17,532 tagged ai-agent, measured the same way as everything else here.
Browse within: LLM 341agent 300cli 284openclaw 219ai-tools 197chatgpt 193agentic-ai 180cybersecurity 160Multi-Agent 132agentskills 123curated 122myclaw 122skill-collection 121coding-agent 113
Skill Claude CodeCodex
ProxyClaw by IPLoop — Residential proxy access for AI agents. Route requests through 2M+ residential IPs across 195+ countries from real Android, Windows, Mac & Smart TV devices. Bypass geo-restrictions, rotate IPs automatically. Free tier with 0.5GB included. Earn unlimited proxy credits by contributing bandwidth via…
Skill Codex
A workplace analysis tool that helps workers understand employment situations and documents.
alvindemesadev/boring-engineering
Skill Claude CodeCodex
Prevents overengineering when designing, implementing, refactoring, or reviewing software. Use when the user asks to implement a feature, add an abstraction, refactor code, review a design, simplify existing code, or make an architectural decision. Also triggers when the user asks if code is too complex, whether to…
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when requesting a code review before pushing changes. Pre-commit verification pipeline — static security scan, baseline-aware quality gates, independent reviewer subagent, and auto-fix loop. Use after code changes and before committing, pushing, or opening a PR.
Skill Claude CodeCodex
DroidRun Portal HTTP/WebSocket/MCP client. Controls Android devices via HTTP, WebSocket, or MCP server, supporting tap, swipe, screenshot, text input, UI state retrieval and more. Use this skill when the user needs to interact with an Android device running DroidRun Portal.
Skill Claude Code
A planning-mode workflow that makes the coding agent design and submit a plan before changing files.
Skill Claude CodeCodex
Use WorkForge for secure profile-scoped Windows or macOS workstation file, shell, and project operations through its bundled MCP server.
Skill Claude CodeCodex
A skill for working with Avito, a Russian online marketplace and business platform, through its APIs.
Skill Claude CodeCodex
Read OpenCode sessions, messages, and tool outputs directly from the SQLite database at /.local/share/opencode/. Use when asked to "read opencode sessions", "query opencode db", "find old sessions", "search session history", "read message history", "export session", "inspect opencode data", "look up past…
sanhuang520-ship-it/awesome-chinese-ai-tools
Skill Claude CodeCodex
A skill for creating Chinese-style real-time 3D web visuals with Three.js, a JavaScript library for displaying 3D graphics in a browser. It focuses on ink-wash, blue-green landscape, mural, paper-cut, and other non-realistic styles.
Skill Codex
Use when a user asks about CST Studio Suite or CST-MWS automation, .cst projects, CST-specific antenna/RF simulation setup, editing CST parameters/geometry/ports/boundaries, running CST solvers, reading CST result trees/logs or CST-generated S11/S21/farfield/gain/efficiency results, using CST installed…
Friz-zy/ai-capability-registry
Skill Claude CodeCodex
AI assistant for ingested content with anonymous access.
Skill Claude CodeCodex
Write C#/.NET Sinch Functions with the Sinch.Functions.Runtime NuGet package. Use when writing or editing a function controller: answering and controlling calls, IVR menus, placing or bridging calls, SMS/WhatsApp/RCS webhooks, custom HTTP endpoints, dependency injection, cache/storage/database and authorization. Also…
Skill Claude Code
Deep analysis of a single paper: download PDF, extract figures, generate structured 20+ section note, fill LLM placeholders.
Skill Claude CodeCodex
Clone repos using bare clones + git worktrees, develop changes, deliver via Pull Requests. Use this skill whenever the user asks you to clone, code, fix, edit, refactor, implement a feature, or open a PR on any repository — including PT-BR phrasings like "clonar repo", "refatorar", "abrir PR", "corrigir bug"…
MetaBrain-Labs/ComfyUI-MCP-Server-TypeScript
Skill Claude CodeCodex
Enables AI agents to discover, inspect, and execute ComfyUI workflows for image and video generation through a structured MCP interface. Supports the full task lifecycle—from context loading and workflow discovery, to parameter mounting and task submission, and finally result retrieval and generated asset management.
Skill Claude CodeCodex
Automated deployment of Hermes Agent — install, configure providers, messaging platforms, and tools on local or remote systems.
Skill Claude CodeCodex
Agent-first cross-platform file operations CLI. Use when AI Agent needs local file operations (zip/unzip/info/read) or cloud storage operations (upload/download/list) with S3-compatible providers.
Skill Claude CodeCodex
A beta guide for building an AI development mode for WeChat Mini Programs, which are small apps that run inside WeChat. It covers the required files, project structure, data formats, text, components, and interfaces.
Core-Mate/Pixel-Perfect-Web-Replica
Skill Claude CodeCodex
Recreate public frontend pages locally with high visual fidelity. Use when the user asks Codex or Claude Code to pixel-perfect clone, mirror, study, sandbox, reproduce, or locally run a public website/page; capture its static assets; preserve layout, scroll animations, media, typography, and interactions; compare…
SquirrelSong5/travel-planner-skill
Skill Claude CodeCodex
A thinking framework that breaks work into five stages: define the problem, explore options, formulate a solution, act, and assess the result. It can be applied fully, partially, or minimally depending on the task.
Skill Claude CodeCodex
A guide for writing useful Git commit messages that explain what changed and why, using a consistent format.
Skill Claude CodeCodex
Control and query Home Assistant through the connector's callservice tool — REST API patterns, common domains, how to find entities before acting.
Skill Claude CodeCodex
Reduce avoidable token and API cost through task-aware model selection, context hygiene, concise responses, and disciplined tool use. Apply as an advisory policy on every turn. Actual savings vary by agent, model, provider, cache behavior, and workload; measure results instead of assuming a fixed percentage.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: