Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Add a new business memory kind end-to-end. Pick the storage combination (Markdown / SQLite / LanceDB), pick the markdown strategy (daily-log / skill-named / single-file), then wire up the schema(s), repo(s), and writer(s).

Validate whether an analysis is accurate, well-supported, and ready to share or use for a decision. Use when reviewing methodology, calculations, comparisons, visuals, caveats, or conclusions.

Validate whether an analysis is accurate, well-supported, and ready to share or use for a decision. Use when reviewing methodology, calculations, comparisons, visuals, caveats, or conclusions.

Understand and customize the local Trellis architecture inside a user project. Use when modifying .trellis plus platform hooks, settings, agents, skills, commands, prompts, workflows, the channel runtime (trellis channel), bundled runtime agents under .trellis/agents/, selectable workflow templates, registry-backed spec refresh, cross-session memory (trellis mem) generated by trellis init, or AI-facing bundled skills (trellis-channel, trellis-session-insight, trellis-spec-bootstrap) and bundled-skill auto-dispatch flow.

Develop and test Screenpipe Windows-native changes on a disposable Azure VM created from the prepared Screenpipe Windows dev image. Use for Windows compiler, process, service, local API, desktop, capture, installer, or permission behavior. Do not use for React-only work proved by the browser mock.

Reorganize NemoClaw documentation pages, navigation, or content ownership while preserving published routes. Use for structural documentation refactors.

Comprehensive citation management for academic research. Search OpenAlex, PubMed, and Google Scholar for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

Use when preparing, tagging, and publishing an apps/cli npm release. Guides changelog drafting, apps/cli/package.json version bumps, cli-vX.Y.Z tags, local npm publishing, and the publish-cli GitHub workflow.

Model oil or gas supply shock exposure for a country and chokepoint. Use when the user asks how an energy disruption could affect fuel supply, strategic cover, or product deficits.

Use when you need to generate an onboarding guide for new team members joining a project

Storybook's workflow for UI changes in a project with Storybook - look up the components to reuse, write and update stories, run story tests, and publish a review of the result. Also shows existing components or stories in a review. Use when the project's agent instructions (such as AGENTS.md) or the user ask for it.

Use after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profiles, benchmarking matrix, white-space analysis, strategic recommendations, and team alignment trigger questions. Final step in the three-skill competitive pipeline.

Trace downstream data lineage and impact analysis. Use when the user asks what depends on this data, what breaks if something changes, downstream dependencies, or needs to assess change risk before modifying a table or DAG.

Run a dbt Fusion project with Astronomer Cosmos. Use when running a dbt Fusion project with Astronomer Cosmos (Cosmos 1.11+, ExecutionMode.LOCAL on Snowflake/Databricks). Before implementing, verify dbt engine is Fusion (not Core), the warehouse is supported, and local execution is acceptable. Does not cover dbt Core.

Review Excalidraw editor changes for scene graph, history, and undo/redo integrity. Use as one lens in a code review run.

Review source-code vulnerability fixes for whether they address the validated root cause without hiding evidence, removing intended demo behavior, or weakening regression coverage. Use as one lens in a code review run.

Review dependency, lockfile, and bundled-asset changes for compatibility, provenance, advisory relevance, and consistency with the runtime. Use as one lens in a code review run.