anvil-research

Delegates research questions to a background agent that writes cited Markdown findings.

1|Updated Aug 27, 2026
One-click install
npx skills add https://github.com/rogerznts/anvil --skill anvil-research-rogerznts
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: anvil-research
Source: https://github.com/rogerznts/anvil/tree/main/anvil/.claude/skills/anvil-research
Command: npx skills add https://github.com/rogerznts/anvil --skill anvil-research-rogerznts

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Researching a topic against primary sources takes long stretches of reading that block your main work. This Skill offloads that investigation to a background agent so you keep working while the findings are gathered and written down. ## Core Features & Use Cases - Background research agent: Spins up a separate agent to investigate the question while you continue your current task. - Primary-source grounding: Every claim is traced back to official docs, source code, specs, or first-party APIs rather than secondary write-ups. - Markdown report with citations: Findings are saved as a single Markdown file where each claim cites its source, placed where the repo already keeps such notes. - Use Case: Ask how a specific API rate limit works; the agent reads the official documentation and source, then saves a cited summary file in your repo's notes directory. ## Quick Start Ask the assistant to research how a specific library or API feature works and save the findings as a Markdown note in the repo.

Frequently Asked Questions about anvil-research

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

FAQPage Schema
How do I delegate research to a background agent?▼

State the research question and let the Skill spin up a background agent to investigate it. The agent reads primary sources, writes findings to a Markdown file with citations, and you continue working in the meantime.

What sources does the research agent use?▼

The agent investigates primary sources only: official documentation, source code, specifications, and first-party APIs. It follows every claim back to the source that owns it rather than relying on secondary articles or summaries.

Where are the research findings saved?▼

Findings are written to a single Markdown file saved where the repository already keeps such notes, matching the existing convention. If no convention exists, the agent picks a sensible location and tells you where it saved the file.

Can I keep working while the research runs?▼

Yes. The research runs in a background agent specifically so your main session stays free. You continue your current task while the agent reads sources and prepares the cited Markdown report.

When should I not use a background research agent?▼

Avoid it for quick factual lookups you can answer immediately or for questions requiring interactive clarification. It fits open-ended investigations where reading legwork can proceed independently and be captured as a written document.