Verhandlungsstrategie und Battlecards für SPA, APA, Term Sheet, W&I, CPs und Disclosure: erstellt Position, Fallbacks, rote Linien, Gegenargumente und Formulierungsvorschlaege:…
Generates a strategic negotiation support document with leverage analysis, BATNA assessment, risk matrix, and issue-by-issue tactical planning.
In-person negotiation skills and barter/trade techniques. Use when someone needs to negotiate a price, hire a contractor, dispute a bill, buy or sell used goods, or wants to trade…
Geschäftsführung ohne Auftrag (negotiorum gestio) im ALR. Skill behandelt ALR I 13 §§ 207-251 zur GoA das Verhältnis zur roemischen actio negotiorum gestorum die…
Römisches Recht: Negotiorum gestio (Geschäftsführung ohne Auftrag) nach D. 3.5 und Iust. Inst. 3.27 - utiliter gestum, actio negotiorum gestorum directa/contraria und…
Handle a neighbor conflict — noise, boundaries, parking, shared costs, pets — with a measured approach that de-escalates first and keeps a paper trail if it has to go formal.
Use when after library-matching has produced ranked candidate spectra with MS2Deepscore embeddings.
Use when targeting The New England Journal of Medicine (NEJM) or deciding whether a clinical medicine manuscript fits this venue.
Use to write the NEJM structured abstract — four headed sections (Background, Methods, Results, Conclusions), ≤250 words, with the trial registration number and funding source,…
Use to convert references to NEJM's Vancouver / ICMJE numbered style — numbered in order of appearance, limited author lists then et al., NLM journal abbreviations, and a capped…
NEJM figure preparation: resolution (300-1200 DPI), editable vector formats (AI/EPS/SVG), in-house medical illustration policy, and strict image integrity requirements.
Use to build NEJM clinical display items correctly — Table 1 baseline characteristics by group (with standardized differences, not P values), Kaplan-Meier curves with…
Use first, before any writing, to stress-test whether a clinical study clears NEJM's bar — practice-changing clinical impact, methodological rigor, and generalizability.
Use to select and enforce the correct EQUATOR reporting guideline for a clinical study — CONSORT for RCTs (with the participant flow diagram), STROBE for observational, PRISMA for…
Use when deciding which nejm-* sub-skill to invoke next, or when sequencing a clinical manuscript from significance test through response to reviewers for The New England Journal…
Nemo orchestrator for universal knowledge work where Codex plans the task, Nemo tools execute the work, and results are returned in structured form.
Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic d — from…
Maintain the NeMo Curator Fern docs site — add, update, move, or remove pages under fern/. Use for any documentation changes.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic d — from…
Build, migrate, review, and maintain third-party NVIDIA NeMo Fabric adapters against the public adapter contract.
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxi — from…
Maintain the NeMo Gym Fern docs site — add, update, move, or remove pages under fern/. Use for any documentation change.
Use when creating, validating, or documenting Nemo Gym pivot datasets from rollout, trajectory, chat-completion, Responses API, or tool-call artifacts.
Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute. — from NVIDIA/skills
Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.
Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex dispatcher backen — from…
Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. — from NVIDIA/skills
Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. — from NVIDIA/skills
Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM f — from…
MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling. — from NVIDIA/skills
Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage.
Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning stacks.
Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper.
Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism config — from…
Validate and use packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs, and applying th — from…
Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. — from NVIDIA/skills
Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library recipes (pretrain/SFT/PEFT) and performance recipes.
Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine. — from NVIDIA/skills
Run the Nemotron-3 Ultra Text2SQL LoRA fine-tuning tutorial (NeMo Megatron-Bridge) end-to-end for the user on their SLURM cluster: data prep, distributed checkpoint conversion,…
Use when the user wants to search, query, extract, transcribe, describe, quote, filter, or aggregate across documents — PDFs, scanned forms / images (`.jpg` `.png` `.tiff`),…
Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work,…
Create GitHub pull requests that follow the NemoClaw PR template. Use when the user wants to create a new PR, submit code for review, open a pull request, or push changes for…
Scan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages and refresh generated user skills for release…
Scans other open issues to find ones a given PR may also fix or accidentally break. Outputs adjacent-fix opportunities and contradiction risks with file:line evidence.
Runs the end-of-day maintainer handoff for NemoClaw. Checks version target progress, bumps stragglers to the next patch version, generates a QA handoff summary, and cuts the…
Runs the morning maintainer standup for NemoClaw. Triages the backlog, determines the day's target version, labels selected items, surfaces stragglers from previous versions, and…
Normalizes GitHub issue and PR titles by removing any bracketed [NemoClaw] tag case-insensitively, even when the tag appears later in the title.
Compares competing PRs that target the same issue and recommends which one to merge. Runs gate, correctness, and quality checks; outputs a deterministic scorecard with reasoning…
AI-assisted label triage for NVIDIA/NemoClaw issues and PRs. Reads triage-instructions.md at runtime for consistent label guidance.
Start here. Introduces what NemoClaw is, what agent skills are available, and which skill to use for a given task.
Connects NemoClaw to a local inference server. Use when setting up Ollama, vLLM, TensorRT-LLM, NIM, or any OpenAI-compatible local model server with NemoClaw.
Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form.
Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint access.
Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential reset, rebuilds,…
Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when to prefer NemoClaw…
Onboard a new model family (Nemotron or third-party) into skills/ — paper chunks, recipe summaries, context packs, and model card.