AI & Agents

Internal support skill for actionbook MCP selectors used by Rust documentation research workflows. Use only when another rust-skills workflow explicitly requests actionbook-backed selectors.

Pyodide Python tools for an already-approved in-app useAtlasChat UI. EOS sidebar Python tools run from agent CDF config — do not vendor Pyodide. Triggers: Pyodide, pythonRuntime, usePyodideRuntime, runPythonCode.

Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows. Use when an agent needs to install, verify, troubleshoot, configure, or operate Open…

MUST be used when fixing Flows app performance — re-renders, query patterns, pagination, unbounded fetches, LLM-over-query-results, bundles, memory leaks. Measure before and after. Triggers: performance, slow, laggy, op…

Scaffolds an AtlasTool for an already-approved in-app useAtlasChat UI. For EOS sidebar tools, use integrate-fusion-agent (createAgentAction) instead. Triggers: AtlasTool, useAtlasChat tool, in-app atlas client tool.

哈耶克 × 米塞斯 × Claude 三人对话。奥派经济学视角的多角色讨论。 触发方式：/chatroom-austrian、/奥派、「奥派聊天室」 Austrian economics chatroom. Hayek × Mises × Claude debate. Trigger: /chatroom-austrian, /奥派, "Austrian chat"

De-slop pass for any text: detects and erases the statistical fingerprints of AI writing (negative parallelism / "not X but Y", em-dash abuse, rule-of-three, false ranges, puffery vocabulary, uniform cadence, hedged bot…

Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test.

Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment. Do NOT use for writing inference code, choosing models, or PhysicsNeMo questions.

Stage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest. NOT for scoring (use /digital-health-clinical-asr-eval).

Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety. Produces a Markdown policy, JSON taxonomy, and d…

Run a spec-driven agent loop where coding tasks live as markdown specs that move through inbox → active → archive, get implemented by Claude Code or Codex, and pass a review gate before they count as done. Use when the…

One-click contribution flow for OpenDesign (nexu-io/open-design) — even for non-coders. Pick one of four cards (ship a Skill or Design System you made with OD; translate docs; fix a typo / write a blog; report a bug), t…

Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.

Scaffold for assembling prediction-market strategies on Binance Agentic Wallet, for recurring BTC Up/Down rounds. Wires round enumeration, market screening, two-step ordering, fill and settlement confirmation and redemp…

Recommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and pretrain/SFT/PEFT goal. Use when selecting a starting recipe, comparing library and ben…

Give your agents capabilities through tools (function calling). Helps you identify what your agent needs to do, create tool definitions, and attach them to config variations.

No description provided.

Deploy and operate the RTVI-CV-3D microservice as MV3DT (`MODE=mv3dt`): per-camera DeepStream perception plus BEV Fusion over calibrated cameras. Supports the bundled sample dataset, custom video files, and RTSP streams…

Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute. Use for activation memory OOMs or regressions involving recompute_granularity, recompu…

Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism configuration.

Create and configure configs in LaunchDarkly. Helps you choose between agent vs completion mode, create the config, add variations with models and prompts, and verify the setup.

Validate and use packed sequences and long-context training in Megatron-Bridge, including offline LLM packing, collate-time VLM packing, Energon online packing, and CP constraints.

Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.

Configure config targeting rules to control which variations serve to different users. Enable percentage rollouts, attribute-based rules, segment targeting, and guarded rollouts.

Use this skill when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams, chat-completions, Kafka). Not for VSS profile deploy or video-search ingestion.

Experiment with configs by creating and managing variations. Helps you test different models, prompts, and parameters to find what works best through systematic experimentation.

Query the user's LLM Wiki knowledge base (the LLM Wiki desktop app at 127.0.0.1:19828 — NOT Obsidian, Notion, Apple Notes, Logseq, or any other PKM tool). Trigger ONLY when the user explicitly names LLM Wiki, says 'my w…

Adopt a typed .spec.ts for an existing hand-written CLAUDE.md — start from the file you already have, non-destructively

Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model shoul…

MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.

Attach judges to config variations for automatic LLM-as-a-judge evaluation. Create custom judges, configure sampling rates, and monitor quality scores.

Begin Build With AI: Basics, the Devpost learning hackathon. Checks you're in a fresh project folder, introduces flipped interaction, learns about your idea and background, and writes the learner profile that every late…

Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

Search and ask questions about coding agent session history across Claude Code, Codex, and Cursor. Use when asking what was worked on, what was tried before, how a problem was investigated across sessions, what happened…

Check if the compound-engineering plugin is up to date and recommend the update command if not. Use when the user says "update compound engineering", "check compound engineering version", "ce update", "is compound engin…

Instrument an existing codebase with LaunchDarkly config tracking. Walks the four-tier ladder (managed runner → provider package → custom extractor + trackMetricsOf → raw manual) and picks the lowest-ceremony option tha…

[BETA] Execute ce-work with external delegate support.

Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.

Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user want…

Create and manage prompt snippets — reusable text blocks referenced inside config variation prompts. Keeps common instructions, personas, and guardrails consistent across multiple configs.

百度 AI 搜索。支持网页搜索、百度百科、秒懂百科、AI 智能生成四种模式。自动包含当前日期上下文。当用户要求搜索信息、查询百科、获取最新资讯、搜索新闻、查找资料时使用。

Actors: The primitive for agent orchestration.

Create and manage agent graphs — directed graphs of configs connected by edges with handoff logic. Use when building multi-agent workflows where configs route to each other.

Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

Manage short-code bundles that authorize the local starchild CLI to talk to this agent, including the agent-shell local-exec channel and the local MCP proxy (stdio MCP servers on the user's machine). Use when connecting…

Agent harness performance system for Claude Code and other AI coding agents — skills, instincts, memory, hooks, commands, and security scanning

Push and publish custom AI models to Replicate, and set up CI/CD for releasing new model versions safely. Use when running cog push, deploying a model to Replicate, releasing a new version, validating a model with cog-s…

Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing expected results', or asks 'how to improv…