uditgoenka/autoresearch v2.1.2

v2.1.2 — Product Improvement Engine

on GitHub

What's New

/autoresearch:improve — Research What to Build Next

New subcommand for product companies. Fills the "what should we build next?" gap in a family that previously only covered "how to build it right."

How it works:

1. Product Context — resolves from learn summary, README, package.json, or auto-discovers
2. Research Loop — 5 categories (ICP challenges, competitor gaps, market trends, UX & experience, revenue & growth) with saturation-based termination
3. Feature Ranking — ICP binary gate → Must-have / Nice-to-have / Moonshot → pairwise within Must-have
4. PRD Generation — per-feature PRDs with evidence chains, DECISION NEEDED markers, confidence tags

Usage:

/autoresearch:improve
Goal: Improve onboarding conversion for our SaaS product
ICP: B2B product managers at 50-500 person companies

Chain into improve:

/autoresearch:probe --improve     # constraints → improvement research
/autoresearch:predict --improve   # expert analysis → improvement research

Other Changes

• CONTEXT.md domain glossary with output types, loop shapes (+ Notes column), scoring systems
• Subcommand count: 12 → 13
• All platform distributions updated (Claude Code, OpenCode, Codex)
• 11 design decisions locked via adversarial reasoning (5-round debates with blind judge panels)

Install / Update

npx skills add uditgoenka/autoresearch

Or update existing:

/plugin update autoresearch

Full Changelog: v2.1.1...v2.1.2