Reusable AI skills and capabilities for agent workflows
videomakingio-gif
Describe your manual process. Get a complete automation blueprint with Automation Score, ROI calculation, and implementation plan. Claude Skill, LLM-agnostic.
...moredtdesigner36
Persistent project assistant for Claude Code. Bootstrap new projects or adopt existing ones via gap analysis. Quiet background hooks maintain wiki, pick the right model per task, and surface past decisions. Built for vibe-coders.
...moremrKanoh
Claude Code skill for WCAG 2.1 accessibility audits, WAI-ARIA patterns, screen reader testing, and CI/CD integration.
benry-products
Claude Code skill: audit your own web app for WCAG 2.2 AA accessibility compliance. Runs axe-core via Playwright, maps violations to WCAG success criteria, proposes remediation diffs, and fills in VPAT 2.5 INT ACRs.
...morezhujian0409
Turn any video link into a polished AI article. Markdown + images, multi-LLM.
tatyanawelschmeyer61979859631
High-performance, privacy-focused desktop client for AI assistants. Features cross-platform support, global hotkeys, custom workspace themes, and enhanced session orchestration.
...moregeekjourneyx
Generate professional README.md with 16:9 infographics, SEO-optimized metadata, and structured author sections — powered by Playwright and AI agent skills
...moreRancho-7
🎬 An AI Agent skill for reviewing and optimizing SRT subtitles with an interactive diff panel.
collindjohnson
Website Speed Optimization Claude Code Skill: Audit a URL with PageSpeed Insights and apply concrete speed fixes to your codebase.
...moretzurp
CLI toolkit for turning OpenAPI specs into agent-ready skills, typed client schemas, request validators, endpoint tests, and exploration tools.
...moreGitHub Actions
COMPASS — Collaborative Orientation, Mapping, Planning, Architecture, Spec & Supervision. An inverted AI coding skill: the human implements, the LLM orients.
...moreraphael.mansuy
EdgeParse PDF parser — WebAssembly build for browsers
hang.yang
The open agent skills ecosystem
GitHub Actions
Elliot's skill stack for Claude Code — install via npx elliot-stack@latest
arjunkai
Capture annotated screenshots of any web UI. Annotations rendered as DOM overlays before Playwright captures. Arrows, highlights, callouts, multi-viewport, and replayable JSON specs so screenshots never go stale.
...moreGitHub Actions
Local Markdown review tool with inline comments for Claude agents
seanmtp
Your AI product operating system — by Mind the Product
plowrance
Transparent proxy that routes Anthropic Messages calls through the Message Batches API for 50% cheaper inference in exchange for minutes-per-turn latency. For long-running unattended agent tasks.
...moreatlaswithiris
Governance guard for Claude Managed Agents. Evaluates every tool call before execution. ACCEPTED flows. RESTRICTED steers. BLOCKED stops.
...morepeterwangze
Intelligent trigger-based router for Claude Code with automatic task type detection and model routing
razroo
Author one model policy; fan out to every harness that supports it. Translates role-based model selection into settings.json, config.toml, opencode.json, and a machine-readable resolved map.
...moredramalf
LangSmith tracing plugin for opencode — traces sessions, LLM calls, tool calls, reasoning, and context compaction. Trace taxonomy compatible with the official langsmith-claude-code-plugins.
...morerupayan10
TypeScript SDK for SAMVAD — Secure Agent Messaging, Verification And Discovery (The Open Sovereign Agent Dialogue Protocol)
...moreGitHub Actions
A TypeScript toolkit for building deterministic, agent-friendly CLIs.