wiki-agent

Extract topic-relevant session history from agent conversations into wiki pages.

Updated Feb 2, 2016
One-click install
npx skills add https://github.com/zjykzk/blog --skill wiki-agent-zjykzk
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: wiki-agent
Source: https://github.com/zjykzk/blog/tree/main/.agents/skills/wiki-agent
Command: npx skills add https://github.com/zjykzk/blog --skill wiki-agent-zjykzk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enables query-driven targeted ingestion from a single agent's conversations to extract only topic-relevant history and present a synthesized answer in the current session.

Core Features & Use Cases

  • Cross-agent topic searches (Claude, Codex, Hermes, OpenClaw, Copilot, Pi) to pull in just the relevant past discussions instead of bulk ingest.
  • Targeted extraction and distillation of blobs into wiki-ready knowledge, with automatic page updates and cross-links.
  • No heavy handoffs: resolves config, inventories sessions, scores relevance, and returns a synthesized summary for immediate use.

Quick Start

Trigger the wiki-agent with a topic to ingest the related sessions from a specific agent and generate a ready-to-use wiki summary.

Frequently Asked Questions about wiki-agent

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

FAQPage Schema
How do I extract topic-relevant conversation history from a specific AI agent without bulk importing?

Query-driven ingestion extracts only topic-relevant history from a single agent's conversations by resolving config, inventorying sessions, scoring relevance, and returning a synthesized summary for immediate use in the current session.

Can I search past sessions across different AI assistants like Claude, Codex, and Copilot?

Cross-agent session searches work across Claude, Codex, Hermes, OpenClaw, Copilot, and Pi to pull in relevant past discussions on a specific topic rather than performing a bulk ingest of all history.

How do I distill extracted conversation blobs into wiki-ready knowledge pages?

Targeted extraction distills conversation blobs into wiki-ready knowledge by generating synthesized summaries with automatic page updates and cross-links, creating ready-to-use documentation without heavy handoffs.

What is the best way to synthesize cross-agent context for immediate use in a new session?

Cross-agent history ingest resolves configuration, inventories past sessions, scores topic relevance, and distills targeted blobs into a synthesized answer, providing instant context without requiring heavy manual handoffs.

Do I need any external dependencies or components to perform cross-agent history ingest?

Cross-agent history ingest requires no external dependencies or components to function; it handles config resolution, session inventories, targeted blob extraction, and distillation internally.