Synthesize discovery findings into a sharp problem statement, How Might We questions, success criteria and scope. Use when research on a topic has been gathered and the user needs to narrow it down to the one problem worth solving.
Installs into .claude/skills of the current project.
Are you the author of Research Define?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/bromso-research-define)
---
name: research-define
description: Synthesize discovery findings into a sharp problem statement, How Might We questions, success criteria and scope. Use when research on a topic has been gathered and the user needs to narrow it down to the one problem worth solving.
metadata:
argument-hint: "[project] [--skip-checks]"
workflow: research
phase: 2
artifact: 02-define.md
---
# Define
Converge the broad discovery findings on "$ARGUMENTS" into a focused problem statement, "How Might We" questions, and a research plan for the solution phase.
**Arguments.** `$ARGUMENTS` may contain the project name and optional flags. Take the first token as `<project>` and treat `--skip-checks` as a flag; never include flags in file paths. All paths below use `<project>`. If `--skip-checks` is present, skip the prerequisite check and, **before writing any artifact**, append one line to `.singularskills/log.jsonl`: `{"ts":"<ISO timestamp>","skill":"research-define","workflow":"research","phase":2,"project":"<project>","event":"skipped","artifact":"02-define.md","note":"<reason or \"none given\">"}`.
## Prerequisites
**Part of a workflow.** This skill is phase 2 (Define) of the Double Diamond workflow (`research`); cross-domain workflows run it too. First check `.singularskills/log.jsonl` for an open run for this project: a `run-started` line with `"project":"<project>"` and no later `run-finished` line for the same `workflow` and `project`. If one exists, the conductor is running you: continue here. Otherwise, if the user asked to start, run, continue or resume a process or workflow rather than this one step, do not continue here: invoke the `workflow` skill with the workflow the user asked for, or `research` when they named none, followed by `<project>`; it runs this phase in order, asks before it writes and records the run. Otherwise continue here: a later phase runs on its own, behind its gate.
Run this skill's gate before writing: `sh <this skill's folder>/scripts/gate.sh <project> <project root>`, where `<project root>` is the folder that contains `.singularskills/` (use `.` when you are already there). If it exits non-zero, stop and tell the user what it printed, unless `--skip-checks` was given (see Arguments). On a refusal, before you stop, append this line to `.singularskills/log.jsonl` (create the folder and file if missing): `{"ts":"<ISO timestamp>","skill":"research-define","workflow":"research","phase":2,"project":"<project>","event":"refused","artifact":"02-define.md","note":"<what the gate printed>"}`. Once the gate has passed, or under `--skip-checks` once you have appended the `skipped` line, append this line before you start work: `{"ts":"<ISO timestamp>","skill":"research-define","workflow":"research","phase":2,"project":"<project>","event":"started","artifact":"02-define.md","note":""}`.
Read `.singularskills/research/<project>/01-discover.md`. If this file does not exist, tell the user:
> Phase 1 (Discover) has not been completed for "<project>". Run `/research-discover <project>` first, or use `--skip-checks` to bypass.
## Process
1. **Read context files:**
- Read `.singularskills/research/<project>/01-discover.md` for discovery findings
- Read `references/double-diamond-guide.md` for methodology reference
- Read `references/research-plan-template.md` for output structure
2. **Synthesize findings:**
- Review all themes from the Discover phase
- Identify the core tension or unmet need
- Distinguish root causes from symptoms
- Map relationships between themes
3. **Formulate the problem statement:**
- Write a clear, specific, actionable problem statement
- Avoid solution-language (the problem, not the answer)
- Ensure it's scoped enough to be solvable
4. **Generate "How Might We" questions:**
- Create 3-5 HMW questions that reframe the problem as opportunities
- Each HMW should open a different solution direction
- Avoid HMW questions that are too broad or too narrow
5. **Define success criteria and scope:**
- What does "solved" look like? Specify measurable criteria
- What's in scope and out of scope for the Design phase?
- Identify constraints and assumptions
6. **Write the artifact** to `.singularskills/research/<project>/02-define.md` following the research plan template structure.
## Output
The problem definition written to `.singularskills/research/<project>/02-define.md`. Present a summary to the user highlighting:
- The problem statement
- Top HMW questions
- Key scope decisions
- Recommended focus for the Design phase
**Record the run.** After you have written the artifact, append this line to `.singularskills/log.jsonl` (the `started` line of Prerequisites, with `"event":"finished"`): `{"ts":"<ISO timestamp>","skill":"research-define","workflow":"research","phase":2,"project":"<project>","event":"finished","artifact":"02-define.md","note":""}`.
Open the artifact with this frontmatter (`agent` is the agent you run in, or `unknown`; `gate` is `passed` when the gate ran clean and `skipped` under `--skip-checks`):
```yaml
---
skill: research-define
workflow: research
phase: 2
project: <project>
started: <ISO timestamp>
finished: <ISO timestamp>
agent: <the agent you run in, or "unknown">
gate: <passed|skipped>
---
```
End the artifact with `## Decisions` and `## Open questions`, in this shape:
```markdown
## Decisions
- <what was chosen> — <why> — <what was rejected>
## Open questions
- <what the next phase or a reviewer must settle>
```