alive:search-world

Search across walnuts for decisions, people, files, references, insights, and logs.

124|7|Updated Feb 19, 2026
One-click install
npx skills add https://github.com/alivecontext/alive --skill alive-search-world
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: alive:search-world
Source: https://github.com/alivecontext/alive/tree/main/plugins/alive/skills/search-world
Command: npx skills add https://github.com/alivecontext/alive --skill alive-search-world

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps users locate decisions, people, files, references, insights, and log history when the item exists but its location is unknown, by enabling cross-walnut search and retrieval.

Core Features & Use Cases

  • Cross-walnut search: Query decisions, people, files, references, insights, and logs across all walnuts in priority order.
  • Structured ranking: Returns results ordered by signal strength, age, and relevance to the query.
  • Use Case: Imagine you lost a reference to a key decision; this Skill helps you locate the walnut containing the item and surface related context.

Quick Start

Ask the AI to search across all walnuts for the item you cannot locate.

Frequently Asked Questions about alive:search-world

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

FAQPage Schema
How do I search across all walnuts to find lost decisions and references?

Cross-walnut search executes frontmatter scans, insights search, log search, task search, working-file search, bundle-manifest search, and raw-reference search to locate scattered artifacts. A context-source cascade acts as fallback to deliver prioritized results.

How are cross-walnut search results ranked and prioritized?

Use cross-walnut search when you need to locate a specific item but its location is unknown. It finds scattered artifacts, transcripts, and contextual metadata across all walnuts, delivering prioritized results to surface related context.

What's the best way to retrieve log history and contextual metadata from scattered files?

Cross-walnut search locates decisions, people, files, references, insights, and log history across scattered artifacts, transcripts, and contextual metadata. It uses structured ranking to return prioritized results ordered by signal strength and age.

Does cross-walnut search work when a specific reference or file location is unknown?

Yes, cross-walnut search works when a file location is unknown by implementing frontmatter scans, working-file searches, bundle-manifest searches, and raw-reference searches. A context-source cascade operates as a fallback to locate the item.

Can I use cross-walnut search to locate people and insights alongside files?

Cross-walnut search locates decisions, people, files, references, insights, and log history across scattered artifacts, transcripts, and contextual metadata. It returns prioritized results ordered by signal strength, age, and query relevance.

What happens if standard frontmatter and task searches fail to find a reference?

If standard searches fail, a context-source cascade acts as a fallback to locate the item. This ensures cross-walnut search can still surface related context and deliver prioritized results from scattered artifacts and transcripts.