Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
SOTA-skills
SkillsEngineering best practices that AI coding agents actually apply — 40+ skills, from secure coding and cloud to compliance and UX writing. BUILD + AUDIT modes. Measured: best-practice coverage 59% → 98% vs. the same model unguided.
git clone https://github.com/martinholovsky/SOTA-skills.git -
fresh-eyes-review
SkillsMandatory final sanity check before commits/PRs - catches security vulnerabilities, logic errors, and bugs that slip through tests
git clone https://github.com/2389-research/fresh-eyes-review.git -
devops-ai-kit
SkillsRules, skills, subagents and guardrails that make Claude Code safer for DevOps and cloud infrastructure work (Kubernetes, Terraform, Ansible, Helm, Argo CD, Azure/AWS/GCP).
git clone https://github.com/hoangminhung/devops-ai-kit.git -
everything-claude-codex
SkillsClaude Code and Codex working as one team: one shared memory (voice included), each sees the other's latest messages. Plus searchable notes, self health checks, and phone access with the laptop shut.
git clone https://github.com/saksham10arora-dotcom/everything-claude-codex.git -
claude-code-plugins
SkillsClaude Code plugins collection - custom plugins and curated favorites. chat-saver/skill-extractor/codex-bridge/etc...
git clone https://github.com/DropFan/claude-code-plugins.git -
aizee
SkillsThe policy layer for AI coding agents. aiZee governs what Cursor, Claude Code, Copilot, Windsurf, Devin & MCP agents may do — 139 enforcement gates, 29 personas, 245 skills, BMAD runtime, hybrid memory, tamper-evident audit. pip install aizee
git clone https://github.com/m3taz-ahmed/aizee.git -
deadeye-cc
SkillsClaude Code plugin that fits the model, effort, and context to each task — fewer tokens, same quality. Deterministic policy kernel in the hooks; every number it reports is measured, not estimated.
git clone https://github.com/deepaksinghcs14/deadeye-cc.git -
claude-handoff-revive
SkillsResume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages.
git clone https://github.com/sofumel/claude-handoff-revive.git -
claude-bible
SkillsMake Claude Code behave consistently across repos, sessions and humans: rules-as-files governance with precedence, declined-decisions journal, objection sparring. Sanitized from a live production system. Free, MIT.
git clone https://github.com/tonydzi/claude-bible.git -
webdev-agent-kit
SkillsA cross-platform frontend kit for Codex, Claude Code, Cursor, OpenCode, etc. It helps AI coding agents work predictably and safely with existing frontend projects.
git clone https://github.com/ytvee-dev/webdev-agent-kit.git -
WongStack
SkillsRepo-native workflow for AI coding agents: your team's process, plans, and decisions live in the repo, so Claude Code and Codex run the same explore → plan → apply → ship loop.
git clone https://github.com/matthewwong525/WongStack.git -
Claude-Abo
SkillsPortable Claude Code setup template: 66 skills with provenance, cost-aware model routing, git safety hooks. Adapt, don't run as-is.
git clone https://github.com/Bank848/Claude-Abo.git -
LocalSetup
SkillsSet up your AI assistants with reusable skills and clear instructions. Save time on repeated setup and keep work consistent across projects.
git clone https://github.com/CruxExperts/LocalSetup.git -
lullsense
SkillsOpen-source, evidence-informed baby & toddler sleep consultant (Agent Skill) — helps from conversation alone, sharper with recent sleep history; constraint-aware, safety-first, never diagnoses.
git clone https://github.com/Kavender/lullsense.git -
agent-skills
SkillsReusable agent skills for battle-tested engineering judgment. Works with Claude Code, Cursor, and 10+ AI tools...
git clone https://github.com/sayeed1999/agent-skills.git -
Claude-auto-pause
SkillsClaude Code plugin: stops Claude before your usage limit and saves a checked handoff note, so a new chat picks up where it left off.
git clone https://github.com/k45sle/Claude-auto-pause.git -
claude-anatomy
SkillsEl árbol de decisión para saber qué construir en Claude Code: una skill, un subagente, un hook, un servidor MCP, un plugin, una rutina, una página web, una app, o nada. Te devuelve una sola pieza y su esqueleto de archivos. No afiliado a Anthropic.
git clone https://github.com/Hainrixz/claude-anatomy.git -
graph
SkillsTurns any idea into a checked plan your AI must follow: reads you first, finds and safety-checks the best skills, one-tap approval, rules enforced in code, full logs. Claude Code, Codex, Cursor, OpenCode, OpenClaw.
git clone https://github.com/gwaghmar/graph.git -
ElevenPowers
Skills"make", but for correctness claims. Decides when a coding agent's work is actually done, and un-decides it when you edit the code.
git clone https://github.com/SatyamSingh-Git/ElevenPowers.git -
skills
SkillsYou say the job; the playbook runs. 161 agent skills + 63 slash commands for Claude Code, Cursor, Codex, and Gemini CLI. Tuned for React / Next.js / Supabase.
git clone https://github.com/kensaurus/skills.git -
fantastic-ui
SkillsAgent skill for Claude: build instrument-grade UI — landing pages that read like the product, plus app pages, dashboards, panels, and subpanels held to the same discipline. Single-accent color system, serif+mono type, live data as proof, a11y/perf ship gates.
git clone https://github.com/succtorlin/fantastic-ui.git -
skillcheck
SkillsConformance suite for Agent Skills: lint SKILL.md against the spec, run against real agent runtimes, publish a compatibility matrix
git clone https://github.com/Sagargupta16/skillcheck.git -
Low-Poly-Modeling-Skill
SkillsAs it says, a low-poly modeling skill for AI agents, Mostly in PS1/PSX style.
git clone https://github.com/IAmTheParsifal/Low-Poly-Modeling-Skill.git -
boss-katana-mcp
SkillsSay 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
git clone https://github.com/dogakocak/boss-katana-mcp.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.