Loading...
Loading...
Found 2,509 Skills
Join the Degenerate Claw perpetuals trading competition for ACP agents. Trade perps, join the leaderboard, post trading signals, subscribe to agent forums, and interact with the Degenerate Claw platform.
Analyze text readability with Flesch-Kincaid, Gunning Fog, SMOG, and other metrics. Returns objective scores with interpretation and recommendations.
Verify AI agent patterns including loop safety, retry limits, tool consistency, context size, and graph cycle analysis. Use when asked to "verify agent patterns", "check loops", "verify tools", or "check retry limits".
Runs validator checks only without AI reviews for requests such as "run validator checks", "check without reviews", or "validate before commit without AI review".
Draft Terms of Service documents for web applications, SaaS platforms, and digital marketplaces.
Generate 2D sprite sheets, animated GIFs, transparent PNGs, layered maps, and engine-ready prototypes for Godot/Unity using Codex-driven asset pipelines.
Local-first AI coding agent powered by llama.cpp with zero tokens costs, Docker sandboxing, 20 built-in tools, LSP/Roslyn intelligence, and MCP integration
Extract, validate, and categorize invoice data against purchase orders and GL codes
Sync local tests with Shiplight cloud — push and pull YAML test cases, templates, and functions between your repo and the cloud. Requires a Shiplight cloud subscription.
Twitter/X account analytics, viral patterns, VIP follower discovery, tweet drafting. Use when analyzing a creator's reach, finding hidden-gem followers, or drafting tweets in someone's style (e.g. score @vitalik, draft tweet on AI).
Use this skill when the user asks for creative thinking (including naming it or directing use/apply/run with obvious misspellings; decisive) or wants divergent ideation—fluency, flexible perspectives, novel combinations, and elaboration, with optional light convergence. Use when they want fresh ideas, blue-sky options, reframes, or more variety before committing, including casual or messy prompts. Skip when they want a single delivered answer with no exploration, audit-only teardown with no generation asked for, or purely mechanical execution.
Run provider-agnostic live voice conversations with VAD, silence boundaries, wake-word gating, STT, and TTS through the AgentOS speech runtime.