agentsclimarketplace
Sign in

Gsp build review

Skill mike007jd/game-superpowers/publish/clawhub/gsp-build-review

Use when reviewing a built or in-progress game against the locked brief before claiming completion.From its SKILL.md

Install
npx -y skills add mike007jd/game-superpowers --skill gsp-build-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.2 KB, 221 tokens by cl100k_base, as published. Nobody here has run it

Game Build Review

Goal

Default review stage between implementation and runtime verification. Catch shape drift, weak scope decisions, and fake-complete output before verifier time is spent.

Outputs

Follow the gsp-orchestrator output strategy:

  • inline (default): present review findings in conversation.
  • minimal or full: write docs/game-studio/build-review.md.

Review focus

  • does the current build still match the locked game form
  • does the implementation match the approved brief and current task plan
  • are the requested core verbs and loops actually present
  • is the result fake-complete, placeholder-heavy, or missing obvious quality-critical work
  • did the builder introduce unnecessary complexity or unrelated scope
  • are the next fixes better handled before runtime verification

Reporting rules

For each issue, report:

  • severity: critical / important / minor
  • evidence source
  • short repair direction

Important

This is not the runtime verifier. Review the implementation against the concept, brief, and plan so the verifier receives a build worth testing.

What ships with it: 5 files

3.9 KB alongside SKILL.md

examples/

tests/

Gives 0 of the 12 instructions most review quality skills give in 221 tokens

Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07

  • Ask questions one at a timein 81 of 1048, across 64 files
  • Provide a recommended answer for each questionin 73 of 1048, across 50 files
  • Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
  • Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
  • Interview the user relentlessly about the planin 38 of 1048, across 13 files
  • Order findings by severityin 31 of 1048
  • Resolve each branch of the decision treein 27 of 1048, across 5 files
  • Run a grilling sessionin 26 of 1048, across 5 files
  • Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
  • Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
  • Create documentation files lazilyin 24 of 1048, across 5 files
  • Assign severity to every findingin 24 of 1048

Said here and by no other author read

  • compare the build against the locked game form
  • compare the implementation against the approved brief
  • verify requested core verbs and loops are present
  • check for fake-complete or placeholder-heavy output
  • report evidence source for each issue
  • report short repair direction for each issue

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,569. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.