606건 · 관련도순
Design a lesson opening that activates prior knowledge and connects previous learning to today's content. Use when planning lesson starters, retrieval openers, or advance organisers.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Pattern for progressively refining context retrieval to solve the subagent context problem
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Designs multiscale chunking for RAG by embedding small units for retrieval precision and returning larger context for synthesis. Use when fixed-size chunks either lose surrounding context or dilute relevance in long documents, manuals, filings, or codebases. Covers sentence-window and parent-child or auto-merging strategies, base chunk sizing, and evaluation. Do not use when a single chunk scale already meets retrieval and generation needs.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Security-first SOP for multi-tenant RAG systems. Activate when a calling agent is building, reviewing, or debugging any retrieval pipeline whose vector store is shared across more than one user, organisation, workspace, customer, or permission scope. Encodes the single non-negotiable rule — **filter at the vector store query, never after retrieval / never after rerank** — together with the per-vendor query-time filter APIs (Pinecone namespaces + `$eq`/`$in`, Weaviate `multiTenancyConfig` + tenant handle, Qdrant `is_tenant` payload index + `Filter.must`, Chroma `where`, pgvector RLS), and the cross-framework adapters (LlamaIndex `MetadataFilters`, LangChain `filter=` dict). Frame the work as preventing CVE-2024-41892 / EchoLeak / Slack-AI-class cross-tenant leakage, not as "adding a filter for relevance".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Routes heterogeneous queries to the appropriate index, tool, or answering engine before retrieval. Use when one endpoint serves multiple handlers, such as summary, vector retrieval, text-to-SQL, or tools, and query types require different paths. Covers LLM, semantic, and rule-based routers, confidence thresholds, fallbacks, and framework mappings. Do not use when one handler serves all queries or branching is fixed.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Provides chunking strategies for RAG systems. Generates chunk size recommendations (256-1024 tokens), overlap percentages (10-20%), and semantic boundary detection methods. Validates semantic coherence and evaluates retrieval precision/recall metrics. Use when building retrieval-augmented generation systems, vector databases, or processing large documents.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Implements document chunking, embedding generation, vector storage, and retrieval pipelines for Retrieval-Augmented Generation systems. Use when building RAG applications, creating document Q&A systems, or integrating AI with knowledge bases.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use FlashRAG for retrieval-augmented generation research workflows: config/data validation, retrieval and index building, generation/refinement components, RAG pipelines/method reproduction, evaluation, and WebUI setup.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use ColBERT/colbert-ai for late-interaction retrieval: prepare data, inspect configs, train/fine-tune, index collections, search rankings, update indexes, serve search, evaluate MS MARCO/LoTTE outputs, or reason about Baleen multi-hop retrieval.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Implements document chunking, embedding generation, vector storage, and retrieval pipelines for Retrieval-Augmented Generation systems. Use when building RAG applications, creating document Q&A systems, or integrating AI with knowledge bases.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Rank an existing set of context chunks by relevance, diversity, freshness, and utility. Use when retrieval has already produced candidates that must be scored or reranked; use context-retrieval when the source corpus still needs to be searched.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Think and work like an expert Exoplanet Scientist. Use when a task calls for Exoplanet Scientist judgment. Reasons from Keplerian motion, transit and RV geometry, and degenerate retrieval spaces through TLS/BLS searches, centroid and odd-even vetting, RadVel and GP activity models, and petitRADTRANS retrievals while treating eclipsing-binary blends, stellar-rotation-mimicking RV signals, and look-elsewhere completeness cliffs as first-class failure modes.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Access UniProt for protein sequence and annotation retrieval. Use this skill when: (1) Looking up protein sequences by accession, (2) Finding functional annotations, (3) Getting domain boundaries, (4) Finding homologs and variants, (5) Cross-referencing to PDB structures. For structure retrieval, use pdb. For sequence design, use proteinmpnn.