quicknode
Blockchain RPC and data access via Quicknode. Use when an agent needs to read onchain data (balances, token prices, transaction status, gas estimates, block…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-08 00:04
Agents & models
25,900 results
siwa
SIWA (Sign-In With Agent) authentication for ERC-8004 registered agents.
zerion
Interpreted crypto wallet data for AI agents. Use when an agent needs portfolio values, token positions, DeFi positions, NFT holdings, transaction history, PnL…
harness-collaboration
For Bankr agents operating a Harness-provisioned wallet. Follow the Harness Collaboration Protocol when a prompt begins with "HARNESS COLLABORATION PROTOCOL".…
basecamp-connect
Connect a Basecamp agent to this computer and manage the local agent connector's setup: the agent's credential (basecamp auth agent connect), connect.json (who…
gate-work
Executes an operator-authored gate document by loading it into context and working through each checkpoint as the executing agent — no subagent dispatch.…
triage
Articulates the why behind a candidate queue item — its direction, its named uncertainty, and the conscious scope-carve — and gates it through a cold-context…
chatgpt-app-builder
Build ChatGPT Apps using the Apps SDK and MCP. Use when users want to: (1) Evaluate if their product should become a ChatGPT App (2) Design and implement MCP…
token-audit
Audit Claude Code token usage and find where tokens are leaking. Reads ~/.claude/projects/*.jsonl transcripts AND Claude desktop cowork (local-agent-mode)…
sglang-deepseek-v31-optimization
PR-backed and current-main optimization manual for DeepSeek V3.1 and DeepSeek-V3.1-Terminus in SGLang. Use when Codex needs to recover, extend, or audit…
sglang-deepseek-v32-optimization
PR-backed and current-main optimization manual for DeepSeek V3.2, V3.2-Exp, V3.2-Speciale, NVFP4, and MXFP4 in SGLang. Use when Codex needs to recover, extend,…
codex-claude-cursor-loop
Orchestrates a triple-AI engineering loop where Claude plans, Codex validates logic and reviews code, and Cursor implements, with continuous feedback for…
codex-claude-loop
Orchestrates a dual-AI engineering loop where Claude Code plans and implements, while Codex validates and reviews, with continuous feedback for optimal code…
prompt-enhancer
Enhance user prompts by analyzing project context (code structure, dependencies, conventions, existing patterns). Use when users provide brief development…
prediction-market-agents
Comprehensive knowledge base and strategic framework for AI agents operating in prediction markets (Polymarket, Kalshi, and others). Use this skill whenever…
scienceclaw-benchmark
Index of the 23 discipline skills (FoR30-FoR52) that mirror the disciplines of the companion ScienceClaw-Eval benchmark: find which discipline skill fits a…
scienceclaw-benchmark-for32
Use when segmenting the hippocampus into anterior and posterior parts in small 3-D T1-weighted brain MRI crops (Medical Segmentation Decathlon Task04) from a…
scienceclaw-benchmark-for36
Use when a task asks to separate stereo music mixtures into four stems (vocals, drums, bass, other) and deliver the estimated stems, optionally with training…
scienceclaw-evolution
Operate ScienceClaw's program-level self-evolution - turn a finished, replay-verified canvas session into a Skill/Operator candidate, gate it on…
apps
Search and run 250+ AI apps — image generation, video, TTS, web search, LLMs
skill
Search, use, install, and publish skills from the belt registry
benchflow-traj-upload
Find a local Claude Code or Codex session, open the BenchFlow trajectory viewer, and submit it after the user reviews it. Use this skill whenever someone…
agent-recovery
Independent counselling for an AI agent that is stuck. Use when you have repeated the same failing attempt, keep undoing your own work, face conflicting…
accelerated-mode
Single source of truth for the bencium-loop opt-in workflow fan-out — the two gates that must both hold, the fallback rule, the guardrails, and how a run is…