Machine learning

Multi-source ML dataset discovery.

Comprehensive book editing system with RAG memory for Hermes.

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based…

Generate the canonical AI Runtime handoff at migrate/output/air_workload from an approved TRL template.

代码仓库智能问答工具（repo_symbol_answer v1）。Tree-sitter AST 召回 function/class/method/interface/variable 定义 + ripgrep 词法搜索 + reranker 精排 + palette:mid LLM 综合，输出含…

LightGBM Trading System — 98 features in 5 decorrelated groups, stacking ensemble of 5 specialized LightGBM models + meta-model, producing a 0-100 score.

Audits whether website content has clear, bounded, retrieval-friendly structural units for AI retrieval and answer generation.

Extract features, API contracts, and design system from React Native / Expo source code.

跨家 LLM 顾问 panel——给一个最小化 scenario，并行 dispatch 给 3-5 个不同 vendor 的模型，每个模型同时跑联网+离线两份，对抗单家族 prior 高度相关导致的 anchoring 偏差。用于复杂诊断、重要技术决策、自己推理 ≥2 小时未收敛兜底。

Core compilation algorithm for the LLM Wiki Compiler.

Use when Codex needs multi-source academic literature retrieval across OpenAlex, PubMed, Semantic Scholar, and arXiv; combines search results into one…

Take a visual anchor (chassis tokens + page list) and produce a reviewable hi-fi prototype wave in ONE shot — a master gallery `index.html` plus one…

Use when | Pipeline para integrar documentos de OnlyOffice con el sistema RAG de KAI.

Review a GitHub pull request chunk-by-chunk with inference-driven findings (security, correctness, performance, etc.), persisted per review and browsable as a…

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity…

Run prompts against a local LLM backend (LM Studio, Ollama, or MLX) with privacy-preserving output guardrails — drop reasoning_content, enforce structured…

LangChain / LangGraph engineering pitfalls and verified fixes.

Karpathy LLM Wiki 패턴 — 임의의 정보 소스(웹 글, PDF, 팟캐스트, 책, 슬랙 스레드, 이미지/OCR, 음성 메모, 영상, 코드 리포, 구조화 노트)를 build-time 합성하는 개인용 위키.

Analyzes site renderability and discoverability for LLM web crawlers.

Query Indian Constitution articles and BNS 2023 (Bharatiya Nyaya Sanhita) criminal law sections using RAG with semantic search.

Shared GPT + classifier inference gateway for persona monitor tasks.

Pharmaceutical machine-learning workflow guide for library profiling, molecular featurization, benchmark dataset fetch, medicinal-chemistry filtering, and…

Statistical modeling workflow guide for hypothesis tests, effect-size reporting, statsmodels regression, diagnostics, and structured result export.

Retired compatibility skill for the former agent-side UC model-materialization workflow.