simon-research

Conducts cited external research and competitive comparisons before planning decisions.

Updated Apr 5, 2026
One-click install
npx skills add https://github.com/Simon-YHKim/eject-button --skill simon-research-simon-yhkim
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: simon-research
Source: https://github.com/Simon-YHKim/eject-button/tree/main/.claude/skills/simon-research
Command: npx skills add https://github.com/Simon-YHKim/eject-button --skill simon-research-simon-yhkim

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Planning and architecture decisions often rely on unsourced assumptions or stale knowledge. This Skill enforces a research-first workflow that gathers official documentation, competitive product data, and recent engineering sources before any major planning step, producing a dated, citation-backed research document. ## Core Features & Use Cases - Source-Grounded Investigation: Collects primary sources (official docs, GitHub repos, RFCs) via parallel WebFetch, rejecting stale blogs and AI-summary articles. - Competitive Comparison Tables: Builds structured comparison of 3+ competing products covering pricing, features, constraints, and community. - Dated Research Documents: Saves results to docs/research/<date>-<topic>.md with full citation metadata, findings, recommendations, and open questions. - Use Case: Before choosing a backend stack, ask for a comparison of Supabase vs Firebase for a Korean startup MVP and receive a saved research doc with cited sources, a 3+ product comparison table, and Korea-specific notes ready to feed into plan reviews. ## Quick Start Ask the agent to research and compare Supabase vs Firebase for your MVP and save the findings as a dated research document.

Frequently Asked Questions about simon-research

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

FAQPage Schema
How do I research a technology stack before planning a project?

Request a research pass naming the topic and decision context. The skill extracts search keywords, fetches official documentation and recent engineering blogs in parallel, compares at least three competing products, and saves a cited research document to docs/research/.

What sources are acceptable for technical competitive analysis?

Acceptable primary sources are official documentation, official GitHub repositories, RFCs and specifications, and engineering blogs from the last six months. Blogs older than one year, unattributed summaries, and AI-generated articles are rejected as primary sources.

How do I compare Supabase vs Firebase with cited sources?

Ask for a comparison naming both products and your context. The skill adds at least one more competitor such as PocketBase or Appwrite, builds a table covering pricing, features, constraints, and community, and attaches a URL and date to every claim.

Where are research results saved and in what format?

Results are saved as markdown at docs/research/<YYYY-MM-DD>-<topic>.md. The document includes a summary, numbered source list with dates and primary/secondary classification, a competitive landscape table, findings, recommendations, and open questions.

When should research run in a planning workflow?

Research runs before major planning steps such as CEO plan reviews, engineering reviews, or large planning sessions. The saved research document is passed as input evidence to those downstream planning skills.

What are the limitations of this research workflow?

It depends on web fetch access, so unreachable or paywalled sources cannot be verified. Context7 MCP integration for fresh library docs is optional and only works when the MCP server is connected, which should be checked beforehand.