Machine learning

Use this skill when you need evidence-bounded repeat inputs, version/model/prompt factors, invariants, variance evidence, and comparison boundaries; triggers…

Use this skill when you need evidence-bounded claim-to-source relations, unsupported assertions, abstention, uncertainty, and evidence review; triggers…

Use this skill when you need evidence-bounded grounding, relevance, completeness, citation support, abstention, and answer-level evidence in RAG outputs…

Use this skill when you need evidence-bounded query variants, chunking, filters, recall/precision proxies, ranking, freshness, and retrieval evidence…

결과를 숨긴 "블라인드" LLM 평가 패킷(사후 판단 편향 통제)은 두 방향으로 동시에 실패한다.

Cloud + LLM spend audit, right-sizing, unit economics.

Curate generated images into a clean training dataset, validate metadata, remove duplicates, and sync manifests/assets to Hugging Face.

给定 PMID / PMCID 取结构化全文（BioC XML/JSON）。封装 NLM BioC PubMed API（标题+摘要）和 BioC PMC OA API（开放获取全文），输出按章节切分的段落、表格上下文、RAG 友好 chunk。适合大批量入向量库。触发词：全文抽取 / BioC / RAG 入库…

Apply the DSG ONE / ProofGate truth boundary and claim policy.

Use for any LLM labeling and structured data extraction from unstructured text.

Use to stream model output, render tool results or let the LLM pick UI ("UI generativa", "chat com streaming"): provider adapters, SSE/Fetch, stop/regenerate…

Full-stack diagnostic for agent and LLM

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection…

Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics.

Elite bioinformatics scientist specializing in genomic data analysis, NGS pipeline development, variant calling, transcriptomics, and precision medicine.

AI-powered design review for Figma components with weighted dual-scoring system.

Audit a codebase for LLM calls that are really classifications in disguise, then produce a costed swap plan for a System One model.

Wire a System One model (Jev, or an open reproduction like Von) into a product feature — routing, guardrails, scoring, classification.

Data Scientist role within the AID methodology.

Chat / code generation via tproxy using OpenAI /v1/chat/completions, Anthropic /v1/messages, or OpenAI Responses.

Use the InfiniSynapse CLI (`agent_infini`) for multi-turn AI data-analysis tasks, database/RAG context, and task workspace files.

Behavioral guidelines to reduce common LLM coding mistakes.

Benchmark and compare system prompt variants (V2/V2a/V2b/V2c) for Sheets Chat by running test scenarios through the real GAS-side ClaudeConversation pipeline.

Run and measure local AI on a Talos GPU worker: storage off the node disk, one GPU app at a time, thermal profile per card, power limits from a privileged…