Loading...
Loading...
Found 1,065 Skills
AI agent development standards using golanggraph for graph-based workflows, langchaingo for LLM calls, tool integration, MCP, and LLM best practices (context compression, prompt caching, attention raising, tool response trimming).
AI integration with Vercel AI SDK - Build AI-powered applications with streaming, function calling, and tool use. Trigger: When implementing AI features, when using useChat or useCompletion, when building chatbots, when integrating LLMs, when implementing function calling.
INVOKE THIS SKILL when adding Arize AX tracing to an application. Follow the Agent-Assisted Tracing two-phase flow: analyze the codebase (read-only), then implement instrumentation after user confirmation. When the app uses LLM tool/function calling, add manual CHAIN + TOOL spans so traces show each tool's input and output. Leverages https://arize.com/docs/ax/alyx/tracing-assistant and https://arize.com/docs/PROMPT.md.
Web crawling and scraping tool with LLM-optimized output. 网页爬虫爬取工具 | Web crawler, web scraper, spider. DuckDuckGo search, site crawling, dynamic page scraping. 智能搜索爬取 | Free, no API key required.
Set up a new Obsidian knowledge base with the LLM Wiki pattern. Use when the user wants to create a second brain, initialize a vault, set up a personal knowledge base, or says "onboard". Guides through an interactive wizard to configure vault name, location, domain, agent support, and tooling.
Manage Databricks Model Serving endpoints via CLI. Use when asked to create, configure, query, or manage model serving endpoints for LLM inference, custom models, or external models.
Run metric-driven iterative optimization loops. Define a measurable goal, build measurement scaffolding, then run parallel experiments that try many approaches, measure each against hard gates and/or LLM-as-judge quality scores, keep improvements, and converge toward the best solution. Use when optimizing clustering quality, search relevance, build performance, prompt quality, or any measurable outcome that benefits from systematic experimentation. Inspired by Karpathy's autoresearch, generalized for multi-file code changes and non-ML domains.
Detects common LLM coding agent artifacts by spawning 4 parallel subagents
Run agency-orchestrator YAML workflows directly in Claude Code / OpenClaw / Cursor — no API key required, using the current session's LLM as the execution engine. Triggered when the user provides a .yaml workflow file or requests multi-role collaboration to complete a task.
Compress LLM responses to pure signal — Rocky's early notation style. Drop articles, filler, hedging. Best for pipelines and coding.
Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
Create validated LLM-as-a-Judge evaluators following best practices — binary Pass/Fail judges with TPR/TNR validation for measuring specific failure modes. Use when you need to automate quality checks, build guardrails, or measure a specific failure mode identified during trace analysis. Do NOT use when failures are fixable with prompt changes (use optimize-prompt) or when failure modes are unknown (use analyze-trace-failures first).