Results for “prefix-caching”

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augmented.

Searches a local-first memory index and returns the top matching entries with paths and headers.

Imported skill composite from langchain

Exploit web cache mechanisms to serve malicious content to other users by poisoning cached responses through unkeyed headers and parameters during authorized security tests.

Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.

Implements multi-level caching with strategies for invalidation, stampede prevention, and performance monitoring.

Caching strategies across the RAG stack. Semantic caching with GPTCache and LangChain, Redis-based embedding-similarity cache, cache key design, TTL/invalidation, partial caching (cache retrieval only), provider-native prompt caching (Anthropic, OpenAI), and hierarchical L1/L2 caches. USE WHEN: user mentions "semantic cache", "GPTCache", "LLM cache", "prompt caching", "Redis vector cache", "cache invalidation for RAG", "reduce LLM cost", "latency reduction LLM" DO NOT USE FOR: retrieval accuracy - use `rag-patterns`; groundedness checks - use `rag-guardrails`; incremental indexing - use `rag-production`

Manages vector embeddings with Pinecone for semantic search, recommendation, and RAG pipelines.

Search and retrieve past work from claude-mem's persistent cross-session memory database using a three-layer workflow: search, timeline, and fetch.

SUPERSEDED by persistent-cache-gap-filling (v2.8.0). Cache data during symbol selection for instant repeat runs.

Layer 0 of the keyword research pipeline. Builds a topic-graph snapshot for the brand's category before any seed work, approximated from Semrush phrase_related + phrase_questions on the category seeds plus the brand's own ranking footprint (domain_organic_unique). Idempotent on brand-config hash; never blocks the pipeline; cheap.

Locates files by name and searches file contents using the fd and ripgrep command-line tools.

Use when searching a local NCBI EDirect archive/postings index with Boolean, title, word, or pair queries inside the `x*` local-cache workflow.

cache-usage

Perform semantic search, find similar content, and conduct structured research using the Exa API.

Semantic search, similar content discovery, and structured research using Exa API

Vector-powered CLI for semantic file search with a Claude/Codex skill

Discover, profile, and evaluate MCP servers for a given domain or purpose. Use when searching for MCP servers to add to a project, comparing server capabilities, enriching the local registry cache, or evaluating whether a server suite covers a stated need. Covers cache-first discovery, remote registry scanning, deep server profiling, and gap analysis.

Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.

Multimodal Few-Shot Learning with Frozen Language Models

Locates files by intent using semantic search, ideal for finding implementations, definitions, or documentation in medium to large repositories.

Searches the web, legal databases, case law, patents, and case.dev knowledge base via the casedev CLI. Use when the user mentions "search", "legal research", "find cases", "case law", "patent search", "web search", "fetch URL", "webfetch", "legal skills", or needs to research legal topics, find similar cases, or retrieve web content.

Multi-tiered memory management (HOT/WARM/COLD) for context compaction. Invoke ONLY for explicit compaction events: post-`/compact` cleanup, MEMORY.md tier promotion, archive batch, or "trim my context". NOT for general recall (use deep-recall) or routine memory writes (use storage-router). Triggers: "compact memory", "promote to durable", "archive old context", "tier this".

Semantic-search personal knowledge (memory, plans, handoffs, skills, Codex rules) via the local RAG index at ~/.claude/rag-index/. Use when a query is fuzzy or cross-file ("how did we fix X", "what did we decide about Y", "which skill handles Z"). Complements grep (exact) and Serena (code symbols). If the user asks a recall question that doesn't map to a specific known file, reach here first.

GOF Proxy Pattern

Retrieve relevant information from a knowledge base using semantic, keyword, or hybrid search to ground a query. Use when the task starts with a corpus or index that must be searched; use context-ranking when candidate chunks already exist and only need ordering.

Build and debug Retrieval-Augmented Generation pipelines — chunking, embedding, retrieval, reranking

Systematically fuzz web applications for hidden content and input validation vulnerabilities across directories, files, parameters, and authentication bypasses.

Trigger: database schema, indexing, cache asidePattern, Redis caching, ORM models, Drizzle schema. Scope: Database query tuning, indexing, and data cache designs. Boundary: Excludes user identity validation.

Plan and execute hot-to-cold processkit context archiving while keeping archived entity metadata queryable through the shared index.

Semantic search, similar content discovery, and structured research using Exa API

SERP-based semantic topic clustering for content architecture planning. Groups keywords by actual Google SERP overlap (not text similarity), designs hub-and-spoke content clusters with internal link matrices, and generates interactive visualizations. Optionally executes content creation if claude-blog is installed. Use when user says "topic cluster", "content cluster", "semantic clustering", "pillar page", "hub and spoke", "content architecture", "keyword grouping", or "cluster plan".

SEO specialist for technical audits, keyword strategy, and GEO. Use when the user requests 'SEO', 'keyword research', 'schema markup', 'crawlability', 'pSEO', 'GEO', 'search rankings', or 'link building'.