knowledge-fetch
CommunityRecall key knowledge across four memory layers.
Software Engineering#semantic search#agent memory#context injection#prompt workflow#consistency checks#knowledge recall#configuration layers
Authorcuipengfei
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Helps you avoid repeating mistakes or forgetting preferences by recalling relevant knowledge from a structured four-layer memory (user config, project root config, submodule config, and situational memory) and injecting it back into the current conversation.
Core Features & Use Cases
- Four-layer knowledge retrieval: Searches user-level configuration, project-level configuration, submodule-level configuration, and situational memory, grouped and presented by layer.
- Scenario-aware behavior: Detects whether the user is frustrated, performing a normal lookup, or requesting a refresh, then adjusts the opening and result formatting accordingly.
- Mandatory backend probing: First detects which storage backends/tools are available, then queries only what exists, with graceful handling when a layer or backend is unavailable.
- Consistency guardrail: If the same topic appears in multiple layers, it explicitly flags the inconsistency and reminds you to clean up rather than silently choosing one source.
Quick Start
Ask an AI agent to recall what it learned about your current topic by writing: " /recall 代码风格 ".
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: knowledge-fetch Download link: https://github.com/cuipengfei/prompts/archive/main.zip#knowledge-fetch Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.