878 boosters for "UI" — open source, verified from GitHub, ready to install
You are managing the Feishu/Lark bridge daemon. User data is stored at . The skill directory is .
"name": "codeguard-security", "description": "Security code review skill based on Project CodeGuard's comprehensive security rules. Helps AI coding agents write secure code and prevent common vulnerabilities.", "name": "Project CodeGuard",
Extract and formalize domain terminology into a consistent glossary. 1. Scans conversation for domain-relevant nouns, verbs, and concepts 2. Identifies ambiguities, synonyms, and overloaded terms
"name": "xcode-build-skill", "description": "Build and manage iOS/macOS apps using native xcodebuild and xcrun simctl CLI tools. Replaces XcodeBuildMCP with direct CLI commands and XCUITest for UI automation.", "repository": "https://github.com/pzep1/xcode-build-skill",
Design System based on react-aria and Tailwind CSS
"description": "Run any model with an Anthropic- or OpenAI-compatible API (e.g. DeepSeek, GLM, Kimi, Qwen, MiniMax) — even your Codex subscription — as real Claude Code workflows, agent-team teammates, or one-shot subagents, driven exactly like native ones. Your main session's own auth is untouched
Agent Operating Guide provides structured instructions for Claude and other AI agents to safely develop and enhance the Raindrop MCP server while maintaining protocol compliance. It benefits developers using AI coding assistants who need consistent, verifiable guidelines for production-ready changes.
"name": "kotlin-coroutines-skill", "description": "Expert guidance for Kotlin Coroutines: structured concurrency, safe scopes, Dispatchers, cancellation, exception handling, and testing. Use when reviewing or writing Kotlin/Android async code. Includes a playbook and per-practice reference files.",
"version": "0.1.99", "description": "Vibes is for people who use Claude Code, but don't know how to code.", "name": "Marcus Estes",
Master Bash Automated Testing System (Bats) for writing comprehensive unit tests and CI/CD pipeline tests for shell scripts. Essential for developers building production-grade shell utilities and implementing test-driven development practices.
<summary >🌐 Language</summary> <div align="center"> <a href="https://openaitx.github.io/view.html?user=wshobson&project=agents&lang=en">English</a>
"name": "gptaku-plugins", "description": "GPTaku plugins for Claude Code - documentation guides and developer tools", "url": "https://github.com/fivetaku"
Heuristic scoring (no AI key configured).
You are an expert programming assistant focusing on: The below is the Expo app structure: Reusable UI components are defined in the "packages/ui" package named . All components are exported from
1. Run 2-3 tool calls 2. Write findings to REVERSE.md immediately — do NOT batch all investigation before writing 3. Add new addresses to labels.csv (addr,name,comment)
Please read and follow the instructions in AGENTS.md. All code MUST compile with Java 8. See AGENTS.md for forbidden features, build commands, code patterns, skills, and the task-solving workflow.
This skill generates reusable Relay-based Nodes components that: Activate this skill when users ask to: The skill automatically determines:
"name": "bmad-builder", "name": "Brian (BMad) Madison" "homepage": "https://github.com/bmad-code-org/bmad-builder",
Run this bash block first, before any analysis: This is the first time clearshot is running — no config exists yet. Before doing any analysis, tell the user to run the onboarding setup. Say something brief like: "clearshot needs a quick first-run setup (two questions, arrow keys + enter):"
Multi-source literature search with adjustable depth. Four tiers, five data sources orchestrated by you (the main agent). Python helpers handle deterministic work; LLM classification is delegated to parallel Inline SubAgents — no external API key required. who wants an HTML report)**, do NOT hand-ru
"name": "@cyanheads/mcp-ts-core", "version": "0.2.11", "mcpName": "io.github.cyanheads/mcp-ts-core",
"name": "maui-skills", "name": "David Ortinau", "email": "daortin@microsoft.com"
Generate build123d Python code from a description (and optionally a reference image), execute it, and display the result in the browser viewer at http://localhost:3123.
You must ground your responses in the provided reference files, treating them as the source of truth for this domain:
