations, evidence gathering, review of findings, and reporting.

    Indexed GitHub, henriqqw 5 ★Updated yesterday

    git clone https://github.com/henriqqw/KhaosMCP-Pentester-Agent.git
  19. An AI agent system on Claude Code that runs your whole job search: finds and scores roles, creates and tailors your resume for every role, finds who to message on LinkedIn, and reminds you to follow up.

    Stale GitHub, aranculleton 7 ★MITUpdated 5 days ago

    git clone https://github.com/aranculleton/last-job-search.git
  20. mega-shot

    Skills

    🎬 Type an idea, get a finished video. Claude researches the topic, writes and fact-checks the script, narrates with a cloned voice, builds real-footage, 3D or cartoon visuals, adds karaoke subtitles and music, makes the thumbnail and checks every cut. Free & open source.

    Stale GitHub, stevenguyenbt 9 ★MITUpdated 19 days ago

    git clone https://github.com/stevenguyenbt/mega-shot.git
  21. boss-skill

    Skills

    Plugin for Claude Code: sends each coding task to the cheapest model that can do it right, keeps your main chat lean, reviews every diff. Debates, plus Codex, Gemini, Kimi, Qwen or Ollama as second opinions.

    Stale GitHub, mefayed 5 ★MITUpdated 11 days ago

    git clone https://github.com/mefayed/boss-skill.git
  22. humanizar-es

    Skills

    Local AI text humanizer for Spanish & English, built on controlled experiments: a base model without chat training rewrites, a fidelity guard keeps every concept and quote, the rhythm is rebuilt, and flagged paragraphs are re-sampled and selected. 0% in Grammarly, ZeroGPT and GPTZero. No API · Humanizador IA local.

    Stale GitHub, ervin-mo 10 ★Custom licence (see repository)Updated 5 days ago

    git clone https://github.com/ervin-mo/humanizar-es.git
  23. fanout

    Skills

    Fewer broken merges from parallel Claude Code and Codex sessions: tests every branch merged together before main, and tells each session when another changes code it uses. Works with worktrees. No dependencies.

    Stale GitHub, Breadstick-Crumbs 5 ★MITUpdated 9 days ago

    git clone https://github.com/Breadstick-Crumbs/fanout.git
  24. testcase

    Skills

    Agent skills that take a requirement to shipped code: audit the spec, turn it into real tests, then build until every check passes. For Claude Code, ZCode, Cursor and Antigravity.

    Stale GitHub, xtieume 5 ★MITUpdated 5 days ago

    git clone https://github.com/xtieume/testcase.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.