ask

Retrieves wiki pages and synthesizes evidence-grounded answers with citations.

77|16|Updated May 9, 2026
One-click install
npx skills add https://github.com/Lambenthan/empiricalwiki --skill ask-lambenthan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ask
Source: https://github.com/Lambenthan/empiricalwiki/tree/main/.claude/skills/ask
Command: npx skills add https://github.com/Lambenthan/empiricalwiki --skill ask-lambenthan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you ask questions about an EmpiricalWiki knowledge base and receive evidence-backed answers that reference the exact wiki pages, optionally crystallizing the result back into new or updated wiki content.

Core Features & Use Cases

  • Global-context aware retrieval: Loads wiki/graph/context_brief.md and wiki/graph/open_questions.md, then uses wiki/index.md to locate the most relevant pages.
  • Citation-grounded synthesis: Produces structured answers where key claims are linked using [[slug]] wikilinks, and flags uncertainty when the wiki lacks sufficient evidence.
  • Knowledge compounding (crystallize): In --crystallize mode, writes query results to wiki/outputs/, and may create or update wiki/concepts/ or wiki/claims/ plus append graph edges and rebuild derived context.
  • Evidence & graph integration: Updates wiki/graph/edges.jsonl, wiki/index.md, and wiki/log.md so future questions benefit from the new relationships.

Quick Start

Ask a research question and let the skill retrieve, synthesize, and cite relevant wiki pages: run /ask with your question, for example: "LoRA 和 Adapter 的核心区别是什么?".

Frequently Asked Questions about ask

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

FAQPage Schema
How do I get evidence-backed answers from a wiki knowledge base?

To get evidence-backed answers from a wiki knowledge base, ask a research question and the skill retrieves relevant pages, synthesizes a response, and enforces wikilink citations to reference exact sources.

What is the best way to synthesize cross-paper research findings on variables and mechanisms?

Synthesizing cross-paper research findings on variables and mechanisms is done by querying an EmpiricalWiki knowledge base that grounds responses in existing identification, robustness, and heterogeneity claims.

How do I query an EmpiricalWiki to update the knowledge graph with new claims?

To query an EmpiricalWiki and update the knowledge graph, use the crystallize mode to write results to wiki outputs, create or update concepts and claims, and append edges to rebuild derived context.

Can I flag uncertainty when a wiki lacks sufficient evidence for a research question?

Yes, you can flag uncertainty when a wiki lacks sufficient evidence because the citation-grounded synthesis explicitly flags uncertainty in the structured answer if the knowledge base cannot support the claim.

Do I need to load global context files before querying my research wiki?

You do not need to manually load global context files before querying your research wiki because the skill automatically loads context briefs, open questions, and the index to locate relevant pages.

What are the limitations of retrieving wiki pages for empirical research workflows?

A limitation of retrieving wiki pages for empirical research workflows is that answer quality depends entirely on the existing EmpiricalWiki content, meaning the synthesis cannot retrieve evidence not already present in the knowledge base.