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
Design world-class SaaS landing pages grounded in real references from saaspo.com (via the saaspo MCP). Use when the user asks to design or build a landing page, marketing site, or any page for a product — especially when they provide copy and want it designed "like a senior designer", or mention saaspo, design…
Skill Claude Code
Forensic retrospective on how work actually FLOWED through the kanban-pro board — reconstruct each card's timeline from the change-log (lane moves, bounces, forced moves, attention, dispatch loops, rounds, cycle time), attribute it to the model that really served it (model-pro requested-vs-resolved, context overflow…
Skill Claude CodeCodex
Use CupOracle to answer FIFA World Cup 2026 questions (fixtures, live scores, consensus odds, knockout bracket) and to buy a vetted, CLV-audited edge that the agent pays for ITSELF via x402 on Injective — under a spend cap, always citing the on-chain receipt. Invoke when the user asks about a World Cup match, "who's…
Skill Codex
Plan, coordinate, and verify bounded public-internet research with claim-level citations, source-relative authority, explicit freshness and contradictions, and safe stopping. Use when a user asks agents to research, browse, search the web, find current or niche information, compare sources, investigate a contested…
ByteFlipper-58/material-icons-agent-skill
Skill Codex
Find, select, and integrate official Google Material Symbols and Material Icons. Use when a user asks to add, replace, search for, export, or choose UI icons; when icon filters such as meaning, category, style, fill, weight, grade, optical size, platform, or output format are specified; or when implementing icons in…
Skill Claude CodeCodex
Use nautli to set up and operate persistent local-first memory for MCP clients. Trigger when the user asks to remember or recall durable facts across sessions, asks "what did we decide about X", complains the agent forgot something from a previous session, wants memory shared between Claude Code and Cursor, wants to…
dcc-mcp/dcc-mcp-substance3d-painter
Skill Claude Code
Host skill - inspect and author the current Substance 3D Painter project. Use when creating or checking projects, building uniform or texture-driven PBR layers, masks and generators, baking mesh maps, importing resources, or exporting. Not for arbitrary JavaScript execution.
Skill Claude CodeCodex
Make a real, shareable meme image. Use when the user wants a meme, an image-macro, or a funny visual for marketing/social — anything where a caption goes on a known meme template (Drake, Distracted Boyfriend, Woman Yelling at Cat, etc.). Renders a finished PNG with correct font, outline, and text fitting.
Skill Claude CodeCodex
When the user says “fix this”, “what is wrong”, or “debug this”, use visible terminal/editor context to create a structured debugging command for Codra / Codex / OpenCode.
Skill Claude CodeCodex
Use when the user reports a 3D model or scene looking wrong (black/invisible/gigantic/untextured model, holes, weird shading), asks to check or QA a 3D file (GLB, GLTF, OBJ, PLY, STL, .splat), works with Gaussian splats, or generates 3D assets with AI and wants them verified. Requires the 3d-eyes MCP server.
Skill Claude CodeCodex
An installation guide for connecting RealtyCalendar webhooks and its MCP server to an AI client. A webhook is a URL that receives automatic event notifications from another service.
Skill Claude CodeCodex
Use when the user explicitly requests Claude, Sonnet, Fable, or Opus, or when an independent Claude perspective would materially improve a coding task, review, or diagnosis.
Skill Claude CodeCodex
Use this skill when changing the Kubernetes-only HTTP deployment.
Skill Claude CodeCodex
Buy and audit World Cup betting edges from LineLock over Injective x402. Use when the user wants the next knockout pick (model probability vs market odds + a conviction staking ladder), wants to pay per-call in USDC without an API key, or wants to audit a tipster's settled record by closing-line value (CLV). Handles…
Skill Claude CodeCodex
Drive an antidetect browser from your AI agent. Oculr gives the agent real, isolated Chromium browser profiles with engine-level fingerprinting and per-profile proxies, controlled over MCP and raw Chrome DevTools Protocol. Use when an agent needs to browse or act inside real logged-in sessions, manage many separate…
Skill Claude CodeCodex
Use when working with SentientUI — an adaptive UI personalization platform — from an AI agent. Covers connecting to the SentientUI MCP server, reading experiment data (variant performance, personas, goal funnels, AI insights, guardrail events), creating and pausing variants, and integrating the @sentientui/react SDK…
Skill Claude CodeCodex
Discover and extract sitemaps from any website using SitemapKit. Use this skill whenever the user wants to find pages on a website, get a list of URLs from a domain, audit a site's structure, crawl a sitemap, check what pages exist on a site, or do anything involving sitemaps or site URL discovery — even if they don't…
Skill Claude CodeCodex
Report meaningful Codex task progress, decisions, blockers, artifacts, and final outcomes to Loomscope. Use whenever a task has multiple phases, several tool calls, or a result worth tracing later.
Skill Claude CodeCodex
Distill a git repo's full history into durable engineering memory under .repo-memory/ (timeline, decisions, landmines, architecture). Use when the user wants historical/"why is this like this" context for a codebase, to onboard an agent onto a repo's past, or asks to run repo-history / analyze git history.
Skill Claude CodeCodex
Share documents, images, and PDFs with a human as persistent links via the Artifacts MCP server. Use when the user asks to publish or share an artifact, document, diagram, generated image, or PDF with a link.
cogniziocompany/agentic-remote-pc
Skill Claude CodeCodex
Drive a Windows or Linux host running agentic-remote-pc over its authenticated MCP runner. Use when the user asks to run commands on a remote PC, drive a coding-agent CLI (claude, cursor, aider, opencode, gemini, codex, copilot, goose, amp, qwen, crush) on a host, inspect health, or validate a local…
ShalomObongo/chrome-bridge-mcp
Skill Claude CodeCodex
Drive the user's real Chrome browser — their own profile, tabs, cookies and logged-in sessions — through the chrome-bridge MCP server. Use for tasks that need existing browser state: reading a page behind a login, filling a form on a site the user is signed into, testing a local app in a real browser, or inspecting…
Skill Claude CodeCodex
Write the behaviour specification for a feature BEFORE implementing it, as test cases. Use whenever you are about to build a new endpoint, screen, flow, or behaviour — especially anything touching auth, sessions, tokens, lists, or pagination. Also use when asked "how should I test this", "what should this actually…
mperkhou/career-agent-workbench
Skill Codex
Use when installing, configuring, operating, or developing the local Career Agent Workbench application, including its public CLI, Flask tracker, FastMCP server, external private workspace, and offline validation surfaces.
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: