Loading...
Loading...
Found 172 Skills
Sub-skill for environment and asset preparation in README-first AI repo reproduction. Use when the task is specifically to prepare a conservative conda-first environment, checkpoint and dataset path assumptions, cache location hints, and setup notes before any run on a README-documented repository. Do not use for repo scanning, full orchestration, paper interpretation, final run reporting, or generic environment setup that is not tied to a specific reproduction target.
Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with command, config, seed, log, checkpoint, status, and metric evidence written to standardized `train_outputs/`. Do not use for environment setup, exploratory sweeps, speculative idea implementation, or end-to-end orchestration.
Rigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching, with debug fixes clearly separated from research contributions. Do not use for broad refactoring, speculative adaptation, automatic exploratory patching, or general repository familiarization.
Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent.
Use when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
Coordinate a cross-functional star-team workflow (Product Manager, Principal Engineer, Backend, Frontend, QA/Security, DevOps) with mandatory architecture and code-review checkpoints. Use when a request needs end-to-end product delivery, multi-role collaboration, or explicit role-based outputs (PM/PE/Backend/Frontend/QA/DevOps), or when the user asks for "star team", "cross-functional", "full lifecycle", or "multi-role" planning.
Create and manage structured documentation — experiments, plans, findings, checkpoints, research, learnings. Config-driven, parallel-safe.
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 campaigns, experiments, training jobs, model or dataset downloads, shared cache-heavy commands, log-producing runs, checkpoint generation, W&B or Hugging Face authenticated workflows, or any workflow that may create large files on Brev.
Expert blueprint for racing games including vehicle physics (VehicleBody3D, suspension, friction), checkpoint systems (prevent shortcuts), rubber-banding AI (keep races competitive), drifting mechanics (reduce friction, boost on exit), camera feel (FOV increase with speed, motion blur), and UI (speedometer, lap timer, minimap). Use for arcade racers, kart racing, or realistic sims. Trigger keywords: racing_game, vehicle_physics, checkpoint_system, rubber_banding, drifting_mechanics, camera_feel.
MANDATORY prerequisite — invoke BEFORE any mcp__blockbench__* tool call that creates, modifies, or exports Blockbench content. Orchestrates the other blockbench-* skills (modeling, texturing, animation, PBR, Hytale, MCP overview). Trigger on: 3D model/texture/animation creation or edits in Blockbench; calls to mcp__blockbench__* tools; phrases like 'build a Minecraft model', 'paint a texture', 'animate this rig', 'export the model'. Dispatches to the right sub-skill(s), enforces pre-flight checks (project open, format, outline), wraps risky work in checkpoints, and ensures exports close the loop.
BAZDMEG Method workflow checkpoint system for AI-assisted development. Enforce quality gates at three phases: pre-code, post-code, and pre-PR. Use when: (1) starting a new feature or bug fix, (2) finishing AI-generated code before review, (3) preparing a pull request, (4) running a planning interview, (5) auditing automation readiness, (6) preventing AI slop, (7) session bootstrap, (8) source rank, (9) domain gates, (10) bugbook. Triggers: 'bazdmeg', 'pre-code checklist', 'post-code checklist', 'pre-PR checklist', 'planning interview', 'quality gates', 'session bootstrap', 'source rank', 'domain gates', 'bugbook'.