Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Provides techniques for understanding a domain's concepts and boundaries. Identifies terminology conflicts and supplies the foundation for a product's conceptual model.
Represent a component's behavior as a state machine. Make states, events, and transitions explicit when many interacting states require exhaustive coverage.
Searches OpenAlex, PubMed, and Google Scholar for academic sources. Extracts and validates metadata, converts DOIs to BibTeX, and checks reference accuracy for scientific writing.
Provides techniques for discovering and prioritizing user needs, pains, and desires. Frames those findings as opportunities that feed product strategy.
Covers training runs in Megatron-LM and Megatron Bridge using mock or real datasets. Includes correlation testing, available recipes, and multi-GPU examples.
Compares FSDP and 3D-parallel approaches to MoE VLM training. Uses lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.
Manages VSS profiles including base, search, lvs, warehouse, and edge. Covers configuration and deployment through verification, debugging, and teardown; standalone microservices use separate deployment skills.
Compares Grafana Cloud k6 runs over time and calculates remaining headroom to thresholds. Identifies degrading metrics even when tests pass and can synthesize findings across all tests in a project.
Covers converting single-node scripts into sbatch jobs using srun-native or uv run torch.distributed approaches. Includes containers, NCCL timeouts, MoE memory sizing, and interactive allocations.
Covers layer-level activation offloading and fractional optimizer state offloading. Includes use of HybridDeviceOptimizer in Megatron Bridge.
Covers overlap_moe_expert_parallel_comm and delay_wgrad_compute. Includes flex dispatcher backends such as DeepEP and HybridEP.
Covers offline LLM packing, collate-time VLM packing, and Energon online packing. Includes validation and context-parallel constraints for packed sequences and long-context training.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name