Library
86,235 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
OpenClaw GenPark Sentiment Harvester - High-throughput lexicon-decay sentiment polarity engine with valence shifting and time-weighted stream aggregation.
git clone https://github.com/alphaparkinc/openclaw-genpark-sentiment-harvester.git -
OpenClaw GenPark Memory Vault - Cryptographically partitioned hierarchical memory vault with Ebbinghaus time-decay and HMAC namespace isolation.
git clone https://github.com/alphaparkinc/openclaw-genpark-memory-vault.git -
OpenClaw GenPark Deep Auditor - Multi-hop agent trajectory auditor with cyclic loop detection, diversity scoring, and execution drift prevention.
git clone https://github.com/alphaparkinc/openclaw-genpark-deep-auditor.git -
llm-wiki-pm
SkillsPM knowledge base skill for Claude Code. Karpathy's LLM Wiki pattern with supersession, privacy, crystallize, and qmd hybrid search.
git clone https://github.com/anh-chu/llm-wiki-pm.git -
kyber-weave
SkillsAgentic coding framework and meta-harness for planning, building, reviewing, and tuning software across coding agents. Portable agent squads, skills, governed project knowledge, quality gates, and local token observability. Human judgment. Agent speed.
git clone https://github.com/dpalfery/kyber-weave.git -
testcase
SkillsAgent 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.
git clone https://github.com/xtieume/testcase.git -
procedural-art
SkillsReal mountains, glass and paintings made with code and real elevation data. No image model. Two Claude skills.
git clone https://github.com/dogum/procedural-art.git -
37 folder-drop skills for Microsoft 365 Copilot Cowork. 21 workflow skills plus a 16-persona executive review board. Drop a folder into OneDrive, no admin, no app package. The same SKILL.md files run verbatim in Claude Code.
git clone https://github.com/kesslernity/awesome-copilot-cowork-skills.git -
omowright
SkillsPlaywright, but built for AI agents: the browser API models already know, token-efficient a11y snapshots, and scroll-driven collection over the network. Zero-port CDP underneath.
git clone https://github.com/code-yeongyu/omowright.git -
master-skills
SkillsUnified skill library for Claude, Codex, Cursor, Antigravity & AI agents — 2,660 skills across 15 domains
git clone https://github.com/sinhoneyy/master-skills.git -
stitch-kit
SkillsYour coding agent designs terrible UI. stitch-kit wires it into Google Stitch MCP and teaches it the whole pipeline — ideation, screen generation, design systems, production components.
git clone https://github.com/gabelul/stitch-kit.git -
Blank Agent Skill Template
Prompts--- name: my-skill-name description: A clear description of what this skill does and when to use it --- # My Skill Describe what this skill does and how the agent should use it. ## Instructions - Step 1: ... - Step 2…
-
code-conductor
SkillsA governance layer for Claude Code sessions: hooks that check an agent's commands before they run, a spec-first workflow, and project memory the next session reads.
git clone https://github.com/yeisonrestrepo/code-conductor.git -
motion-film-skill
SkillsTurn a report, a deck or a product into a voice-led motion film, written in code by your AI agent. Skill for Claude Code, Codex and any agent: AI voiceover, beat-synced animation, captions, critic rounds, 60 fps 16:9 + 9:16.
git clone https://github.com/tonyprots/motion-film-skill.git -
suno-lyrics-skill
Skills수노(Suno)용 한국어 작사 Claude 에이전트 스킬 — 가사와 Style·Exclude·Title을 장르에 맞춰 함께 설계 (v3.1, CC BY 4.0) · Korean lyric-writing Agent Skill (SKILL.md) for Suno
git clone https://github.com/previtlab/suno-lyrics-skill.git -
VMware-VKS
SkillsMCP server and CLI for VMware Supervisor and VKS Kubernetes lifecycle, namespace, ClusterClass and kubeconfig workflows.
git clone https://github.com/vmware-skills/VMware-VKS.git -
ai-marketplace
SkillsPortable Kong skills and Konnect MCP configuration for agents — contributor source for packaged Konnect, Gateway, DataKit, and declarative-tool skills distributed via marketplace catalogs and plugin bundles.
git clone https://github.com/Kong/ai-marketplace.git -
parallel-lanes
SkillsClaude Code skill: run an approved implementation plan as parallel lanes of reviewed tasks
git clone https://github.com/noderaven/parallel-lanes.git -
miadi-orchestration-kit
SkillsThe agent-host side of the Miadi Factory: Claude Code plugins, host-neutral skills and apt packages for Chronicle episodes, session capture and restore, and witnessed review.
git clone https://github.com/jgwill/miadi-orchestration-kit.git -
skill-evolution
SkillsImprove Claude Code and OpenAI Codex skills from real feedback, with evidence, regression checks, and human review.
git clone https://github.com/rwang23/skill-evolution.git -
claude-skills-czl
SkillsBattle-tested Claude Code configs — opinionated CLAUDE.md baselines, skills, slash commands and enforcement hooks you drop into any project
git clone https://github.com/Cristhianzl/claude-skills-czl.git -
design-review
SkillsClaude Code skill: scored UX critique with Before/After/Why fixes and Nielsen/WCAG citations
git clone https://github.com/humbleteam/design-review.git -
claude-code-python-setup
SkillsReady-to-use .claude configuration for Python projects: agents, skills, commands, rules, and MCP server templates for Claude Code.
git clone https://github.com/skateddu/claude-code-python-setup.git -
contentforge
SkillsAn open-source editorial production system that researches, verifies, drafts, and delivers publication-ready long-form content with human review and provenance built in.
git clone https://github.com/indranilbanerjee/contentforge.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.