home/productivity/review-tech-spec-quality-prompt

Review Tech Spec Quality.prompt

GPTClaudeDeepSeek··562 copies·updated 2026-07-14
review-tech-spec-quality-prompt.prompt
---
description: "Review a technical specification, score architecture quality, and provide prioritized improvements before implementation."
name: "Review Tech Spec Quality"
argument-hint: "Path to tech spec file or tech spec text"
agent: "agent"
---

Review the technical specification provided by the user and produce a structured architecture quality assessment.

References:
- [Create Tech Spec Skill](../skills/create-tech-spec/SKILL.md)
- [Tech Spec Template](../skills/create-tech-spec/assets/tech-spec-template.md)

## Scope
- Evaluate architecture and specification quality, not code style.
- Focus on decision quality, requirement coverage, operational readiness, and risk.

## Review Steps
1. Confirm context and boundaries:
   - Feature intent
   - Source PRD assumptions
   - In-scope and out-of-scope constraints
2. Evaluate architecture decisions and rationale.
3. Score the spec using the rubric below.
4. Identify blocking gaps, ambiguities, and contradictions.
5. Provide priority-ordered fixes that improve delivery readiness.

## Architecture Quality Rubric (0-100)
- PRD alignment and traceability (20)
  - Are major FR/NFR items mapped to technical decisions?
- Architecture clarity and boundaries (20)
  - Are components, responsibilities, and interfaces clearly separated?
- Data, API, and integration design quality (20)
  - Are contracts, data flows, and compatibility impacts clear and coherent?
- Non-functional design coverage (20)
  - Are performance, reliability, security/privacy, and compliance addressed?
- Rollout, migration, and operability readiness (15)
  - Are rollout strategy, rollback, observability, and operational signals defined?
- Alternatives and decision rationale (5)
  - Are tradeoffs explicit and the selected option justified?

## Decision Quality Checks
For each major design decision, verify:
- Clear context and constraint framing
- Explicit alternatives considered
- Tradeoff rationale
- Expected consequences
- Validation approach

## Output Format
Return the review in this structure:

### Tech Spec Quality Score
- Overall score: <0-100>
- Rating: <Excellent|Good|Needs Work|High Risk>
- Summary: <2-4 sentences>

### Score Breakdown
| Category | Score | Max | Notes |
|---|---:|---:|---|
| PRD alignment and traceability | <n> | 20 | <notes> |
| Architecture clarity and boundaries | <n> | 20 | <notes> |
| Data/API/integration design quality | <n> | 20 | <notes> |
| Non-functional design coverage | <n> | 20 | <notes> |
| Rollout/migration/operability readiness | <n> | 15 | <notes> |
| Alternatives and rationale | <n> | 5 | <notes> |

### Critical Findings
- <highest-priority risk>
- <next risk>

### Recommended Fixes (Priority Ordered)
1. <fix 1>
2. <fix 2>
3. <fix 3>

### Readiness Decision
- Status: <Ready for implementation planning|Needs revision>
- Minimum changes required for readiness:
  - <change 1>
  - <change 2>

when to use it

Community prompt sourced from the open-source GitHub repo lhenrique42/ai-templates (MIT). A "Review Tech Spec Quality.prompt" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.

tags

productivitycommunitydeveloper

source

lhenrique42/ai-templates · MIT