Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
awesome-llm-observability
Skills50+ curated LLM observability tools PLUS 26 Agent Skills (several with runnable, unit-tested scripts) to build, evaluate, debug, secure & monitor reliable LLM apps. Tracing, evals, guardrails, LLMOps.
git clone https://github.com/ContextJet-ai/awesome-llm-observability.git -
agent-vision-toolkit
Skills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
git clone https://github.com/Anionex/agent-vision-toolkit.git -
spellbook
SkillsCross-runtime skills for Claude Code, Codex, and multi-agent workflows.
git clone https://github.com/majiayu000/spellbook.git -
platform-skills
SkillsA platform engineering handbook covering Kubernetes, OpenShift, Argo CD, Flux CD, AWS, Azure, Terraform, and GitHub Actions — with an optional Claude plugin layer for interactive guidance.
git clone https://github.com/nitinjain999/platform-skills.git -
claude-booping
SkillsA playbook framework for Claude Code and the sprint loop built on it — deterministic state machinery, model-driven steps, plain-markdown vault
git clone https://github.com/A/claude-booping.git -
reanimate
SkillsA Claude Code skill that reverse-engineers any animation frame by frame, then proves the copy moves the same.
git clone https://github.com/NiazMorshed2007/reanimate.git -
context-docs
SkillsAgent skills for Codex and Claude Code that preserve project context, decisions and next steps across AI sessions in plain Markdown.
git clone https://github.com/jaredchu/context-docs.git -
han
SkillsHan: AI skills and agents for "Solo" product engineers and small teams
git clone https://github.com/testdouble/han.git -
tiktok-skills
SkillsTikTok marketing skills for Claude Code and Codex: 3-second video hooks, captions, trend mapping, and a weekly plan. Draft, humanize, and publish via Publora. MIT. Content engineering by Creative Content Crafts.
git clone https://github.com/sergebulaev/tiktok-skills.git -
Deterministic Python Model Context Protocol (MCP) server & autonomous agent skill for Openclaw Latent Action Engine.
git clone https://github.com/Alpha-Park/openclaw-genpark-latent-action-engine.git -
claude-seo-skills
Skills60 free Claude Skills for SEO and AI search. Built by Hawk Academy + StudioHawk. Drop into Claude Desktop and run.
git clone https://github.com/lhitches/claude-seo-skills.git -
bundles-forge
SkillsAn agentic skills framework & bundle-plugin engineering toolkit that works.
git clone https://github.com/OdradekAI/bundles-forge.git -
js-reverse-ops
SkillsProduction-grade JavaScript reverse-engineering skill: evidence-driven workflows, verbatim sandbox harnesses, 19 battle-tested playbooks, 136 scripts, public benchmarks
git clone https://github.com/DQmyth/js-reverse-ops.git -
llm-wiki-newsroom
SkillsHarness 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.
git clone https://github.com/alfadur7/llm-wiki-newsroom.git -
dcc-mcp-unreal
SkillsUnreal Engine MCP adapter for AI agents to author actors, assets, Blueprints and cinematics, run editor automation, and package projects through the DCC-MCP gateway.
git clone https://github.com/dcc-mcp/dcc-mcp-unreal.git -
rei-skills
SkillsThe engineering-grade skill layer for AI agents. 895 validated skills, 21 AI adapters, workflows & REI Reverse Engineering (REA) for Claude, Codex, Cursor & Copilot.
git clone https://github.com/rootcastleco/rei-skills.git -
taste-engine
SkillsA portable, open-source Agent Skill for building distinctive, accessible frontends with user-selected visual styles, anti-slop quality gates, SEO guidance, and purposeful motion.
git clone https://github.com/kennedys0/taste-engine.git -
engineering-docs
Skills22 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
git clone https://github.com/fattain-naime/engineering-docs.git -
RivalSearchMCP
SkillsDeterministic research MCP server on FastMCP 3 — 5-engine web search, 9-platform social search, 6 academic DBs, news aggregation, entity profiles, conflict detection, document analysis. No API keys. No in-server LLM. Structured outputs for agent chaining.
git clone https://github.com/damionrashford/RivalSearchMCP.git -
kai-cmo-harness
SkillsOpen-source marketing harness for Claude Code and Codex: skills for SEO, content, email, ads, launches, CRO and AI-search visibility. Run as a service by Talk To Gina.
git clone https://github.com/cgallic/kai-cmo-harness.git -
reverse-skill-evolver
SkillsReverse-engineering skills for AI coding agents, with IDA/MCP integration, APK and JavaScript workflows, bounded agent swarms, and routing evaluation.
git clone https://github.com/2233admin/reverse-skill-evolver.git -
pm-claude-skills
Skills1,310 professional Agent Skills for Claude, Claude Duet, ChatGPT, Gemini, Cursor & Codex: PRDs, postmortems, leases, medical bills, payroll checks, morning briefs. 21 skills built for always-on agents like Claude Duet. Plain markdown, MIT, in Anthropic's plugin directory. Free in-browser or npx pm-claude-skills add.
git clone https://github.com/mohitagw15856/pm-claude-skills.git -
Prompt-sensei
SkillsLocal-first prompt coach for Claude Code and Codex that improves prompts, observes prompting habits, and analyzes local history with explicit consent.
git clone https://github.com/chengzhongwei/Prompt-sensei.git -
nerviz
SkillsNerviz — an agent harness for Spring Boot. Claude Code skills, agents and hooks that generate Spring Boot projects and keep AI-written code on-architecture: DDD, dependency direction and naming enforced from domain to tests.
git clone https://github.com/nerviz-ai/nerviz.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.