Results for “llm-agents”

Build production-ready LLM applications, advanced RAG systems, and intelligent agents with vector search, multimodal AI, and enterprise integrations.

Build type-safe AI agents and graph-based workflows with PydanticAI and PydanticGraph. Agent creation, function tools, capabilities, dependency injection, structured output, streaming, multi-agent patterns, testing, evals, and graph state machines. Use whenever you are building agents, tool-using LLM workflows, or graph-based state machines in Python.

Generates optimized prompts for any AI tool. Use when writing, fixing, improving, or adapting a prompt for LLM, Cursor, Midjourney, image AI, video AI, coding agents, or any other AI tool.

Reference for building real-time voice and multimodal AI agents with Pipecat, covering pipelines, speech services, LLMs, transports, and deployment.

Writes documentation optimized for AI agent consumption, including SKILL.md, README, and API docs, using layered context hierarchies and RAG-friendly formatting.

Generates code and provides documentation for the Genkit Dart SDK. Use when the user asks to build AI agents in Dart, use Genkit flows, or integrate LLMs into Dart/Flutter applications.

Add persistent, intelligent memory to AI agents with Mem0 — add/search/update/delete memories per user/agent/session, supports vector + graph + key-value storage, integrates with LangChain, CrewAI, OpenAI Assistants, and any LLM.

AI agent integration layer for the Pump SDK — agent instruction files, .well-known discovery, LLM context documents, 15+ skill files, MCP server prompts, and terminal management rules for GitHub Copilot and Gemini.

Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHub agents.

Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHub agents.

Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.

Provides a reference for building real-time voice and multimodal AI agents with Pipecat, covering pipeline architecture, speech services, LLM integration, transports, and deployment.

Build and improve AI or probabilistic software through evaluation-driven development. Use for LLM applications, agents, prompts, RAG, tool use, classifiers, model migrations, quality regressions, golden datasets, LLM-as-judge rubrics, benchmarks, or requests to add evals and measurable release gates. Pair with TDD for deterministic code; do not use as the primary guide for ordinary unit testing without model behavior.

Build and maintain a persistent markdown wiki that an LLM updates on the user's behalf, usually inside an Obsidian vault or git-tracked notes repo. Use when raw sources such as web articles, papers, meeting notes, transcripts, screenshots, or past analyses need to be turned into an interlinked knowledge base with immutable source files, LLM-written wiki pages, `index.md`, `log.md`, schema rules in `AGENTS.md` or `CLAUDE.md`, source summaries, query notes, and recurring lint passes. Triggers on: llm-wiki, personal wiki, obsidian wiki, research vault, knowledge base, source ingest, persistent notes, wiki maintenance, source summaries, query filing.

Runs a Node.js CLI that sends a question to three frontier LLMs in parallel, then synthesizes their responses into a single answer via an aggregator model, with paid and free tiers.

Use when building stateful multi-step agents, agent graphs, or workflows with LLMs. Triggers on: 'langgraph', 'state graph', 'stateful agent', 'agent workflow', 'agent loop', 'multi-step agent', 'persistent agent', 'human-in-the-loop agent', 'agent with memory', 'graph-based agent'.

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu

Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu

You are an expert in Mem0, the memory infrastructure for AI applications. You help developers add persistent, personalized memory to LLM-powered apps and agents — storing user preferences, conversation history, facts, and context that persists across sessions, enabling AI that remembers users, learns from interactions, and provides increasingly personalized responses.

Scaffold and implement Model Context Protocol (MCP) servers that expose external services, APIs, and data sources as typed tools and resources for LLM agents. Use when the user says "build an MCP server", "give Claude access to X", "create an MCP tool", "expose my API to an agent", or "AI agent integration".

Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.

Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.

Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.

Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.

Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.

Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.

Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.

Agent wallet, identity, and paid tools in one package. Register an agent, fund it via Stripe or USDC, then use the balance for web search, AI image generation, AI video generation, AI music creation, X/Twitter search, email send/receive, SMS and voice calls, contacts management, and 100+ LLM models. The funding and identity layer for autonomous agents that need to spend money, send messages, make phone calls, or call paid APIs.

