agentleFS
Sign inStart free
Kevin-Liu-01Kevin-Liu-01/Claude-of-Tanks/SKILL.md

claude-of-tanks-skill

Skill531 starsChanged 3 months agoMITView on GitHub

Build and verify Claude of Tanks without crossing simulation, rendering, fleet-generation, or shared-worktree ownership boundaries.

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. Distinctive:

    Keep rendering/presentation out of headless simulation and network modules.

    line 28
  2. Very specific:

    Verify focused behavior first, then npm test and the public build.

    line 30

≈ “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

claude-of-tanks — working here

Purpose

<!-- agent-docs:fill:purpose -->

Ship the browser game while preserving deterministic combat, first-party tank fidelity, smooth low-end performance, and reproducible visual/test evidence.

Mental model & key files

<!-- agent-docs:fill:model -->

src/main.ts is the shrinking composition root; extracted lifecycle owners are strict TypeScript modules documented in docs/SYSTEMS.md and docs/DECISIONS.md. src/game/state.ts owns solo integration, src/sim/ owns gameplay truth, src/mp/ owns the peer-to-peer multiplayer, and tools/ contains performance, fleet, screenshot, and release gates. Start with docs/SYSTEMS.md and the nearest directory SKILL.md.

Patterns to follow / invariants

<!-- agent-docs:fill:patterns -->
  • Work from the current remote safe boundary in an isolated worktree when the shared checkout is dirty or another tank-generation task is active.
  • Preserve fixed-step semantics and seeded randomness.
  • Keep rendering/presentation out of headless simulation and network modules.
  • Make optional/high-cost features dynamically reachable, not boot-critical.
  • Verify focused behavior first, then npm test and the public build.

Common tasks → first action

<!-- agent-docs:fill:tasks -->
  • Runtime flow: trace src/main.ts plus src/game/state.ts exports.
  • Physics/combat: read src/sim/SKILL.md, then its existing selftests.
  • UI: read src/ui/SKILL.md and inspect the rendered browser surface.
  • Multiplayer: read docs/MULTIPLAYER-V2.md and src/mp/README.md.
  • Tank creation/rebuild/markup repair: read docs/tank-generation/SKILL.md, src/vehicles/SKILL.md and the latest per-tank/batch packet; use the handbook's source-freeze, gate, prompt and handoff templates.
  • Performance: capture a baseline with the committed probes before editing.

Gotchas

<!-- agent-docs:fill:gotchas -->

The root checkout is frequently mixed dirty and may lag hundreds of tank commits. Do not pull, reset, clean, or blanket-stage it. Public builds strip quarantined assets; both a green build and runtime provenance checks matter.

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