Kick off international expansion planning for a new country — gathers intake, runs EOR vs. entity framing, drafts cross-functional questions, surfaces country-specific flags, and creates a persistent tracker. Use when someone says "we're hiring in [country]", "expansion to [country]", or "first hire in [country]".

Build the material contracts disclosure schedule from diligence findings, applying the purchase agreement's Material Contract definition and formatting per the agreement's schedule format. Use when user says "build the contracts schedule", "disclosure schedule", "schedule 3.X", "material contracts list", or when drafting disclosure schedules.

Review a vendor agreement, NDA, or SaaS subscription against your playbook. Identifies the agreement structure from titles, routes to the right review skill (vendor-agreement-review, nda-review, saas-msa-review), and integrates the output into a single memo. Use when the user says "review this contract", "check this MSA", "is this NDA okay", "look at this SaaS agreement", or attaches an inbound agreement for review.

Show contracts with cancel-by deadlines coming up and warn before notice windows close, working from a maintained renewal register. Use when the user asks "what's renewing soon", "what renewals are due", "did we miss a cancellation window", "add this to the renewal tracker", or on a scheduled basis. Receives handoffs from saas-msa-review.

Draft a firm AI usage policy from published model policies, adapted to your practice profile — a research-and-synthesis tool whose output is a draft for attorney review and adoption, not a finished policy. Use when user says "draft an AI policy", "we need an AI policy", "build an AI usage policy", "our firm needs a GenAI policy", or similar requests to generate a first-cut internal AI policy.

Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.

Speak and transcribe through the user's local VoiceStudio — free, offline, no API key. Text-to-speech (including the user's cloned voices) and speech-to-text via the OpenAI-compatible API at localhost:3900.

Build or redesign polished browser-rendered visual artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use for visual front-end creation, design-system exploration, design critique, or explicit browser acceptance / QA of a web artifact. Not for back-end, CLI, non-visual coding, source-to-longform article conversion, or narration-driven click-through video presentations.

Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.

Detect and fix clang-format, clang-tidy, and copyright header violations in an OpenVINO C++ codebase. Use when the user complains about code style or formatting, asks to clean up changes, fix linting, add a copyright header, or when a style check or linting CI job is failing. Do not use for build errors, compilation failures, linker errors, test failures, runtime crashes, accuracy issues, or CMake config problems.

Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored to the LoRA's task and inputs (Union/multi-task control, edit, video, image, etc.), respecting model-card recommendations (trigger words, steps, guidance, LoRA scale, example inputs), and shipping to ZeroGPU hardware as a private Space by default.

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a paper or codebase into a structured, machine-executable knowledge package, building an ARA from scratch, or converting research outputs into a falsifiable, agent-traversable form.

Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.

Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn. Use when creating any figure for a conference paper.

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

How raw multimodal robot data maps onto the Rerun data model. Read FIRST, before modeling or converting a dataset — and whenever you are about to convert/ingest/preprocess robot data into an .rrd or build a Rerun recording, even if not asked for the data model. Resolves the entity-vs-component, property-vs-component-vs-layer, and static-vs-temporal decisions and routes to the mechanism (do it with readers and lenses, not hand-built chunks or per-message rr.log): rerun-chunk-processing and the importer skills rerun-mcap, rerun-urdf, rerun-parquet, rerun-mp4, rerun-lerobot.

Interactive guide for creating, reviewing, and improving agent skills (SKILL.md folders). Use when the user wants to build a new skill ('create a skill', 'make a skill for X', 'write a SKILL.md', 'turn this workflow into a skill'), review or improve an existing skill, fix a skill that never triggers or triggers too often, or validate a skill folder before sharing it. Do NOT use for general prompt writing, MCP server development, or editing arbitrary markdown files.

Use when the user wants strategy for one active deal, renewal, negotiation, buying process, or initial sales motion for an offer or product. Build a grounded deal map or practical sales plan with objections, sequencing, posture, and prioritized next actions. Use prepare-for-meeting instead for multi-account same-day customer call queues.