agentsclimarketplace

Gsp loop bootstrap

Skill mike007jd/game-superpowers/publish/clawhub/gsp-loop-bootstrap

Skills-first game development superpowers for Claude Code and Codex: build, audit, polish, and productionize game projects with reusable Agent Skills.

Install
npx -y skills add mike007jd/game-superpowers --skill gsp-loop-bootstrap

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

  • 5 stars5 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.

What its author says it does

Copied from the file, not written here

Use when establishing core game runtime structure such as state flow, control, camera, and UI ownership.

SKILL.md

1.0 KB, 191 tokens by cl100k_base, as published. Nobody here has run it

Game Loop Bootstrap

Goal

Create a maintainable gameplay architecture that matches the chosen target quality.

Outputs

Follow the gsp-orchestrator output strategy:

  • inline (default): present architecture decisions in conversation.
  • minimal or full: write or update docs/game-studio/architecture.md.

Prefer abstractions like

  • GameManager
  • InputProfile
  • StateMachine
  • PlayerController
  • CameraRig
  • HUDFlow
  • SoundLayer
  • EncounterDirector

Rules

  • Separate simulation state and UI state clearly enough to reason about them.
  • Avoid hiding critical gameplay state inside presentation objects.
  • Choose the simplest architecture that still supports the requested result.
  • In aggressive greenfield modes, do not fear building a complete coherent shell if it prevents later churn.
  • In live modes, preserve compatibility unless a deliberate migration plan exists.

What ships with it: 5 files

3.9 KB alongside SKILL.md

examples/

tests/

Gives 0 of the 12 instructions most project setup skills give in 191 tokens

Counted across 999 of the 1,637 authors here whose files we hold, read 2026-08-07

  • Ask one question at a timein 29 of 999, across 28 files
  • Detect the package manager from lockfilesin 28 of 999, across 9 files
  • Present findings to the userin 26 of 999, across 5 files
  • Explore current repo statein 24 of 999, across 3 files
  • Update the agent skills block in place if it existsin 24 of 999, across 3 files
  • Install husky lint-staged and prettierin 23 of 999, across 4 files
  • Create the lintstagedrc filein 22 of 999, across 3 files
  • Commit all changed filesin 22 of 999, across 3 files
  • Run lint-staged to verify it worksin 22 of 999, across 3 files
  • Create the husky pre-commit filein 21 of 999, across 2 files
  • Create a prettierrc file if missingin 21 of 999, across 2 files
  • Initialize huskyin 21 of 999, across 2 files

Said here and by no other author read

  • separate simulation state and UI state
  • avoid hiding critical state in presentation objects
  • choose the simplest sufficient architecture
  • use named abstractions like GameManager
  • build a complete shell in greenfield modes
  • preserve compatibility in live modes

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 328,083. 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.