agentleFS
Sign inStart free
tykisgodtykisgod/quick-question/skills/post-design-review/SKILL.md

post-design-review

Skill12 starsChanged 8 months agoMITView on GitHub

Review a game design document from an implementer's perspective — check self-consistency, playability, buildability, and codebase gaps. Use after writing a design doc, or when you want to validate an existing design against the current codebase.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Find the document: if a path is given, read it.

    line 17
  2. Distinctive:

    Verify, then present: check each finding yourself against the document and the code.

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Run qq scripts as ${CLAUDE_PLUGIN_ROOT}/bin/<name>: they are not on PATH, so a bare qq-execute-checkpoint.py exits 127.

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.

Workflow: take --workflow <name> from $ARGUMENTS if present, else run qq-config.py field workflow. On prototype-loop, this review is not a step of the workflow: when invoked directly, run one round and stop (shared/prototype-loop.md §Design); on heavy-review (the default), follow this file as written.

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

Process

  1. Find the document: if a path is given, read it. Otherwise, find the most recent *_design.md in Docs/qq/.
  2. Spawn a review subagent (Agent tool) that reads design-reviewer-prompt.md and the design document, checks the document's claims against the codebase itself, and returns the review in that prompt's format.
  3. Verify, then present: check each finding yourself against the document and the code; the subagent can misread code or cite stale information. Present only the findings you confirmed, and say which ones you rejected and why.
  4. 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. Items moved to the document's "Needs the user's decision" list count as resolved.
  5. If verdict is SOLID: confirm and recommend /qq:plan. If invoked with --auto: 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>.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free