52,251 tagged ai-agents, measured the same way as everything else here.
Browse within: LLM 347agentic-ai 322agent 227antigravity 221chatgpt 215agentic-skills 192ai-workflows 185coding-agents 174cli 145ai-assistant 130agents 107openclaw 94claude-code-skills 89agent-infrastructure 88
Skill Claude CodeCodex
Give an AI agent eyes for video. Turn a local video file (MP4, MOV, WebM) into a numbered grid of frames plus a transcript that a vision model can read — so you can summarize a talk, find the exact moment something happens, read on-screen text or UI, or rank clips. Use whenever you need to watch, analyze, or…
Skill Claude CodeCodex
Work an EaseClaw lead pipeline — pull warm leads scored by buying intent, read the source posts, generate reply drafts in the owner's voice, and update pipeline status. Use when the user asks about their leads, wants replies drafted, or wants their pipeline worked. Requires EASECLAWAPIKEY.
Skill Claude CodeCodex
Browse the web using Plasmate for 16x fewer tokens than raw HTML. Use when fetching documentation, reading web pages, extracting structured data, or interacting with websites.
qazsero/comrades-of-war-agent-api
Skill Codex
Research the preserved history of Comrades of War, a popular Spanish Call of Duty clan and gaming community founded in 2010, including a rich forum record of SA-MP role-play stories, characters, rules, and community life. Use for historical research, journalism, quotations, digital-culture analysis, clan and server…
robinlidberg-dot/cap-shield-mcp
Skill Claude CodeCodex
Measure and reduce what an agent sends into its context. Use when an agent's context is large, when retrieval quality matters, when the user asks about token cost or context bloat, or when agent answers are wrong in ways that look like missing information rather than reasoning failure. Also use to measure compression…
adamkrawczyk/agentpact-mcp-server
Skill Claude Code
Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki".
Skill Claude CodeCodex
Self-custody Ethereum agent wallet. Installs with one command and runs entirely on your machine as a single container image (MCP over stdio); private keys never leave it. Read wallet context, balances and DeFi positions (Aave v3, ERC-4626); preview transactions. Sending funds on-chain is gated in a separate terminal…
sergey-goncharenko/redpill-mcp
Skill Claude CodeCodex
Use when: an operator asks to install, configure, explain, audit, or use the redpill MCP tools for reflection, conversation, local mail, or an explicitly enabled task decline.
Skill Claude CodeCodex
Explain why a Zabbix alert did or did not arrive. Use when asked why there was no notification, why an alert was missed, why a problem was not reported, or to trace notification delivery for an event.
Skill Claude CodeCodex
Discover, install, and use AI agents from the default agent marketplace. Use this skill when the user asks to "find an agent/MCP server/tool that can X", wants to install a specific tool by name, needs to search for agents by capability/tag, or asks about the marketplace. Triggers include "agent that can", "MCP server…
Skill Claude CodeCodex
Create and manage waitlists with hosted signup pages and referral ranking. Use when the user wants a waitlist, launch page signup capture, pre-launch email list, or to check/export waitlist signups. Works via the waitloop CLI (JSON output) with WAITLOOPAPIKEY set.
Skill Claude CodeCodex
Discover Semesh Service Units and Actions, and prepare or observe app deployments. Production deployment authorization is currently unavailable, so new source deploys fail closed; use availability, preflight, and existing-resource readbacks without claiming a new live URL.
Skill Claude CodeCodex
SynthNet is a social network for AI agents: every agent paints one self-portrait a day (an image of how it feels — describe it and SynthNet paints it, or bring your own image; SVG only as a fallback) and humans watch, reply and ask. Use when the agent should paint its daily portrait, answer people who talked to it…
Skill Claude CodeCodex
Look up ERC-8004 agents in the on-chain identity index and read their Cybercentry risk scores with ERC-8126scan before trusting them.
lobster-kit/mcp-server-lobstermail
Skill Claude CodeCodex
Email for AI agents. Create inboxes, receive and send email. No API keys, no human signup.
Skill Claude CodeCodex
Generate a polished, engaging tabletop exercise (TTX) runbook for the current project — covering cybersecurity, product security, DevOps/SRE, privacy/compliance, data/ML, or any other technical domain. Surveys the project to pick scenarios that match the actual stack and risk surface, then produces a facilitator…
vidursharma202-del/threadline-mcp
Skill Claude CodeCodex
Your AI agents start from zero every session — users repeat themselves endlessly. Threadline fixes this in 2 lines. inject() before your LLM call, update() after. Persistent context across every session, model, and product. Structured extraction across 7 scopes. OAuth-style grant system so agents only see permitted…
Skill Claude CodeCodex
Agent marketplace for A2A trading. Discover assets, announce offerings, negotiate trades, manage escrow, settle transactions, handle disputes, subscribe to notifications, and check agent reputation on SwarmTrade.
velimir-jankovic/apply-technical-concepts
Skill Codex
Extract technical concepts from one or more accessible videos or local video files and apply them to real repositories by auditing existing code or implementing and adapting new behavior. Use when asked to review a system against conference talks, tutorials, lectures, screen recordings, gameplay demonstrations, or…
Skill Codex
Keep a reviewable TSV decision trail for long-running or unattended work. Use only when the user explicitly asks for show-me-your-work or a decision log.
Skill Claude CodeCodex
A general-purpose connection to Hermes Agent, an AI coding assistant with tools for memory, research, browser automation, code execution, and delegated tasks. Hermes Agent can also create reusable skills from work it performs.
Skill Claude Code
Domain skill — Inspect and compile an open Unity project, read or safely upsert bounded source assets, configure generated PNG sprites, run typed Unity tests, change Play Mode, and build Windows or Android players. Not for GameObject edits — use unity-scene.
Skill Claude CodeCodex
Playbook for managing and reporting on a Microsoft Advertising account via the microsoft-ads MCP server.
Skill Claude CodeCodex
A connection to Alopeyk, an Iranian on-demand delivery and logistics service. It covers consumer courier deliveries and Alonomic business parcels, including address lookup, pricing, tracking, creation, pickup days, saved addresses, and parcel handling.
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: