skills.rest
d-o-hub
d-o-hubCOMMUNITY
Explore all skills by this author →
GitHub

context-retrieval

Retrieve relevant episodic context from memory using semantic or SQL-based search.

11|Updated Nov 5, 2025
Search Tags:#embeddings#patterns#retrieval#memory#semantic-search#context-retrieval
One-click install
npx skills add https://github.com/d-o-hub/rust-self-learning-memory --skill context-retrieval
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: context-retrieval
Source: https://github.com/d-o-hub/rust-self-learning-memory/tree/main/.claude/skills/context-retrieval
Command: npx skills add https://github.com/d-o-hub/rust-self-learning-memory --skill context-retrieval

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Retrieve relevant episodic context from memory for informed decision-making. This Skill helps you access past episodes, patterns, and solutions to similar tasks, saving time and avoiding reinventing the wheel.

Core Features & Use Cases

  • Semantic Search (Preferred): When an embedding service is configured, retrieve context via vector similarity to find semantically similar tasks.
  • Keyword/Index Search (Fallback): If embeddings are unavailable, fall back to SQL-like indexing for fast, deterministic results.
  • Use Case: Quickly gather prior implementations and patterns for a current task to accelerate delivery and reduce risk.

Quick Start

Use the context-retrieval skill to fetch the most relevant past episodes for the task "implement async batch updates" and provide a concise context briefing to inform the current work.

Frequently Asked Questions about context-retrieval

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I retrieve relevant past episodes from memory to inform current decisions?▼

Context retrieval fetches semantically similar tasks and solutions from memory using embeddings or keyword search, ranking results by relevance to accelerate decision-making and reduce duplicate work.

When should I use semantic search versus keyword-based retrieval for context?▼

Use semantic search with embeddings when available to find conceptually similar tasks; fall back to SQL-based keyword indexing when embeddings are unavailable for deterministic, fast results.

What types of patterns and episodes can context retrieval extract from memory?▼

Context retrieval surfaces past episodes, implementation patterns, solutions to similar tasks, reusable tool sequences, and heuristics formatted with relevance scores to support decision-making across debugging, batch processing, and tool composition.

Can I use context retrieval without an embedding service?▼

Yes, context retrieval automatically falls back to SQL-like index-based search when embeddings are unavailable, filtering and ranking results by relevance or recency to return structured context.

How does context retrieval format and rank the results it returns?▼

Results are formatted into a standardized RetrievedContext structure containing episodes, patterns, heuristics, and relevance scores, ranked by semantic similarity or recency depending on the search method.

What output structure should I expect from context retrieval?▼

Context retrieval outputs a RetrievedContext object with ranked episodes, extracted patterns, applicable heuristics, and relevance scores ready for downstream decision logic or task implementation.

Related Skills

Explore More Data & Analytics Skills→
rizaldiemrizaldiem

langchain4j-vector-stores-configuration

Configure LangChain4J vector stores for embedding storage and semantic search.

Community
Advanced
c-dalyc-daly

distill

Distill episodic session learnings from EPISODES.md into persistent memory patterns in MEMORY.md.

Community
Intermediate
markus41markus41
1

vectordb

Manage vector embeddings for semantic search across Pinecone, Weaviate, Chroma, and pgvector.

Community
Intermediate
tiankong0101-bytetiankong0101-byte

openviking

Retrieve relevant stored content using hybrid semantic and keyword search.

Community
Advanced