Total 50,505 skills, AI & Machine Learning has 8478 skills
Showing 12 of 8478 skills
Reduce LLM API and infrastructure costs through model selection, prompt caching, batching, caching, quantization, and self-hosting strategies. Track spend by team and model, set budgets, and implement cost-aware routing.
Run isolated eval and grading calls using CC 2.1.81 --bare mode. Constructs claude -p --bare invocations for skill evaluation, trigger testing, and LLM grading without plugin/hook interference. Use when running eval pipelines, grading skill outputs, benchmarking prompt quality, or testing trigger accuracy in isolation.
Audit Codex/OpenClaw skills: loaded roots, duplicate skills, unused skills, prompt-budget costs, compact descriptions.
Current LLM prices. How to use the Narev API endpoints — list model pricing (GET) and calculate call cost (POST). Use when the user needs endpoint behavior, parameters, responses, or errors; real-time per-token rates; token-to-USD math for one call; or when they mention "Narev pricing", "model rates", "USD per token", "cost calculation", or "AI unit economics". For committing catalog snapshots or generator scripts, use update-llm-pricing.
Interactive QA session where users report bugs or issues through conversation, and the agent creates GitHub issues. Explore the codebase in the background to obtain context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".
Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform prompts.
Validate and use packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs, and applying the right CP constraints.
Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism configuration.
Generates blog post thumbnail images for Orbitant following the brand's visual identity, using Google's Imagen API (Nano Banana 2). Activates when creating blog images, generating thumbnails, designing featured images for articles, or when someone needs a visual for an Orbitant insight/blog post. Use this skill even if the user just says "I need an image for this article", "create a thumbnail", "generate a hero image", or "make a featured image". Also triggers when the user mentions "Nano Banana 2", "image generation", or asks for a prompt for an AI image tool.
Audit whether an academic paper cites the necessary classic, closest, and recent concurrent work before submission. Use this skill whenever the user worries that references are incomplete, wants missing citations found, needs related work coverage checked, asks whether a paper cites classic work or recent arXiv/OpenReview work, or wants a citation coverage report for ML/AI venues such as NeurIPS, ICML, ICLR, CVPR, ACL, EMNLP, or similar conferences.
Use when the user is starting a new project or feature, or mentions "concept", "roadmap", "feature", "spec", "plan", "idea", or "what to build". Walks them through three plain-English phases — Concept (what & why) → Roadmap (the path) → Features (the work) — producing one-page markdown artifacts under `specdriven/` that anchor every later turn. Skip when the task is already small and well-scoped (a rename, a one-line bug fix).
Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".