Skill catalog

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.

Internal command support for dynamic Rust crate skill management. Use only when explicitly invoked by /sync-crate-skills, /clean-crate-skills, or /update-crate-skill.

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

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.

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…

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

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.

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.

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

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…

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.

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

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…

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

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

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…

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

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.

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。

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

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…

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…

Create agent skills for Microsoft technologies using official documentation. Use whenever the user wants to build, generate, or scaffold a skill for any Microsoft technology (Azure, .NET, M365, VS Code, Bicep, etc.)—eve…

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

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

Install, configure, and operate MemPalace, including a private local palace, a shared-brain hub, or a client joining an existing hub. Use for first-time setup, MCP wiring, mining, status, palace audit and repair, wings,…

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…

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…

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

10 C-level advisory agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. CEO, CTO, COO, CPO, CMO, CFO, CRO, CISO, CHRO, Executive Mentor. Multi-role board meetings, strategy routing, structured…

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…

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

一本书 → 一幅清晰的「取景框」意向画面 → 一张 2050 图书馆借书卡（PNG）。取景框 = 作者从哪个角度看什么问题、看到了哪幅画面；卡上有真实封面、作者头像、书目信息。取景框 block 用费曼式讲解把这幅意向画面讲得通俗又准确；图解 block 用 AI 生图把这幅画面画出来，继刚是固定主角（从其墨像参考生成、认得出的他）。图解风格：吉田诚治式绘本感（异世界日常空间、暖光斜射、治愈又精致）。浅色光学玻璃卡身、强调色从封面动态…

Reference for the standalone Astrale CLI (`astrale`) - setup, graph reads and mutations, kernel calls, instances, domains, identities, delegation, journals, views, output, debugging, and local storage.

Review a GitHub pull request using Alan's GitHub MCP tools

P7 Senior Engineer mode — solution-driven execution under P8 supervision. Use when user says 'P7模式', '方案驱动', or when spawned as sub-task executor by P8. Produces: implementation plan + code + 3-question self-review, del…

Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. Use when running nemo-rl-auto-research c…

Resolve `/flag` style requests into the right LaunchDarkly flag lookup flow. Use when the user types `/flag`, asks to quickly find a flag by name/key, wants a direct flag detail summary, or needs fast disambiguation bet…

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…

人間がどう読み、どう考え、何を察するかを AI が前提として持つために読む。人間が読む文章を書くとき、ユーザーの判断を仰ぐとき、ユーザーの指摘の意図を読み取るときに使う。

Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved b…

Benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use when the user runs /agent-eval or asks to test, benchmark, audit, or validate a codegraph version (the…

Actors: The primitive for agent orchestration.

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…

Connects AI agents to remote Windows desktop applications on Amazon WorkSpaces Applications (AppStream 2.0) through the managed Agent Access MCP server, and guides reliable desktop automation. Covers connecting an agent…

Evaluate models, datasets, and agents with the NeMo Evaluator plugin. Use for metric selection, SDK checks, platform jobs, and result retrieval.

Debug LLM applications using the Phoenix CLI (`px`, from @arizeai/phoenix-cli). Fetch traces, spans, and sessions, annotate them, analyze errors, measure how often a failure or pattern occurs across traces, inspect data…

Show how much context window context-mode saved this session. Displays token consumption, context savings ratio, and per-tool breakdown. Read-only — shows stats only, no reset capability. To wipe the knowledge base enti…