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build GraphRAG retrieval pipelines on Neo4j using the neo4j-graphrag Python package (v1.22.0+). Covers retriever selection (VectorRetriever, HybridRetriever, VectorCypherRetriever, HybridCypherRetriever, Text2CypherRetriever, ToolsRetriever), external vector DB retrievers (Weaviate, Pinecone, Qdrant), retrieval_query Cypher fragments, query_params, filters, GraphRAG pipeline wiring (GraphRAG + LLM + prompt), all LLM providers (OpenAI, Anthropic, Gemini/VertexAI, Bedrock, Cohere, Mistral, Ollama), embedder setup, index creation, token usage tracking, Cypher 25 SEARCH clause, and LangChain/LlamaIndex integration. Does NOT handle KG construction — use neo4j-document-import-skill. Does NOT handle plain vector search — use neo4j-vector-index-skill. Does NOT handle GDS analytics — use neo4j-gds-skill. Does NOT handle agent memory — use neo4j-agent-memory-skill.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Builds local-first note vault retrieval for Obsidian, markdown notebooks, and NotebookLM-adjacent exports. Use when packaging notes into LLM-ready context.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Batch query TikTok product detail data, including multi-period sales and GMV (1d/7d/15d/30d/60d/90d/cumulative), live sales and live GMV, promoting video and creator data, views, price, rating, review count, commission rate, and delisted/fully-managed status. Supports batch retrieval by product ID or TikTok Shop product URL. Trigger when users mention TikTok product detail, batch query TikTok products, TikTok product sales analysis, TikTok product GMV, TikTok live sales, TikTok influencer sales data, TikTok product price rating, batch get TikTok product info, Nexscope product detail, TikTok product detail, batch product lookup, TikTok sales analysis, TikTok GMV, TikTok live sales, TikTok influencer data. Even if the user does not explicitly mention "Nexscope", trigger this skill whenever their need involves batch retrieval of detailed TikTok product sales and marketing data by product ID or product URL.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Query patent simple bibliographic (catalog) data from the Nexscope patent database. Triggered when users mention patent bibliographic information queries, patent basic info retrieval, patent catalog data, patent publication details, searching by patent number for inventors, patent applicant information, patent abstract retrieval, patent classification codes (IPC/CPC), patent citation queries, or any request to search for structured metadata by patent ID or publication number, patent brief bibliography, patent basic info, patent number lookup, patent abstract, Nexscope, or patent metadata. Even if the user does not explicitly mention "Nexscope" or "bibliographic info," this skill should be triggered whenever their need involves querying core bibliographic fields of specific patents.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design a lesson opening that activates prior knowledge and connects previous learning to today's content. Use when planning lesson starters, retrieval openers, or advance organisers.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto frontier of quality vs cost — using native Agent / Workflow / loop tools instead of a standalone Python harness. Use this whenever the user wants to optimize, evolve, tune, distill, or search over a harness, scaffold, prompt system, memory or retrieval policy, context-assembly code, or summarizer while keeping the model fixed; whenever they mention Meta-Harness, harness optimization, scaffold evolution, automatic prompt/memory optimization, an evolutionary or Pareto search over candidate implementations, or "make the harness/agent better without retraining"; and whenever the gain must come from the code AROUND the model rather than the model weights. Reproduces the Meta-Harness paper's method natively, with no claude_wrapper.py and no metered solver API.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Expert guide for engineering and optimizing ultra-large context windows (2M+ tokens) across Gemini 4 Pro, Claude 5.5, and GPT Astra 6 — context partitioning, retrieval-augmented context injection, sliding window strategies, and cost-aware token budgeting / Panduan ahli rekayasa dan optimasi context window ultra-besar (2M+ token) di Gemini 4 Pro, Claude 5.5, dan GPT Astra 6 — partisi konteks, injeksi konteks berbasis retrieval, strategi sliding window, dan penganggaran token sadar-biaya.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Enhanced web search and real-time content retrieval via Grok API with forced tool routing. Use when: (1) Web search / information retrieval / fact-checking, (2) Webpage content extraction / URL parsing, (3) Breaking knowledge cutoff limits for current information, (4) Real-time news and technical documentation, (5) Multi-source information aggregation. Triggers: "search for", "find information about", "latest news", "current", "fetch webpage", "get content from URL". IMPORTANT: This skill REPLACES built-in WebSearch/WebFetch with Grok Search tools.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Pattern for progressively refining context retrieval to solve the subagent context problem
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.