skills.rest
cuipengfei
cuipengfeiCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

knowledge-fetch

Retrieve historical knowledge from four layered memory stores with grouped results.

8|2|Updated Oct 29, 2025
Search Tags:#semantic search#agent memory#context injection#prompt workflow#consistency checks#knowledge recall#configuration layers
One-click install
npx skills add https://github.com/cuipengfei/prompts --skill knowledge-fetch
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: knowledge-fetch
Source: https://github.com/cuipengfei/prompts/tree/main/plugins/session-learn/skills/knowledge-fetch
Command: npx skills add https://github.com/cuipengfei/prompts --skill knowledge-fetch

SYSTEM DOCUMENTATION & REQUIREMENTS

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 ".

Frequently Asked Questions about knowledge-fetch

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

FAQPage Schema
How do I recall agent memory and past preferences during an AI conversation?▼

Agent memory recall works by querying four layered stores—user config, project root config, submodule config, and situational memory—then grouping and injecting relevant historical knowledge directly into your current conversation.

How do I retrieve project configuration and situational context when chat context becomes stale?▼

Retrieving project configuration and situational context involves probing available backend storage layers, matching keywords layer by layer, and returning grouped results to refresh stale chat context.

What happens if the same knowledge appears in multiple configuration layers during semantic search?▼

Semantic search flags the inconsistency explicitly when the same topic appears across multiple configuration layers, reminding you to clean up conflicting sources rather than silently choosing one.

How does agent memory retrieval adapt when a situational memory backend is unavailable?▼

Agent memory retrieval requires mandatory backend probing first, querying only existing layers, and provides graceful handling with clear behavior when a layer or situational memory backend is unavailable.

Can I use semantic search to recall knowledge when I am frustrated with repeated mistakes?▼

Semantic search detects frustration-driven scenarios and adjusts its opening and result formatting accordingly, retrieving relevant historical knowledge to help you avoid repeating mistakes or forgetting preferences.

What is the best way to structure knowledge recall for prompt workflow consistency checks?▼

Knowledge recall for prompt workflow consistency uses a four-layer memory structure with consistent source labeling across layers, ensuring retrieved context is grouped and ready for immediate reuse.

Related Skills

Explore More Software Engineering Skills→
cuipengfeicuipengfei
8

auto-extract

Extracts learning signals from chat sessions and persists them to configuration files.

Community
Advanced
starlink-awakenstarlink-awaken

compliant-position

Prioritize internal gbrain knowledge base queries before external web searches.

Community
Basic
23blocks-OS23blocks-OS
744

AI Maestro Memory Search

Retrieve prior discussions and decisions via memory-search.sh before starting new tasks.

Official
Advanced
zenbase-aizenbase-ai
10

skill-retrieval

Index and retrieve skills via ColBERT semantic search.

Official
Advanced