SuperAPI AI DirectoryFind an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-11 00:16
26,094 results
Web content extraction strategy. This skill must be used when you need to read web page content, crawl pages, extract article body text, handle JS-rendered pages, or bypass anti-scraping restrictions. Three-tier tool selection: WebFetch (built-in) → Crawl4AI (JS rendering/anti-scraping) → native Playwright (fallback degradation).
Use this skill when the user needs to use the API reverse-proxied through Antigravity (Gemini 3 Flash, Gemini 3 pro, banana image generation, video analysis and understanding).
Build, inspect, edit, and install Yanzi extensions. Use when an agent needs to create or modify `manifest.json`, author C# or PowerShell extensions, call…
Find open AI engineering jobs that fit a candidate, verify location and apply links, and assess each employer's product. Use for one-off shortlists or a job…
Resume a limit-blocked OpenCode session in a fresh sandbox: same project and agent setup, no host OpenCode config/token/key, attached in a tmux panel. Don't…
Export, save, and import cookies for isolated browser MCP agents. Use after new logins in isolated browsers to persist sessions across restarts, or to seed…
Set up Playwright MCP with the Chrome extension for browser automation in Claude Code. Use when setting up Playwright MCP, troubleshooting browser connection,…
Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator…
Jesse Livermore's thinking framework and trading philosophy. Based on in-depth research across 6 dimensions, distills 5 core mental models, 8 decision heuristics, and a complete expression DNA. Purpose: To serve as a trading thinking advisor, analyzing the market, reviewing trading decisions, and providing feedback from Livermore's perspective. When the user mentions "from Livermore's perspective," "what would Livermore think," "Livermore mode," "Livermore...
CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish…
Coordinate multiple agents in parallel or sequential workflows. Use when running agents simultaneously, delegating to sub-agents, switching between specialized…
Use proactively when any other skill is invoked - checks that skill's recommended_skills field, compares against installed skills, and suggests missing…
Decision criteria for UI verification, E2E testing, and screenshot capture using Agent Browser (a headless browser automation CLI). Prioritize accessibility-tree-based element selection, aiming for test designs that are hard to break.
Render accumulated workflow state from memory into a valid Agent Skills bundle directory for workflow-architect, with sub-skills, manifest, decision map, and…
Monitor a session passively to infer the user's workflow from what actually happened, staying dormant until a trigger phrase activates observation for…
Entry point for Codex-discoverable skills used by the Run-Smart AI coach.
Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and…
[23] UNDERSTAND. Consult external AI models when internal sources are exhausted. Build quality prompts using Prompt150 formula (Context + Query + Method +…
Implement Agent-to-Agent (A2A) protocol for inter-agent communication. Use for agent discovery, agent cards, task delegation, and multi-agent orchestration.…
Agent-to-Agent (A2A) server configuration patterns for HTTP, STDIO, SSE, and WebSocket transports. Use when building A2A servers, configuring MCP transports,…
Generate A2UI 0.8 protocol compliant UI code. Use when building agent-driven interfaces, generating JSONL messages for…
Add new skills to an existing workflow and update all related documentation. Use when user wants to add skills from GitHub URLs to a workflow (e.g., "add this…
Imported skill agent from langchain
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand…