Loading...
Loading...
Found 172 Skills
This skill should be used for multi-session autonomous agent work requiring progress checkpointing, failure recovery, and task dependency management. Triggers on '/harness' command, or when a task involves many subtasks needing progress persistence, sleep/resume cycles across context windows, recovery from mid-task failures with partial state, or distributed work across multiple agent sessions. Synthesized from Anthropic and OpenAI engineering practices for long-running agents.
Eino orchestration with Graph, Chain, and Workflow. Use when a user needs to build multi-step pipelines, compose components into executable graphs, handle streaming between nodes, use branching or parallel execution, manage state with checkpoints, or understand the Runnable abstraction. Covers Graph (directed graph with cycles), Chain (linear sequential), and Workflow (DAG with field mapping).
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
Create an annotated Git tag to mark a project milestone, documenting achievements and next-phase plans. Use when completing a phase, releasing a version, or marking a research checkpoint with a structured summary.
Create and work with Meta SAM 3 (facebookresearch/sam3) for open-vocabulary image and video segmentation with text, point, box, and mask prompts. Use when setting up SAM3 environments, requesting Hugging Face checkpoint access, generating inference scripts, integrating SAM3 into Python apps, fine-tuning with sam3/train configs, running SA-Co or custom evaluations, or debugging CUDA/checkpoint/prompt pipeline issues.
Test-Driven Development workflow with session integration. Use when implementing features/bugfixes to enforce RED-GREEN-REFACTOR discipline. Integrates with session-management for enhanced TDD session tracking, checkpoints, and metrics.
Configure Lakebase for agent memory storage. Use when: (1) Adding memory capabilities to the agent, (2) 'Failed to connect to Lakebase' errors, (3) Permission errors on checkpoint/store tables, (4) User says 'lakebase', 'memory setup', or 'add memory'.
Pixel-perfect Figma to React conversion using coderio. Generates production-ready code (TypeScript, Vite, TailwindCSS V4) with high visual fidelity. Features robust error handling, checkpoint recovery, and streamlined execution via helper script.
This skill should be used when the user has a written implementation plan to execute in a separate session with review checkpoints.
Comprehensive paid media auditor who systematically evaluates Google Ads, Microsoft Ads, and Meta accounts across 200+ checkpoints spanning account structure, tracking, bidding, creative, audiences, and competitive positioning. Produces actionable audit reports with prioritized recommendations and projected impact.
This skill should be used when the user asks to "quantize a model", "run PTQ", "post-training quantization", "NVFP4 quantization", "FP8 quantization", "INT8 quantization", "INT4 AWQ", "quantize LLM", "quantize MoE", "quantize VLM", or needs to produce a quantized HuggingFace or TensorRT-LLM checkpoint from a pretrained model using ModelOpt.
Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted endpoints. Use when a request names a Nemotron step or workflow, or asks to clean, translate, train, fine-tune, align, convert, optimize, evaluate, or compose these into a pipeline. Do NOT use for frontend/dashboard/visualization work, generic ML advice, billing/access, or non-Nemotron coding tasks.