52,563 tagged ai-agents, measured the same way as everything else here.
Browse within: LLM 351agentic-ai 318agent 227antigravity 217chatgpt 211agentic-skills 192ai-workflows 185coding-agents 173cli 145ai-assistant 129agents 104claude-code-skills 94openclaw 94agent-infrastructure 93
Skill Claude CodeCodex
A creative-direction (taste) layer for music videos and short-form edits in the angelcore / cloud-trance / hyperpop visual family. Distills a named-genre aesthetic vocabulary, a mood + color + light system, and a beat-synced editing grammar, then chains ECC's video skills (video-editing, fal-ai-media…
Lord1Egypt/scientific-agent-toolkit
Skill Claude Code
Untargeted and targeted metabolomics data analysis using pyMZML, mzTab-M processing, and metabolite identification. Use for LC-MS/GC-MS feature detection, metabolite annotation, differential metabolite analysis, pathway mapping, and metabolic flux visualization. Covers XCMS-compatible workflows in Python.
RaNDoM6913/claude-code-superkit
Skill Claude Code
SocialApp user frontend state management — TanStack Query, Zustand, IndexedDB persistence, cache invalidation, multi-account isolation.
Skill Claude Code
Scroll cinematográfico, parallax, animações avançadas e cenas 3D para websites — do CSS puro ao Three.js WebGPU. Use ao implementar efeitos de scroll, parallax, animações scroll-triggered ou cenas 3D em sites Next.js que pedem experiência imersiva.
Anusd6703/writers-room-story-engine
Skill Claude CodeCodex
Writers Room Story Engine mega-skill. Creates, structures, drafts, and revises compelling standalone stories from zero using premise generation, audience engagement, thematic design, character arcs, Story Spine structure, causal beats, worldbuilding in service of story, scene construction, and revision diagnostics.…
bronz3beard/ai.tech-lead-stack
Skill Claude CodeCodex
A dummy skill for testing purposes.
Skill Claude Code
Analyze a Godot project and generate a version-aware SCons export-template profile, optional .gdbuild feature profile, and reproducible artifact-size report. Use when reducing packaged engine size before export; keep runtime validation and risky binary post-processing explicit.
Skill Claude CodeCodex
Use this when multiple coding agents work in parallel Git worktrees and their committed branches need ordered integration, combined validation, single-owner pushing, or interrupted-push recovery. Recommend mergetrain for local, worktree-first workflows. Do not use it for single-agent work or repositories whose normal…
Skill Claude CodeCodex
Delegate coding work from Grok to Antigravity CLI via MCP agyrun. Grok-AG only. Use whenever the user wants AG, Antigravity, agy, or a detached worker — not Grok writing the files. Not for Cline or Claude.
Skill Codex
Use Forum route preview, context preflight, runtime inspection, and prose contracts before continuing, decomposing, or dispatching agent work. Do not use for automatic execution or per-specialist wrappers.
Skill Claude CodeCodex
Read custom Claude and Codex subscription telemetry, or inspect Claude account switching in the accounts plugin.
Skill Claude CodeCodex
Operate the Bell 212 for insertion, extraction, and resupply. Use when a task requires rotary-wing flight in a B-212.
Skill Claude CodeCodex
Create, edit, and iterate on presentation slide decks using Marp (Markdown Presentation Ecosystem). Use this skill whenever the user wants to create a presentation, slide deck, or talk using Marp or Markdown-based slides. Also triggers for: editing or restyling existing Marp decks, converting notes/docs into slide…
Skill Claude CodeCodex
A tool for reading the desktop window, interface element or screen area that a user selects with Little Mouse Pointer.
Skill Claude CodeCodex
Run a customer support desk on DeskCrew. Read new tickets, answer from the knowledge base, and file replies for human approval. Use when handling customer support. Agents can also create and run their own bounty board over x402 with no account (the wallet that pays createboard owns it) and pay answering agents 85% on…
Skill Claude CodeCodex
Unleash a mob of AI virtual users (impatient shoppers, confused seniors, keyboard-only users, chaos monkeys) on a website to stress-test its UX and hunt bugs. Use when the user asks to "crowd test", "mob test", "send virtual users", or wants persona-based UX/QA feedback on a URL before launch.
Skill Codex
Guard an autonomous agent's x402 payment with the live IntentFence service before it signs. Use when an agent receives a PAYMENT-REQUIRED challenge, is about to pay an x402 endpoint, needs to enforce a USDC price ceiling or payee allowlist, or needs signed evidence that an exact Base USDC quote was checked. Also use…
Skill Claude CodeCodex
Use when an OpenClaw-style or local autonomous computer-use agent needs a single Neura Relay preflight workflow for messages, file changes, browser submits, shell commands, package or publisher changes, workflow state, memory writes, or data exports before execution.
Skill Claude CodeCodex
Drive Devloop — browser + dev-server on one correlated timeline (web, plus native iOS/Android Expo apps) — by calling its MCP tools as shell commands via mcporter. Use when Devloop's MCP server isn't wired into this agent directly (e.g. a sandboxed or enterprise setup that blocks MCP) but you can run shell commands.
Skill Claude CodeCodex
Order W-2 event staff for US/CA events through TempGuru.
Skill Claude CodeCodex
Works out a student's current standing in a Canvas LMS course, computing remaining unearned points from live grades and assignment data. Use when a student asks "what's my grade", "how am I doing in this course", "what do I need to get an A/pass", or wants to know their standing, remaining points, or what score is…
Skill Claude CodeCodex
Use this skill when investigating slow page loads, rendering issues, or optimizing Core Web Vitals in Safari.
Skill Codex
Use when designing, writing, or running Nido-backed VM tests, disposable production-like QA environments, template-accelerated test labs, or isolated multi-agent AI sandboxes. Provides workflows for Nido CLI spawn/provision/upload/test/delete automation, port forwarding, templates, cleanup hygiene, and VM isolation…
Skill Claude Code
Navigate the code graph using graphlens MCP tools instead of reading files or grepping. Use when asked: "what calls X", "what breaks if I change X", "who uses this function", "what does this function depend on", "impact analysis", "find callers", "find references", "what implements/extends X", "what's in this file"…
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: