# Onechange Causal UX

> Turn competing A/B interface drafts into a controlled single-variable UX research plan and a validated OneChange Research Pack. Use when a PM or UX researcher needs to identify confounds, freeze one testable change, plan first-click or five-second research, or hand the method to another team. Do not claim a winning design, reuse historical evidence, or treat AI observations as participant results.

- Skill: `seanj1ang/onechange-causal-ux` (Agent Skill, multi-file: 14 files)
- Install (CLI): `npx skillmds@latest add seanj1ang/onechange-causal-ux`
- Raw SKILL.md: https://api.skillmd.com/api/skills/seanj1ang/onechange-causal-ux/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: SeanJ1ang (https://skillmd.com/u/seanj1ang)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/seanj1ang/onechange-causal-ux

---


# OneChange Causal UX

Help a product team answer one narrow question: what changed, which single change is worth testing, and what evidence would support a decision?

Respond in the user's language. Keep machine-readable field names unchanged when creating a Research Pack.

## Choose the smallest useful route

| Available material | Route |
| --- | --- |
| A/B screenshots or mockups | Observe differences → identify confounds → propose one variable contract |
| A written product hypothesis | Turn it into a decision question, participant task, method and stopping rule |
| An existing `.onechange.json` | Validate structure and integrity before recommending import |
| A complete study design | Produce a Research Pack; do not invent results or participant evidence |

Read [references/research-contract.md](references/research-contract.md) before selecting a variable or interpreting evidence. Read [references/research-pack.schema.json](references/research-pack.schema.json) when constructing or repairing a Research Pack.

When the user asks what a complete handoff should look like, read [examples/EXPECTED_HANDOFF.md](examples/EXPECTED_HANDOFF.md) or its English mirror. Reuse its structure, not its business facts, variable choice, or sample assumptions.

## Build the research contract

1. Separate user-supplied facts, observable interface differences and model inferences.
2. List all simultaneous changes before selecting a target. Do not call a visual difference a user problem without research evidence.
3. Select exactly one allowed variable. Describe its A → B* transition in observable terms.
4. Freeze the remaining copy, action, DOM role, hit area, brand identity and non-target modules.
5. Write a falsifiable hypothesis, a participant task without answer leakage and a decision question.
6. Choose `first_click`, `five_second`, or both. State the primary metric, minimum detectable effect and target sample per arm.
7. Mark preview QA, formal participant evidence and AI observations as different evidence classes.

If the material cannot support a single-variable contract, stop with the unresolved confounds instead of fabricating B*.

## Produce a reusable Research Pack

Start from [assets/guest-checkout.onechange.json](assets/guest-checkout.onechange.json). Change only the research design fields in `payload`; never add experiment IDs, deployment tokens, identities, sessions, events, results or conclusions.

After editing a pack, explicitly regenerate its payload hash:

```bash
node scripts/validate_research_pack.cjs <pack.onechange.json> --fix-hash
```

Then validate without mutation:

```bash
node scripts/validate_research_pack.cjs <pack.onechange.json>
```

Treat validation success as format and integrity evidence, not proof that the study is methodologically correct or that the publisher is authentic.

## Return a decision-ready handoff

Provide:

- the decision question and current business context;
- observed differences and unresolved confounds;
- the one allowed variable and frozen properties;
- the participant task, methods, primary metric, MDE and stopping rule;
- evidence boundaries and missing facts;
- the validated Research Pack path, when one was created;
- the next human decision.

Never announce a winner from AI analysis, preview data or insufficient formal samples. The product manager keeps the final business decision.