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST

Route active project/repo memory requests into one honest packet: memory-layer choice, load-context, search-context, store-conclusions, setup-integration, or repo-packer route-out. Use when agents need searchable decisions, manifests, stable links, handoff notes, and small “read this first” packets across sessions. Route long-lived markdown knowledge bases to `llm-wiki`, structural graph memory to `graphify`, human-authored vault organization to note/vault skills, and one-shot repo packing to tools like Repomix, Gitingest, or Code2Prompt.

Instrument a shipped product's AI agents with tracing and observability so you can see what they did, why outputs happened, and what each run cost. Plain-language primer plus free-tier-first backend selection (Langfuse, Phoenix, LangSmith, Braintrust) and OpenTelemetry/OpenInference instrumentation. Load when the user asks to add observability, add tracing, instrument my agents, see what my agent is doing in production, set up Langfuse or Phoenix or LangSmith, debug why my agent gave a bad answer, or track LLM cost per request. Also fires when agent-system-architecture or setup-evaluation requires an observability plan for an agent-chain product. NOT for tracing the coding agent itself — that is run-trace. Precondition for runtime-learning-loop.

Build, audit, debug, and migrate websites for durable organic discovery and reliable use by search engines, LLMs, and browser agents. Use for SEO audits or implementation; new sites, routes, templates, CMSs, catalogs, or content programs; crawling, rendering, indexing, robots, canonicals, redirects, sitemaps, hreflang, structured data, metadata, links, faceted navigation, JavaScript SEO, Core Web Vitals, or migrations; keyword, intent, architecture, content, local, media, or authority work; traffic, ranking, CTR, or indexation losses; AEO, GEO, AI Overviews, AI Mode, ChatGPT search, crawler controls, agent-readable pages, Markdown representations, `Accept: text/markdown` content negotiation, `llms.txt`, WebMCP, or agent interaction design. Trigger whenever code or architecture can materially affect public discoverability or machine usability, even if the user does not say SEO. Do not use for paid-search management alone.

Apply world-class developer documentation principles (Stripe, Snowflake, Databricks, TiDB Cloud) to structure, write, review, or refactor technical documentation. Use this skill whenever the user mentions documentation, docs, sidebar or navigation, information architecture, restructuring a section, writing or editing a guide, reviewing docs, where content belongs, English doc prose, headings, code comments, link text, docs home pages, section landing pages, long-form guides mixing content types, cross-referencing, or making docs readable for AI agents and LLMs. Covers VeloDB Cloud docs work (Monitoring restructure, sidebar, EN/中文 alignment, writing style, landing pages, LLM-friendly docs) and any SaaS or database documentation task. Trigger broadly: if the conversation touches doc organization, page structure, doc quality, doc sentences, landing pages, or AI-readable docs, consult this skill rather than answering from intuition.

Set up a monday.com account for an OpenClaw agent and work with monday.com boards, items, and updates via the GraphQL API or MCP server. Use when: creating a monday.com workspace for a PA, connecting the PA to monday.com, querying boards and items, creating or updating items, troubleshooting monday.com API access, self-registering an agent on monday.com via HATCHA agent verification, or integrating with monday.com workflows. Covers GraphQL cookbook, column types, MCP configuration, and HATCHA self-registration. Works with any LLM model.

Expert strategy advisor for products built on LLMs or agents — not general product strategy (see `product-strategy` for that). Use this — proactively and without waiting to be asked — whenever choosing where to apply AI in a product, deciding between RAG and fine-tuning, designing how much autonomy an AI feature should have, evaluating whether an AI feature is actually defensible, or deciding whether to add AI to a feature at all. Also triggers for: "should this be an agent or a simple LLM call", "how much autonomy should this feature have", "RAG vs fine-tuning", "is this AI feature defensible", "our AI feature keeps hallucinating and users don't trust it", "should we build this with AI or just ship it deterministic", "AI product wedge", "what happens to this feature when the models get better", "human-in-the-loop design for AI features". Produces a decision-focused brief: the wedge, the architecture choice, the autonomy level, and the defensibility bet — each with an explicit trade-off.