Loading...
Loading...
Found 1,066 Skills
Expert in designing, optimizing, and evaluating prompts for Large Language Models. Specializes in Chain-of-Thought, ReAct, few-shot learning, and production prompt management. Use when crafting prompts, optimizing LLM outputs, or building prompt systems. Triggers include "prompt engineering", "prompt optimization", "chain of thought", "few-shot", "prompt template", "LLM prompting".
Pre-ship audit checklist for Ethereum dApps built with Scaffold-ETH 2. Give this to a separate reviewer agent (or fresh context) AFTER the build is complete. Covers only the bugs AI agents actually ship — validated by baseline testing against stock LLMs.
The essential mental models for building onchain — focused on what LLMs get wrong and what humans need explained. "Nothing is automatic" and "incentives are everything" are the core messages. Use when your human is new to onchain development, when they're designing a system, or when they ask "how does this actually work?" Also use when YOU are designing a system — the state machine + incentive framework catches design mistakes before they become dead code.
Remove LLM-generated code patterns that add noise without value. Use when reviewing diffs, PRs, or branches to clean up AI-generated code. Triggers include requests to "remove slop", "clean up AI code", "review for AI patterns", or checking diffs against main for unnecessary verbosity, redundant checks, or over-engineering introduced by LLMs. Language-agnostic.
Configure a Mac mini as a reliable local LLM server with remote access, observability, and power-safe operation.
4-stage funnel that screens all 500+ Hyperliquid perps down to the top trading opportunities. Scores setups 0-400 across smart money, market structure, technicals, and funding. BTC macro filter, hourly trend gate (counter-trend = hard skip), cross-scan momentum tracking. Near-zero LLM tokens — all computation in Python. Use when scanning for new trading opportunities on Hyperliquid, evaluating setups, or checking market conditions.
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
Query the ExoPriors Scry API -- SQL-over-HTTPS search across 229M+ entities spanning forums, papers, social media, government records, and prediction markets. Includes cross-platform author identity resolution (actors, people, aliases), OpenAlex academic graph navigation (authors, citations, institutions, concepts), shareable artifacts, and structured agent judgements. Use when the task involves: Scry API, ExoPriors, /v1/scry/query, scry.search, scry.entities, materialized views, corpus search, epistemic infrastructure, 229M entities, lexical search, BM25, structured agent judgements, scry shares, cross-corpus analysis, who is this person, cross-platform identity, OpenAlex, citation graph, coauthor graph, academic papers, author lookup. NOT for: semantic/vector search composition or embedding algebra (use scry-vectors), LLM-based reranking (use scry-rerank), or the user's own local Postgres / non-ExoPriors data sources.
Orchestrate Chinese LLMs (DeepSeek, Qwen, Yi, Moonshot) through OpenRouter API with LangChain. Use when: openrouter, chinese llm, deepseek, qwen, moonshot, yi model, model routing, auto router, llm orchestration.
Use this skill when working with PostHog - product analytics, web analytics, feature flags, A/B testing, experiments, session replay, error tracking, surveys, LLM observability, or data warehouse. Triggers on any PostHog-related task including capturing events, identifying users, evaluating feature flags, creating experiments, setting up surveys, tracking errors, and querying analytics data via the PostHog API or SDKs (posthog-js, posthog-node, posthog-python).