skills.rest
Signet-AI
Signet-AIOFFICIAL
Explore all skills by this author →
GitHub

recall

Query persistent memories using hybrid vector and keyword search.

237|40|Updated Feb 11, 2026
Search Tags:#recall#memory#persistence#vector#bm25#hybrid-search#daemon
One-click install
npx skills add https://github.com/Signet-AI/signetai --skill recall-signet-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: recall
Source: https://github.com/Signet-AI/signetai/tree/main/skills/recall
Command: npx skills add https://github.com/Signet-AI/signetai --skill recall-signet-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Query persistent memories using a hybrid vector- and keyword-based search to surface relevant context as you work with Signet-enabled agents across sessions.

Core Features & Use Cases

  • Hybrid search across memories using vector similarity plus keyword matching to locate past decisions, preferences, and conversations.
  • Automatic session injection: memories relevant to the current session are injected automatically to maintain continuity.
  • Targeted recall: use the /recall command to retrieve memories by type, tags, date range, or author for debugging and decision traceability.
  • Use Case: When planning a new agent capability, recall prior design decisions to avoid rework.

Quick Start

Use /recall to fetch memories related to a topic, for example /recall API design decisions.

Frequently Asked Questions about recall

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

FAQPage Schema
How do I retrieve past decisions and context across different agent sessions?▼

You retrieve past decisions across sessions by querying persistent memories using a hybrid vector and keyword search, which automatically injects relevant context at session start.

What is hybrid search for persistent memory and how does it work?▼

Hybrid search for persistent memory combines vector similarity with keyword matching to locate past decisions and conversations, returning structured results based on relevance.

Do I need a specific environment setup to use persistent memory recall?▼

Persistent memory recall requires the Signet daemon to be running to query, auto-inject, and retrieve stored context across your agent sessions.

Can I filter memory search results by tags, date range, or author?▼

You can filter memory search results by type, tags, date range, and author using the /recall command to target specific past preferences or topics.

How do I query specific topics from past conversations during a session?▼

Query specific topics from past conversations by using the /recall command followed by your topic, such as /recall API design decisions, to fetch relevant structured memories.

What are the limitations of using auto-injection for session context?▼

Auto-injection for session context relies on hybrid search relevance and requires the Signet daemon; if the daemon is inactive, memory persistence and session continuity are unavailable.

Related Skills

Explore More Software Engineering Skills→
RheasilviaRheasilvia

pinecone-research

Integrate Pinecone vector databases for retrieval-augmented generation and long-term memory.

Community
Intermediate
iulianditaiuliandita
2

handoff

Compress active agent session context into a structured markdown document.

Community
Advanced
aeonbridgeaeonbridge

graphiti

Manage persistent, temporal knowledge graphs for AI agents with bi-temporal data modeling.

Official
Advanced
fyrsmithlabsfyrsmithlabs

using-contextd

Initialize contextd MCP sessions for cross-session memory and semantic search.

Official
Advanced