# Sdd Research

> Map how the existing code works before specifying a change to it.

- Skill: `mariano-aguero/sdd-research` (Agent Skill)
- Install (CLI): `npx get-skill add mariano-aguero/sdd-research`
- Raw SKILL.md: https://api.skillmd.com/api/skills/mariano-aguero/sdd-research/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- License: MIT
- Author: mariano-aguero (https://skillmd.com/u/mariano-aguero)
- Updated: 2026-11-18
- Page: https://skillmd.com/skills/mariano-aguero/sdd-research

---


# sdd-research

Paths below are relative to this file. Resolve them before running anything.

Read `../spec-driven-development/SKILL.md`, section "Phase 0.5".
Read `../spec-driven-development/references/workflow-phases.md`, section "Phase 0.5".
Use "Codebase Research Prompt" and "Research Consolidation Prompt" in `../spec-driven-development/references/prompt-patterns.md`.
Use the template under "research.md Template" in `../spec-driven-development/references/artifact-templates.md`.

Produce: `specs/<feature>/research.md`, every finding cited `file:line`.
Describe how the code works today. No ACs, user stories, or proposed design in `research.md`.
Put what you could not determine under `## Open questions / not investigated`; never fill a gap with a guess.
Gate: "Gate R" in `../spec-driven-development/references/quality-gates.md`, with "Research Verification Prompt" from the prompt file.
Validate: `node ../spec-driven-development/scripts/sdd-check.mjs specs/<feature>`
Next: `/sdd-specify`. Report the Gate R verdict and wait for the human before Phase 1.

