wiki-agent

Search an agent's history for a topic and ingest relevant blobs into wiki pages.

6|2|Updated May 11, 2026
One-click install
npx skills add https://github.com/pax-k/war-gov-uap-wiki --skill wiki-agent-pax-k
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: wiki-agent
Source: https://github.com/pax-k/war-gov-uap-wiki/tree/main/.cursor/skills/wiki-agent
Command: npx skills add https://github.com/pax-k/war-gov-uap-wiki --skill wiki-agent-pax-k

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enables query-driven, targeted ingestion from a single agent's conversation history to populate the wiki with relevant insights, reducing noise from bulk ingestion and preserving provenance.

Core Features & Use Cases

  • Targeted history search: locate conversations about a specific topic across one agent's history.
  • Ingest as-needed: extract only relevant blobs, distill them into durable wiki knowledge, and create or update pages with provenance.
  • Cross-agent analysis: combine insights across Claude, Codex, Hermes, OpenClaw, and Copilot contexts for a unified knowledge base.
  • Use Case: when you want to pull how you handled a particular problem in Codex into your Claude workspace for rapid cross-reference.

Quick Start

Search the target agent's history for a topic and ingest the relevant blobs into the wiki.

Frequently Asked Questions about wiki-agent

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

FAQPage Schema
How do I extract specific topics from agent conversation history into a wiki?

To extract specific topics from agent conversation history into a wiki, you perform a targeted ingestion that searches one agent's sessions for relevant blobs and distills them into durable wiki pages with provenance, avoiding bulk harvesting noise.

Can I combine cross-agent insights from Claude, Codex, and Copilot into a unified knowledge base?

You can combine cross-agent insights by applying targeted ingestion across Claude, Codex, Hermes, OpenClaw, and Copilot histories, extracting relevant blobs from each to synthesize a unified wiki knowledge base with cross-links.

What is the best way to ingest Codex problem-solving sessions into a Claude workspace?

The best way to ingest Codex problem-solving sessions into a Claude workspace is to search the Codex history for the specific topic, extract the relevant conversation blobs, and distill them into wiki pages for rapid cross-reference.

How does targeted history ingestion preserve provenance when creating wiki pages?

Targeted history ingestion preserves provenance by extracting specific conversation blobs from a single agent's history and creating or updating wiki pages with proper frontmatter and provenance tracking attached to the distilled knowledge.

Why should I use targeted ingestion instead of bulk harvesting for wiki population?

You should use targeted ingestion instead of bulk harvesting because it performs a query-driven search for a specific topic within one agent's history, significantly reducing noise and ensuring only relevant blobs become distilled wiki knowledge.

Do I need bulk conversation exports to synthesize cross-agent history into wiki pages?

You do not need bulk conversation exports to synthesize cross-agent history into wiki pages; the process relies on query-driven targeted ingestion that locates specific topic sessions and extracts only the relevant blobs needed.