Skill

Process

From qq

Reviews game design documents from implementer's perspective: self-consistency, playability, buildability, codebase gaps. Validates against codebase.

documentation

code-quality

npx claudepluginhub tykisgod/quick-question

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Respond in the user's preferred language (detect from their recent messages, or fall back to the language setting in CLAUDE.md).

Supporting Assets

design-reviewer-prompt.md

SKILL.md

Similar Skills

design-review

Reviews design docs with an 8-point checklist validating problem clarity, success criteria, architecture fit, alternatives, scope, decisions, consistency, and handoff before planning.

1 file

claude-caliper-workflow

design-review

139

Reviews design and implementation docs from analysis-process for document quality, internal consistency, and technical soundness before implementation-process.

2 files

using-superpowers

185.1k

Mandates invoking relevant skills via tools before any response in coding sessions. Covers access, priorities, and adaptations for Claude Code, Copilot CLI, Gemini CLI.

3 files

superpowers

Stats

Stars6

Forks2

Last CommitApr 4, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Respond in the user's preferred language (detect from their recent messages, or fall back to the language setting in CLAUDE.md).

Review a game design document from an implementer's perspective.

Arguments: $ARGUMENTS (path to a design document, or empty to use the most recent design doc in Docs/qq/)

Process

Find the document: if a path is given, read it. Otherwise, find the most recent *_design.md in Docs/qq/.
Spawn a review subagent using the Agent tool. The subagent should:
- Read design-reviewer-prompt.md for the full review checklist
- Read the design document
- Independently explore the codebase (Services, configs, existing design docs) to verify claims — do not rely solely on what the document says exists
- Output the review in the format specified in the reviewer prompt
Verify the findings: as the main agent, independently spot-check the subagent's claims against the codebase. The subagent may misread code or reference stale information. For each finding, confirm or reject it with your own evidence before presenting to the user.
Present the verified review to the user — only include findings you confirmed. Note any subagent findings you rejected and why.
If verdict is HAS GAPS or NEEDS REWORK: revise the document together with the user. Re-run the subagent review after revisions. Loop until SOLID or the user explicitly accepts the gaps.
If verdict is SOLID: confirm and recommend /qq:plan. If invoked with --auto (or called from a skill running in --auto mode): run qq-execute-checkpoint.py pipeline-advance --project . --completed-skill "/qq:post-design-review" --next-skill "/qq:plan", then invoke /qq:plan --auto <document-path>.