22 packages found
A Claude Skill that coaches you to write better coding prompts before implementing — evaluate, clarify, plan, code, revi
Design intelligence engine for AI coding tools (Claude Code, Cursor, Windsurf). Deterministic anti-AI-slop linter with 1
AI-ready Solidity style guide for Solidity 0.8.30 — naming, layout, NatSpec, custom errors, ERC-7201 storage, transient
your ai agent keeps making the same mistakes. sheal fixes that.
A CLAUDE.md Generator and Maintenance tool for for Claude Code to create high-quality CLAUDE.md instruction files — alig
Generate Apple Shortcuts from natural language using Claude Code. Describe any automation and get a signed .shortcut fil
An open-source AI skill that upgrades your prompts. Load verified thinking profiles of tech founders and philosophers to
Installable GitHub library of 1,500+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and mor
The open source circuit breaker for AI agents. Real-time security, secret DLP, and loop burn prevention for Claude Code,
@microsoft✓ OfficialA collection of skills and MCP systems to enable users of CLI, VSCode, Claude to operate over Microsoft Fabric
[Legacy] Optimized AGENTS.md system instructions for AI CLI/IDE agents. Token-efficient (Caveman ~75%), skills, subagent
Production-extracted architecture for Claude Code CLI. 3-layer system: CLAUDE.md constitution + specialist Skills + pers
Lint and optimize your CLAUDE.md / AGENTS.md — find dead rules, token waste, and structural issues. One command, one sco
任意链接（网页/播客/视频/X）→ 中文结构化解读 → NotebookLM 式对话。自包含 skill，任何能跑 shell 的 AI agent 都能用。
@threerocksClaude Code skill：把内容套进内置手绘画风配方,产出可直接复制的生图提示词。内置儿童涂色/极简线条/蜡笔童涂/吉卜力/小豆人涂鸦 5 种已验证画风。
Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, re
One command. Full stack. Zero compromise. — All-in-one Claude Code skill with 33 modes, 6-layer security, 23 hooks, a
Connection-first PhD advisor matcher — find the right advisor by network strength, not h-index. Quantitative 4.0 scoring
Scholar-Wendao (学者问道) — open-source Claude Skill framework for distilling scholar perspectives into runnable analytical
AI context engine for Claude Code, Cursor, Windsurf — pack, compress, and optimize any codebase. Save 60-90% tokens. Web
Turn your local Claude Code / Codex CLI history into a shareable, anonymized AI-Native developer profile + viral SVG pos