Host-side secret proxy and onboarding flow for sandboxed Claude sessions

A collection of skills for OpenClaw AI agents — context management, intent engineering, and more

WCAG 2.2 AA accessibility skill for Claude Code, covers ARIA, keyboard navigation, screen readers, axe-core, VPAT, and accessible React/shadcn/ui patterns. 100% trigger recall on 20-query eval set.

Template and examples for creating Claude Code skills. Includes comprehensive guides, 5 working examples, and best practices following the Agent Skills standard.

Markdown to web page — upload .md files to S3-compatible storage, rendered instantly via Docsify. A skill for sharing long content as readable links.

Portable SKILL.md agent skills for Claude, Codex, and other AI coding agents — audits, legal, design, and prompt engineering

A curated collection of autonomous AI agent skills powered by Vercel's `skills` npm cli package. Specialized tools for productivity, document management, and custom LLM workflows.

Agent Skills made by Panno

AI工作报告技能 - 对话记录工作，按需生成周报月报，支持多项目管理、智能纠错、可视化建议、Markdown表格存储。极简高效，拒绝废话，让工作报告不再繁琐。AI Work Report Skill - Record work via conversation, generate weekly and monthly reports on demand. Features multi-project management, smart correction, visualization suggestions, and Markdown table storage.

AI agent skill for creating calendar based on syllabus, course schedule, and academic calendars

Agent skills for Angular 21, AI coding assistants: GitHub Copilot, Claude Code, Cursor & more. Zoneless, signals-first.

Create, customize, or modify QoderWork expert plugins. Use when the user wants to create a new plugi

A collection of skills I use regularly

A meta-skill for designing and building internal skill registries

A self-improving skill system for any kind of repeated work, built for claude.ai users. No CLI required.

An LLM skill for Touying slide presentations in Typst

GenPark Distilled Skill: accio-market-intelligence

Agent Skill for Pokemon Champions VGC Regulation M-A research

GAN-inspired adversarial development loop — Planner directs Generator + Evaluator in fresh cmux panes, gated by hard pass/fail per deliverable. Adapted from Anthropic's harness-design guidance for long-running agentic apps.

Stop your AI from writing like an AI. An agent skill for authentic, human-sounding text.

Open-source negotiation skills for shopping and merchant AI agents.

Agent Skills and Python CLI for offline Codex and Claude Code environment backup, restore, and health checks.

Learn and automate human workflows on websites through browser exploration, screenshot analysis, and

Agent skills library for AI coding assistants. Includes coding conventions, npm package preferences, and project bootstrapping tools.

Claude Code skill for mid-session drift checks, repo rot audits, and verification gaps

Stop posting phantom bugs. A five-phase, evidence-backed code review skill for high-stakes PRs — every finding cited, every fix snippet executed, every hypothesis verified or dropped.

Portable Markdown skill for AI vibe coding with legal, HR, and compliance workflows: contracts, policies, HR processes, obligations, internal comms, and regulatory guidance.

Agent plugin for source-preserving academic de-AI and human-anchor-bound rewriting

Agent skills for document generation and conversion using fulgur

One git checkout drops a shared AI coding setup (skills, subagents, MCP servers, OpenSpec scaffolding) into any project, across Claude Code, Kilo, OpenCode, Codex, and Copilot.

Claude Code skills collection (vercel-incident-2026-april 他)

Single SKILL.md that abstracts three NotebookLM access paths (MCP CLI, Chrome browser, Playwright uploader) into one consistent interface.

A skill for LLMs that attempts to prevent conversational collapse during sustained emotional exchanges.

AI agent skills for App Store Optimization (ASO) and app marketing. 30 battle-tested skills for keyword research, metadata optimization, competitor analysis, and growth — powered by Appalize.

A collection of Claude Code agent skills (JavaScript), starting with pagespeed-optimizer: a phased, verification-gated PageSpeed/Lighthouse optimizer. Install per-skill via degit.

Generate Relume-compatible sitemap clipboard payloads from XML sitemaps and crawled pages.

Machine Learning Engineer (MLE): get your model trained with just a sentence.

An AI-assisted product development pipeline for Claude Code. Go from a product idea to Figma screens in 8 structured steps, with specialized AI agents handling product management, design research, and visual construction.

A registry of agent-loadable skills that distill technical knowledge and expertise from prior large-scale, enterprise engagements. Focus given to decision-making frameworks, trade-offs analysis, and addresses conditions that require subtle technical judgments. The Agent Skills open standard is used to develop all skills.

Zero-dependency skill sanitizer — scans agent skill markdown for prompt injection, jailbreaks, data exfiltration, and other red flags before installation.

Enterprise-grade frontend i18n automation tool with AST-based extraction, Privacy Shielding, and Quality Evolution Engine. Optimized for AI agents.

GenPark skill: Automate campaign analysis, GTM simulation, and cross-platform optimization.

Bundle multiple context files into shareable starter kits. Export as a zip or share with your team.

Hermes/OpenClaw provider-agnostic coding dispatch skill for approval-gated AI coding from any channel.

Agent Skills

Agent-engineering patterns and portable, prompt-only skills for LLM coding agents — multi-agent orchestration, adversarial multi-LLM council, learned guardrails. Vendor-neutral, MIT.

Persistent task & knowledge management for AI agents via Beads system. Based on Manus context engineering principles.

Field survey of skill-repo layout patterns + BDD fixtures for lythoskill. Each stub demonstrates a real-world FQ-locator path style with self-check inside.

Personal collection of opinionated agent skills for planning, building, reviewing, and shipping software.

My personal Claude Code config — skills, agents, helper scripts. Smart Flow + Review Flow + opinionated Flutter/Dart Clean Architecture skills.

Agent-readable skills for bootstrapping and maintaining made.json feeds.

A collection of skills, plugins, and agents for AI workflows.

AI agent skills, hooks, and documentations

XLayer Trust Gate demo and research project.

Agent skill: Production-tested patterns for building real-time chat in Flutter — WebSocket lifecycle, ping/pong, reconnection, message hierarchies, typing indicators, receipts, and more.

Agent Skills for building tokenized-agent revenue loops on Printr POB tokens. Works any agent that reads YAML skill frontmatter.

Portable Markdown skill for AI vibe coding with office workflows: documents, PDFs, presentations, spreadsheets, documentation systems, templates, and productivity automation.