wiki-agent

Ingest topic-specific agent session history into synthesized wiki pages.

Updated Apr 27, 2014
One-click install
npx skills add https://github.com/Nirajkashyap/nirajkashyap.github.io --skill wiki-agent-nirajkashyap
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: wiki-agent
Source: https://github.com/Nirajkashyap/nirajkashyap.github.io/tree/main/.agents/skills/wiki-agent
Command: npx skills add https://github.com/Nirajkashyap/nirajkashyap.github.io --skill wiki-agent-nirajkashyap

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables query-driven targeted ingestion from a specific AI agent's raw conversation history. It finds sessions about a SPECIFIC TOPIC in a given agent's history, ingests just those blobs, distills them into the wiki, and returns a synthesized answer ready to act on in the current session.

Core Features & Use Cases

  • Targeted cross-agent history search: pull in topic-specific context from Claude, Codex, Hermes, OpenClaw, or Copilot.
  • Focused ingestion over bulk: selects relevant sessions and extracts only the needed content.
  • Synthesis and wiki integration: converts extracted blobs into durable wiki pages with proper linking and attribution.

Quick Start

Issue a command like /wiki-claude "your topic" to fetch and ingest topic-specific Claude history.

Frequently Asked Questions about wiki-agent

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

FAQPage Schema
How do I search cross-agent conversation history for a specific topic?▼

Cross-agent history ingestion works by issuing a command like /wiki-claude with your topic. The Skill identifies and ingests only the relevant session blobs from that agent, distills them into wiki pages, and returns a synthesized answer for your current session.

Can I pull topic-specific context from Claude or Copilot without importing bulk history?▼

Yes, you can pull topic-specific context without importing bulk history. By invoking commands like /wiki-claude or /wiki-copilot, the Skill performs focused ingestion, selecting only relevant sessions and extracting the needed content instead of loading entire histories.

How does synthesized knowledge get integrated into a wiki?▼

Synthesized knowledge is integrated by converting extracted conversation blobs into durable wiki pages. These pages include frontmatter, attribution, and cross-links to related content, while the Skill tracks all ingested sessions and generated pages.

What is the difference between targeted ingestion and bulk history ingestion for knowledge management?▼

Targeted ingestion selects only relevant sessions about a specific topic from an agent's history, whereas bulk ingestion imports everything. Targeted ingestion prevents clutter by distilling only the needed content into durable, cross-linked wiki pages.

Which AI agents can I use for cross-reference history ingestion?▼

You can use cross-reference history ingestion with Claude, Codex, Hermes, OpenClaw, and Copilot. You invoke the specific agent by using its corresponding command, such as /wiki-codex or /wiki-hermes, to pull topic-specific context.

What are the limitations of using targeted cross-agent history blobs for synthesis?▼

A limitation of targeted cross-agent history ingestion is that it requires selecting sessions about a specific topic from a single agent at a time. It does not bulk process entire histories or automatically ingest across multiple agents simultaneously.