数据与 AI技能

Structured idea generation + multi-LLM debate for the product-owner stage. Diverge (generate genuinely different bets), debate (a 4-persona panel on 4 models argues over 2 rounds), converge (synthesize a recommendation). Used by product-owner before architect; available to architect for design-space exploration.

中文简介正在准备中。当前显示原文说明。

Forget data stored in Cognee memory. Use when the user asks to forget, delete, or remove something from memory (e.g. "forget what we talked about tennis", "delete that from memory"). Finds the documents in the current dataset whose raw content matches what the user wants forgotten and deletes them.

中文简介正在准备中。当前显示原文说明。

Store data permanently in the Cognee knowledge graph. Accepts a data category (user, project, or agent) to tag the data with the correct node_set for filtered retrieval.

中文简介正在准备中。当前显示原文说明。

Search Cognee memory. Session memory is automatically searched on every prompt via hooks. Use this skill explicitly for permanent knowledge graph search, filtered category search, or when you need more results than the automatic lookup provides.

中文简介正在准备中。当前显示原文说明。

Applies production AI integration patterns for chat, structured output, guardrails, provider routing, and AI UX. Use when adding LLM-powered features to an application.

中文简介正在准备中。当前显示原文说明。

Designs product and site search for end users. Use when choosing search engines, indexing, reindexing, relevance tuning, facets, autocomplete, merchandising, or search analytics.

中文简介正在准备中。当前显示原文说明。

Proves protocols and agent workflows with TLA+, P, Alloy, Z3, Dafny, or Lean. Use when proving protocols correct, writing TLA+ specs, or verifying LLM proofs.

中文简介正在准备中。当前显示原文说明。

Tests whether data supports a claim: A/B significance, peeking, sample size, eval error bars, multiple comparisons. Use when deciding if results are significant.

中文简介正在准备中。当前显示原文说明。

Builds local-first note vault retrieval for Obsidian, markdown notebooks, and NotebookLM-adjacent exports. Use when packaging notes into LLM-ready context.

中文简介正在准备中。当前显示原文说明。

Evaluates neuromarketing studies and neural-data law. Use when judging EEG, fMRI, eye-tracking, or GSR ad study or vendor, or if signals are regulated neural data.

中文简介正在准备中。当前显示原文说明。

Designs lakehouse platforms across Iceberg, Delta, Hudi, and Paimon. Use when choosing catalogs, CDC paths, query engines, governance, or cost controls.

中文简介正在准备中。当前显示原文说明。

Chooses among AI/ML approaches: classical ML, LLM, RAG, fine-tuning, agents, embeddings, MoE or SSM. Use when picking or scaling an architecture, or self-host vs API.

中文简介正在准备中。当前显示原文说明。

Builds LLM pretraining corpora from Common Crawl: extract, filter, deduplicate, decontaminate, mix, synthesize. Use when curating or ablating a pretraining corpus or data pipeline.

中文简介正在准备中。当前显示原文说明。

Builds ML pipelines: EDA, features, leakage checks, evaluation. Use when doing data science or explaining fairness, privacy, speech, vision-language, or diffusion mechanics.

中文简介正在准备中。当前显示原文说明。

Builds and backtests demand and revenue forecasts: rolling-origin backtests, prediction intervals, reconciliation, zero-shot foundation models. Use when forecasting time series.

中文简介正在准备中。当前显示原文说明。

Designs operating models for AI in product teams. Use when planning platform ownership, provider strategy, data boundaries, evals, or sensitive-data controls.

中文简介正在准备中。当前显示原文说明。

Prompt engineering for production LLMs — structured outputs, evals, RAG, tool workflows, multimodal prompting, and safety. Use when designing, debugging, or shipping prompts.

中文简介正在准备中。当前显示原文说明。

Builds analytics engineering layers for metrics, contracts, and BI-ready models. Use when shaping dbt or SQLMesh marts, metric governance, lineage, or data quality.

中文简介正在准备中。当前显示原文说明。

Automates Metabase cards, dashboards, Remote Sync, embedding, tenants, and the Agent API/MCP server for AI workflows. Use when scripting, promoting, or embedding Metabase content.

中文简介正在准备中。当前显示原文说明。

Designs streaming platforms for Kafka, Flink, CDC, and lakehouse ingestion. Use when planning event backbones, CDC pipelines, schema governance, or real-time lakehouse delivery.

中文简介正在准备中。当前显示原文说明。

Builds multi-repo context hubs and compiled markdown knowledge maps. Use when profiling repo portfolios or assembling LLM-ready cross-repo knowledge bases.

中文简介正在准备中。当前显示原文说明。

Adapts LLMs: SFT dataset loss masking, LoRA and QLoRA, full FT vs PEFT, distillation, pruning, tokenizer fragmentation. Use when fine-tuning or compressing a model.

中文简介正在准备中。当前显示原文说明。

Creates reusable vector-brain implementations: repo, docs, compliance. Use when building pgvector SQL, manifests, ingest scripts. Not for context design (dev-context-engineering).

中文简介正在准备中。当前显示原文说明。

Designs RAG retrieval for LLM grounding: chunking, BM25+vector hybrid, reranking, GraphRAG. Use when adding embeddings to SQLite FTS5 search or running held-out retrieval eval.

中文简介正在准备中。当前显示原文说明。