52,468 tagged ai-agents, measured the same way as everything else here.
Browse within: LLM 352agentic-ai 317agent 228antigravity 216chatgpt 211agentic-skills 192ai-workflows 185coding-agents 172cli 145ai-assistant 129agents 104openclaw 94claude-code-skills 93agent-infrastructure 92
tonytanglab/deepseek-harness-relay-mcp
Skill Codex
Dispatch and monitor an explicitly scoped, simple or medium-complexity local subtask through models available in DeepSeek Harness, including read-only review and user-authorized workspace implementation. Use when the user says “调用 Harness”, asks Harness to analyze or review, or delegates a fix, edit, refactor, test…
Skill Claude Code
Lint and improve AI agent context files (CLAUDE.md, AGENTS.md, .cursorrules, COPILOT.md) based on empirical research. Use when reviewing, auditing, or creating context files.
Skill Codex
Scourgify closes out AI coding work by taking safe repository snapshots, classifying every in-scope Git path captured before or after the closeout, reconciling multi-chat or multi-agent work, syncing durable docs, recording verification, and validating a permission-aware handoff. Use when the user says "Scourgify!" or…
Skill Claude Code
Run the same task on a recurring cron schedule. Parses interval syntax (5m, 2h, 1d, "/15 "), records the schedule, and acknowledges back to the user.
Skill Claude CodeCodex
Generate production-ready AI steering documents — CLAUDE.md, AGENTS.md, GEMINI.md, SKILL.md, rules.md, .cursor/rules/, .kiro/steering/, copilot-instructions.md — for any AI coding system. Use when asked to write, improve, or review project instructions, agent rules, or steering docs for Claude, Copilot, Cursor, Kiro…
axelfreeman/b2b-contact-finder-guides
Skill Claude CodeCodex
Find and verify B2B business contacts using a three-tier playbook — manual research first, then free open-source scrapers, then automated MCP. Covers website scraping, Telegram channels, and Discord communities, with SMTP validation to keep bounce rates at 2–5%. Use when the user asks how to find business contacts or…
Kim-FengLei/multi-perspective-meeting
Skill Claude CodeCodex
Turn a single Agent into a full multi-perspective meeting. The Agent auto-generates one role-played participant per perspective, runs a structured debate with cross-examination, converges to a conclusion, and outputs an HTML meeting-minutes file. Trigger on any research / analysis / discussion / decision request.
Skill Claude CodeCodex
Persistent knowledge wiki and memory system that compounds across conversations using an Obsidian-compatible vault. Consult at the START of any non-trivial task to recall project context, preferences, and past discoveries. Ingest sources and build wiki pages when accumulating knowledge on a topic. Save at the END when…
Skill Claude CodeCodex
Use the blockrun CLI to pay-per-request AI (chat/image/video/music/speech), live data (web/X search, prediction markets, Pyth prices, 40+ chain RPC), and any x402-paid endpoint — all billed from a local USDC wallet, no API keys. Use when the user asks to run a model, generate media, query crypto/prediction/web data…
Skill Codex
Create, standardize, or audit a Howells project. Covers repo shape, tooling, package boundaries, UI, data, AI, agent workflow, deployment, and launch checks.
Skill Claude CodeCodex
Locate Apple devices (iPhone, iPad, Mac, AirPods) via iCloud Find My using the findmy-agent CLI. Use this skill when the user asks to find an Apple device, check iPhone/iPad/Mac/AirPods location, locate lost AirPods, "Where's my iPhone", "Dov'è il mio Mac", verify if a device is home vs away, or check if devices are…
Skill Claude CodeCodex
Search and analyze your own session logs (older/parent conversations) using jq.
Skill Claude CodeCodex
Tests Krayin CRM using the Pest PHP framework (v2) with Laravel 10.
Skill Claude CodeCodex
Use when working in a repository that uses Mneno for local project memory through the CLI, including task-start context recovery, narrow memory search, and storing durable project facts before stopping work.
Skill Claude Code
Create adaptive interfaces and real-time experiences via the pub CLI, with live P2P browser sessions.
thomasthzh/full-agent-takeover
Skill Codex
A task-delegation skill that hands an entire job to the coding agent after you choose its permission level.
Skill Claude CodeCodex
Full-featured GitHub integration via the gh CLI. Manage repositories, issues, pull requests, CI/CD workflows, releases, and make raw API calls.
Skill Claude CodeCodex
Automatically use klayer for grounding, codebase indexing, session memory, and episode logging during software development tasks unless the user explicitly opts out.
Skill Claude CodeCodex
Apply security guidelines when designing, building, or reviewing AI chatbots, LLM-powered apps, autonomous/tool-using agents, and mobile apps (React Native/Expo, Flutter) — covering agent controls (authorization checks, plan validation, execution limits, audit logging), LLM/prompt security (prompt injection, RAG…
fyzycyst/Agentic_Loop_Notation
Skill Claude CodeCodex
Design, audit, repair, and export AI-agent loops using Agentic Loop Notation v0.3. Use for loop design, prose-to-ALN translation, Loop Doctor safety reviews, and exports to Claude Code or Codex — scoped task prompts, Codex goals, skills, hooks, scheduled tasks, automations, and reusable loop examples.
Skill Codex
Coordinate a code or artifact delivery through exactly two user-visible Codex tasks, Developer and Reviewer, with durable checkpoints, immutable candidate fingerprints, independent verification, candidate-scoped review gates, explicit user release authorization, guarded recovery, and terminal handoff receipts. Use…
blackjose007-stack/adaptive-reasoning-router
Skill Codex
Classify project work into medium, high, or extra-high reasoning effort while keeping high as the stable default. Use when planning or starting a work order, choosing validation scope, handling repeated failures, making architecture or release decisions, controlling reasoning-cost usage, or preventing frequent…
ybx-stack/rich-brain-clean-hands
Skill Claude CodeCodex
This is the production-grade SKILL file that the rich brain loads when it needs to delegate. It covers the complete decision tree: when to delegate, who pulls data, how to launch, how to wait, how to read results. Paths use / placeholders — adapt to your layout.
Skill Claude CodeCodex
Auto-generates short vertical videos from YouTube content and publishes to social platforms.
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: