30 skills found
openclaw / model-usageUse CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
anthropics / Agent DevelopmentThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
google-gemini / async-pr-reviewTrigger this skill when the user wants to start an asynchronous PR review, run background checks on a PR, or check the status of a previously started async PR review.
triggerdotdev / trigger.devTrigger.dev – build and deploy fully‑managed AI agents and workflows
PaperDebugger / paperdebuggerA Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing
drhelius / GearboyGame Boy / Game Boy Color / Super Game Boy emulator, debugger and embedded MCP server for macOS, Windows, Linux, BSD and RetroArch.
golf-mcp / golfProduction-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents
OrionStarAI / DeepVCodeDeepV Code - A highly customizable AI coding assistant compatible with all major AI models. The perfect alternative to Claude Code and Codex, offering deep code analysis, intelligent suggestions, version rollback, multi-device sync, and automated testing across multiple languages and platforms.
microsoft / DebugMCPGift your VS Code agent a real debugger: breakpoints, stepping, inspection.
agentify-sh / desktopAgentify Desktop lets Codex/Claude/OpenCode control your logged-in ChatGPT, Claude, AiStudio, Gemini, Grok, Perplexity web sessions via MCP, parallel hidden/visible tabs, file upload + image download
flytohub / flyto-coreThe open-source execution engine for AI agents. 412 modules, MCP-native, triggers, queue, versioning, metering.
nim444 / mcp-android-server-pythonMCP Android agent - This project provides an *MCP (Model Context Protocol)* server for automating Android devices using uiautomator2. It's designed to be easily plugged into AI agents like GitHub Copilot Chat, Claude, or Open Interpreter to control Android devices through natural language.
illegal-instruction-co / processhacker-mcpyour ai debugger, vibe hacking tool
OkGoDoIt / beemcpBeeMCP: an unofficial Model Context Protocol (MCP) server that connects your Bee wearable lifelogger to AI via the Model Context Protocol
sani-iv / hyperblueBuild premium, brand-aware React/Next.js frontends that feel designed by a senior UI engineer, not generated by AI. Use this skill whenever the user wants to create websites, landing pages, dashboards, web apps, React components, or any frontend UI — especially when they provide brand assets (logos, screenshots, colors), mention a specific business or industry, want to match an existing design system, or ask for "non-generic" or "premium" output. Also trigger when the user shares competitor sites for inspiration, asks for design tokens, wants animation direction, or needs responsive brand consistency. This skill replaces generic AI aesthetics with market-aware, brand-calibrated design engineering. Created by Incredible Visibility.
diegosouzapw / codexReview code changes, implementation plans, or specific files using OpenAI Codex CLI. Triggers on "review", "check", "validate", "codex". Perfect for maker-checker workflows where you want a second AI agent to review Claude's work before committing. Requires the Codex CLI to be installed (brew install codex-cli or from https://codex.storage.googleapis.com).
diegosouzapw / valenceQuery and manage the Valence Knowledge Substrate - how agents build genuine understanding of their humans. Use for: (1) Searching past knowledge/decisions/context, (2) Storing new beliefs/facts/learnings, (3) Checking database stats. Triggers on "what do I know", "remember this", "store this", "knowledge base", "valence", "beliefs", or questions about past work/decisions.
diegosouzapw / mad-logicThe official MAD-Logic reliability framework for high-stakes multi-step tasks. Uses MAKER principles (Maximal Agentic Decomposition, voting consensus, red-flagging) to achieve zero-error execution. Auto-triggers for complex workflows or critical operations (deployment, security, financial). Compliant with ASP v2.0 Standard.
diegosouzapw / sprite-cliManage Sprite environments using the sprite CLI. Use for creating/destroying sprites (only when user explicitly requests), listing sprites, executing commands in remote sprites, managing checkpoints, port forwarding, file transfer between sprites, and API operations. Triggers on sprite management tasks or cross-sprite operations.
cagdotin / cmuxEnd-user control of cmux topology and routing (windows, workspaces, panes/surfaces, focus, moves, reorder, identify, trigger flash)
d4n-sec / jdb-mcpJava Debugger MCP Server. Enables AI agents to debug live Java apps via JDI with breakpoints, stack tracing, and variable inspection.
udayanwalvekar / clearshotStructured screenshot analysis for UI implementation and critique. Analyzes every UI screenshot with a 5×5 spatial grid, full element inventory, and design system extraction — facts and taste together, every time. Escalates to full implementation blueprint when building. Trigger on any digital interface image file (png, jpg, gif, webp — websites, apps, dashboards, mockups, wireframes) or commands like 'analyse this screenshot,' 'rebuild this,' 'match this design,' 'clone this.' Skip for non-UI images (photos, memes, charts) unless the user explicitly wants to build a UI from them. Does NOT trigger on HTML source code, CSS, SVGs, or any code pasted as text.
viktorvuka / things-todoGenerate a clickable Things 3 import link from tasks discussed in conversation. Use this skill whenever Claude produces a list of actions, tasks, to-dos, next steps, or a project plan that the user might want to track — even if they don't explicitly say "Things" or "todo list." Also trigger when the user says things like "ajoute ça dans Things", "fais-moi une todo", "crée les tâches", "envoie ça dans Things", "make a task list", "send to Things", "plan this out as tasks", or any variation. If a conversation ends with a clear set of actionable items, proactively offer to generate the Things link. Always use this skill instead of outputting a plain markdown checklist when the user could benefit from real task management.
rickyltwong / xnatctlUse when running xnatctl commands, writing scripts that call xnatctl, troubleshooting XNAT CLI operations, or helping users with XNAT neuroimaging server administration via the command line. Triggers on mentions of xnatctl, XNAT CLI, session download/upload, prearchive, scan management, or XNAT project administration.
Garfield1002 / tgUse tg to send Telegram messages, attach files, and listen for replies from the command line. Trigger when the user wants to send notifications, share files, or receive messages via Telegram.
diegosouzapw / mad-logicThe official MAD-Logic reliability framework for high-stakes multi-step tasks. Uses MAKER principles (Maximal Agentic Decomposition, voting consensus, red-flagging) to achieve zero-error execution. Auto-triggers for complex workflows or critical operations (deployment, security, financial). Compliant with ASP v2.0 Standard.
mattobee / estimating-accessibility-effortUse this skill to estimate the effort required to remediate accessibility issues. Triggers when sizing accessibility work for a sprint, estimating how long a WCAG fix will take, scoping remediation work, or planning accessibility improvements.
openclaw / recall-double-checkQuality assurance system that verifies deliverables match user requirements and execution plans. Features: (1) Auto-Memory - record conversations and tasks, (2) Double Check - verify deliverables in 3 scenarios: plan confirmation, post-delivery verification, user-triggered check, (3) Idle Reflection - periodic review and lesson extraction. Triggers on 'double check it', 'dc it', 'what's wrong', '再检查一下', '到底怎么回事'.
Phap1106 / competitor-intelligenceFull competitor analysis chain for Facebook pages. Triggers on ANY facebook.com URL or "phân tích đối thủ" request. Automatically resolves pageId + displayName, scrapes Ad Library via Apify, falls back to Serper organic data, saves to memory. Never stops mid-chain to ask questions.
lancejames221b / suggestGet AI-powered hAIveMind command suggestions based on current context and intent
