Library
86,235 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
write-human
SkillsStatistical linter that flags the words, phrases and constructions that make text read as LLM output, measured against billions of words people wrote before 2022. Runs offline. CLI on npm plus an Agent Skill for coding agents.
git clone https://github.com/arslanrakh/write-human.git -
rob-janoff-design
SkillsAgent Skill for logo design with Rob Janoff's method from "Taking a Bite out of the Apple": design, critique and refresh logos as three one-ink SVG concepts built from a golden series, measured and rendered at 256, 48 and 16 px before they are shown.
git clone https://github.com/carrapido/rob-janoff-design.git -
m3-memory
MCP serversLocal-first memory backend for AI agents · 99.2% LongMemEval-S retrieval @ k=8 · Supports Claude · Antigravity · LangChain · Hermes · Gemini · OpenCode · OpenClaw · MCP-native and plugins · Hybrid search (FTS5 + vector + MMR) · GDPR · FIPS 140-3 ready · 100% local (fully offline) or cloud capable
git clone https://github.com/skynetcmd/m3-memory.git -
loopover
MCP serversThe loop never sleeps — you finally can. Agents automate the entire development lifecycle (write, review, merge, learn) end to end, with a published safety record. Self-host today; rentable hosted loops in development. Any GitHub repo; Gittensor-native intelligence built in.
git clone https://github.com/JSONbored/loopover.git -
shidi-skill
SkillsAI4S 科研 Agent 技能 | AI-for-Science research workflow skill for coding agents: literature review · experiment design · figures · paper reading — files out, cross-verified, zero deps | 文献调研/实验方案/作图/精读,交付文件+交叉验证,零依赖,MIT
git clone https://github.com/IcyCreamDAS/shidi-skill.git -
shim-mcp
MCP serversWordPress MCP server plugin, live on WordPress.org. Connect Claude Code, Cursor, or any MCP client to WordPress over stdio (WP-CLI) or HTTP. 56 abilities, self-contained, no cloud.
git clone https://github.com/justadityaraj/shim-mcp.git -
Crea shorts animados para TikTok y YouTube con Claude Skills, sin escribir código. Proyecto open source, personalizable y con tutorial paso a paso.
git clone https://github.com/miguelcotrinaia/claude-skills-shorts-animados.git -
CoalFace
SkillsFan-out discipline for AI coding agents - scout, partition, wave, QC, single-writer apply, receipt. Bounds a swarm to the solo-cost budget; does not make models smarter. Zero-dependency, Phoenix-13. Part of TheColliery.
git clone https://github.com/TheColliery/CoalFace.git -
requesting-code-review
SkillsUse when completing tasks, implementing major features, or before merging to verify work meets requirements
-
writing-plans
SkillsUse when you have a spec or requirements for a multi-step task, before touching code
-
ask-matt
SkillsAsk which skill or flow fits your situation. A router over the skills in this repo.
-
claude-handoff
SkillsHand the current conversation off to a fresh background agent that picks up the work immediately.
-
html-to-explainer-video
SkillsAgent Skill:把任意主题做成带配音、词级字幕和 HTML/GSAP 动效画面的讲解视频(MP4)与封面;逐帧确定性渲染,画面按吐字时刻对位。Turn any topic into a narrated explainer video with word-level captions.
git clone https://github.com/amliuyong/html-to-explainer-video.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 -
pptwise
SkillsA real PowerPoint, not HTML. Tell your AI what to cover and pptwise builds an editable deck on your own machine. Agent skill + DSH plugin, no account and no API key to render. | 真正的 PPT,不是 HTML。跟 AI 说要讲什么,pptwise 在你自己电脑上做出一份能改的 PPT。Agent skill + DSH 插件,不用注册,渲染不用 API key。
git clone https://github.com/liustack/pptwise.git -
motion-promo-reels
SkillsClaude skill: promotional videos with motion graphics and audio, 100% generated by code (canvas + ffmpeg). For a person, a product or a whole store catalog. Install: npx skills add david-d2c2/motion-promo-reels
git clone https://github.com/david-d2c2/motion-promo-reels.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 -
paint-video-skill
SkillsAn agent skill for hand-drawn animated shorts and music videos made entirely in code: thirteen styles, each with a finished film and the code that made it. 让 AI agent 用代码画手绘动画短片和 MV,十三套画风,每套都有成片和能跑的代码。
git clone https://github.com/nzl153/paint-video-skill.git -
qrdx
SkillsOpen-source QR code platform: free static codes with no sign-up or watermark, dynamic codes with hosted pages and scan analytics, a REST API, image API, MCP server, CLI and React library. Self-hostable.
git clone https://github.com/qrdxinc/qrdx.git -
command-centre
SkillsUnderstand, measure and manage how AI is transforming your organisation. Works with Claude, ChatGPT and Codex.
git clone https://github.com/frontiercc/command-centre.git -
xmaster-cli
SkillsX (Twitter) CLI for AI agents: read, post and reply to any thread through your browser session, free. JSON out, draft checks, one Rust binary.
git clone https://github.com/paperfoot/xmaster-cli.git -
CONTINUUM
MCP serversCONTINUUM: Verifiable semantic recovery for long-running AI agents. Semantic checkpoints (not conversation dumps), an idempotent action ledger that refuses duplicate side effects, and a hash-chained tamper-evident event log, all exposed as a deny-by-default MCP server. Framework-agnostic, Python 3.11+
git clone https://github.com/Cyrax321/CONTINUUM.git -
CoalWash
SkillsMemory washer/defragmenter for AI agent memory: class-B semantic wash (fidelity-gated, blocks any structured-token drop, snapshot+rollback) and class-A byte-identity session estate (ULTRA archive/restore, RE-TIER) - never semantic-edited. Cleans the FAT, never the MEAT. Slows memory-overhead growth; does not eliminate it. Zero-dependency.
git clone https://github.com/TheColliery/CoalWash.git -
little-canary
SkillsDetects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.
git clone https://github.com/hermes-labs-ai/little-canary.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.