Total 53,555 skills, AI & Machine Learning has 8922 skills
Showing 12 of 8922 skills
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.
Iterate on RAG systems with structured evals instead of eyeballing. This skill should be used when the user is tuning a RAG pipeline — changing retrieval prompts, swapping models, adjusting chunking, or debugging poor answers — and wants a cheap, ranked set of experiments with cost tracking and structured feedback on the stack. Also use when the user asks "how do I know if my RAG is working?", "this RAG eval is burning money", or "what should I try next on retrieval?".
Route content to specialized ingestion skills. Detects input type and delegates.
Manage customer support — track tickets, respond, escalate issues.
Skeleton-intelligent revenue strategy for AI automation agencies. Frames proposals through monetization lenses across all UI types — dashboards, product pages, and admin panels. Knows the full skeleton catalog, SaaS wrapper productization flow, and enrichment boundaries. Active in propose phase only. Max 1-2 questions, plain language, agency-native vocabulary.
OpenRouter integration. Manage data, records, and automate workflows. Use when the user wants to interact with OpenRouter data.
Generate setup scripts/configs for AI agent worktrees and isolated environments across Cursor, Codex, and Conductor. Use when wiring up a project so AI agents start with the same dependencies, env files, and tool configs as the main repo.
Use when a Luma / 拾光 / 拾光智能体 / 拾光工具 agent needs to inspect local material libraries, describe material groups, upload or understand materials, search candidates, or prepare PIP matching inputs.
Overcome LLM knowledge cutoffs with real-time developer content. daily.dev aggregates articles from thousands of sources, validated by community engagement, with structured taxonomy for precise discovery.
Convert a photo of a person into a custom 3D action figure, complete with collectible toy packaging.
Publish or fetch learned patterns across projects via IPFS (Pinata) -- the cross-project pattern transfer that hooks_transfer enables
Use when agent instruction files (AGENTS.md, rules/) need analysis, trimming, or restructuring. Orchestrates /imperatives → /policy-algebra → /visualize into a distillation pipeline.