Total 50,638 skills, AI & Machine Learning has 8488 skills
Showing 12 of 8488 skills
Internal guidance for composing prompts that Pi runs (DeepSeek by default) handle reliably for coding, review, diagnosis, and research tasks
Agent Design Consultant and Review Tool. Based on 12-Factor AgentOps best practices, it is used for: (1) Discussing Agent architecture design solutions; (2) Reviewing the design of existing Agents/Skills/workflows, identifying issues, and providing improvement suggestions. Trigger phrases: Review my agent, Help me analyze this skill, Agent design, Agent optimization, Help me review this workflow, What's wrong with this agent, How to design an agent, Agent architecture consultation.
Literature Scout — Responsible for multi-source literature retrieval, screening, and classification, and constructing literature matrices. Activated when assigned by research supervisors to collect literature. Conduct systematic literature retrieval using tools such as Exa, ArXiv API, Semantic Scholar, etc.
Use this skill when the user wants to analyze Claude token usage, understand Claude API spending, check cache hit rates, review Claude Code workflow patterns (skills, agents, hooks), or get cost optimization recommendations.
Update LLM prices in the repo: Use this skill to snapshot live LLM pricing into a checked-in file so billing or cost math can run offline with deterministic rates. Use for any language or stack (TypeScript, Python, Go, JSON registries, etc.) — not only typescript. Use when the user wants pinned prices, wants to remove a runtime dependency on the Narev API, wants to refresh a committed pricing file, or mentions "snapshot pricing", "freeze prices", "pin model rates", "regenerate pricing file", "update pricing in the repo", or "sync token pricing from Narev".
Google Dialogflow integration. Manage data, records, and automate workflows. Use when the user wants to interact with Google Dialogflow data.
Orchestrate audio team: audio-director + sound-designer + technical-artist + gameplay-programmer for full audio pipeline from direction to implementation.
Autonomous research agent that reads RESEARCH.md, infers what's needed, dynamically adjusts TODOs, and delegates to the right skill. Supports opt-in BFS mode for autonomous design space search. Respects a configurable supervision policy (presets: manual / checkpointed / autonomous / wild) governing notifications, approval gates, resource limits, and idea-change handling. Proactively surfaces gaps and asks before acting. Trigger phrases: "start research", "continue project", "what's next?", "explore design space", "autoresearch".
Runs ML experiments reproducibly — single runs or autonomous BFS batches. Single mode: isolated venv, time-budgeted, failure-handled, logs to RESEARCH.md. BFS mode (opt-in): designs N hypotheses, runs each for a fixed budget, compares via a single verifiable metric, keeps improvements and git-resets failures — fully autonomous until done. Respects the RESEARCH.md supervision policy for notifications, approvals, and stop limits. Trigger phrases: "run experiment", "train model", "explore design space", "find best config", "autoresearch".
Configure the project's supervision policy in RESEARCH.md. Uses a preset-first flow (`manual`, `checkpointed`, `autonomous`, `wild`), then lets the user adjust notification events, approval gates, stop limits, resource rules, and idea-change handling. Trigger phrases: "configure supervision", "set supervision", "automation settings", "change autonomy", "/supervision".
Run an autonomous Humanize-governed vLLM SOTA performance loop for one LLM model: first perform the fixed fair vLLM/SGLang/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches vLLM code, optionally uses ncu-report-skill for kernel evidence, and revalidates until vLLM matches or beats the best observed framework under the same workload and SLA.
使用 parallel sub-agents 为 module 生成多个 radically different interface designs。Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".