# Evidence First Research

> Use when a question needs investigating and the answer will be acted on — "research X", "look into whether Y", "find out how Z works", "is this worth doing", "compare these options", a benchmark someone will quote, or a claim that has to survive being challenged. Produces a dated record where every finding carries how it is known — measured, read, inferred, or unverified — plus a self-contained HTML view. Not for locating code (that is explore-codebase), tracing one symptom (debug-issue), or judging a diff (review-changes); reach for this when the output is a set of findings someone else will rely on.

- Skill: `arasz/evidence-first-research-3` (Agent Skill, multi-file: 7 files)
- Install (CLI): `npx get-skill add arasz/evidence-first-research-3`
- Raw SKILL.md: https://api.skillmd.com/api/skills/arasz/evidence-first-research-3/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Web & Frontend
- License: MIT
- Author: Arasz (https://skillmd.com/u/arasz)
- Updated: 2026-11-14
- Page: https://skillmd.com/skills/arasz/evidence-first-research-3

---


> **This is the generic copy.** If this project has been scaffolded, prefer the unprefixed
> `evidence-first-research` skill: it is `.ai-badger/skills/evidence-first-research/SKILL.md`, and it has this project's
> extensions and any `project-local.md` merged in. This copy has neither.
>
> The full procedure is in `SKILL.full.md` beside this file, unchanged — read it if the project has no
> `.ai-badger/`, or run `welcome-ai-badger` to scaffold one.

