/hai-prd

name: hai-prd
description: |
  Decides whether a PRD is needed, drafts one from a product problem, repairs an existing PRD, or judges its split/merge boundary. Use for PRDs, product requirements, requirement specs, scope, user-visible behavior, and acceptance criteria（写 PRD、需求文档、PRD 拆分或打磨）. Use hai-goal for execution phases, hai-architecture for technical design, entity-model-auditor for field placement, and document-audit skills when the task is consistency diagnosis rather than product shaping.

Hai PRD

For Chinese readers, see `SKILL.zh_CN.md`. The English `SKILL.md` is the execution source of truth.

Overview

Handle all PRD-related work: deciding whether a PRD is even needed, choosing PRD granularity, splitting or merging PRDs, drafting a PRD from a product problem, and refining an existing one.

The non-obvious framing: a PRD is not the default artifact. Not every idea, field, API, configuration change, or technical decision earns one. Pick the mode that fits the request and do not wrap work in a PRD when there is no product boundary or acceptance to prove.

Core Principle

A PRD is a product argument with verifiable acceptance — not a feature list. Three rules carry the rest:

• **Acceptance must be provable.** One PRD should resolve one clear outcome, one main user journey

or product boundary, and acceptance criteria that prove it shipped.

• **Boundary follows the user's mental model, not the tech.** Granularity tracks user journeys and

independent acceptance — not technical layers, teams, or files.

• **Fix the boundary before the wording.** If the PRD boundary is wrong, split, merge, or reframe

it before polishing local sentences; edit an existing PRD as a system where goal, scope, behavior, acceptance, risks, and rollout must agree.

Modes

1. Need PRD

First decide the artifact type — a PRD is one option among several:

| Situation | Better artifact | |-----------|-----------------| | User or business behavior changes and goal, scope, and acceptance need alignment | PRD | | Execution goal, phases, and verification are the main need | `hai-goal` | | Architecture, module boundaries, or technical tradeoffs are the main need | `hai-architecture` | | The main question is whether the idea is worth doing at all | `hai-idea` | | The work is a code task, bugfix, or test-first implementation | `hai-tdd` or task note | | The work is documentation consistency auditing | `hai-audit-docs` |

Ask:

• Is there a user-, buyer-, operator-, maintainer-, or business-visible behavior change?
• Does the work need explicit in-scope and out-of-scope boundaries?
• Does it need acceptance criteria to prove it was done correctly?
• Are there product-level options, risks, constraints, or rollout concerns to record?
• Would the team disagree on goal, scope, or acceptance without a PRD?

If most answers are no, do not force a PRD. When auditing a *set* of PRDs, also check for duplicate boundaries, circular dependencies, or broken user journeys across them.

2. Design PRD

Turn a feature idea or product problem into PRD-level requirements:

1. **Gather context.** Target user, product surface, current behavior, desired outcome, constraints, assumptions; plus existing PRDs, docs, screenshots, user flows, issues, data, or adjacent specs. 2. **Frame the requirement.** Write the problem in product language; define the target outcome and non-goals; identify the user journey or workflow boundary; separate facts, assumptions, and open questions. 3. **Shape scope.** Decide what belongs in this PRD versus another PRD, design doc, goal, or task. Do not bundle unrelated cleanup, platform work, or refactors unless they directly affect product behavior or acceptance. 4. **Define behavior and acceptance.** Describe expected behavior by scenario; add observable acceptance criteria; include edge cases, failure states, permissions, empty states, data dependencies, and rollout only when relevant.

3. Craft PRD

Refine an existing PRD as a whole product argument:

1. **Read the full document first.** Identify title, target user, goal, journey, scope, non-goals, acceptance, risks, and open questions; mark contradictions, duplication, stale sections, local patches, and unreasonable content. 2. **Diagnose document drift** using this taxonomy:

• **Goal drift**: sections optimize for different outcomes.
• **Scope drift**: requirements pull in unrelated work.
• **Conflict drift**: behavior, state, permissions, data, or rollout disagree across sections.
• **Acceptance drift**: acceptance criteria cannot prove the target outcome.
• **Solution drift**: implementation choices replace product requirements.
• **Local-edit drift**: one section improves while the whole PRD becomes worse.

3. **Reframe before rewriting.** State the corrected target outcome and the PRD boundary; decide whether to preserve, reorganize, split, merge, or rewrite. 4. **Craft the document.** Edit directly when the user provides a file; preserve useful content but move it to the right section; remove unsupported, duplicated, obsolete, or out-of-scope content; explain why removal beats rewriting or moving when content is deleted.

4. Scope PRD

Judge PRD granularity by user mental model and independent acceptance, not technical modules or teams. Run the six tests — this is the decision core:

| Test | Question | Signal | |------|----------|--------| | Press Release | Can one sentence express one clear user value? | Multiple unrelated values lean split | | Independent Value | Does this PRD deliver value on its own? | Independent value can split; no value leans merge | | Independent Acceptance | Can it be accepted independently? | Independent acceptance can split | | Domain Language | Does it share the same core entity, terminology, and lifecycle? | Same entity leans merge; different contexts lean split | | User Journey | Does splitting break the user journey? | Broken jou