planning-with-files
Optional persistent file-based planning for multi-phase or long-running work that benefits from recovery across sessions or…
Build or iterate on HTML/JavaScript games with a short Playwright verification loop, screenshot and console inspection, and render_game_to_text state checks. Use for playable browser-game implementation or debugging.
$ npx -y skills add khaneliman/khanelinix --skill develop-web-game --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/develop-web-gameContext preview
The summary Claude sees to decide when to auto-load this skill.
Build or iterate on HTML/JavaScript games with a short Playwright verification loop, screenshot and console inspection, and render_game_to_text state checks. Use for playable browser-game implementation or debugging.
name: "develop-web-game" description: "Build or iterate on HTML/JavaScript games with a short Playwright verification loop, screenshot and console inspection, and render_game_to_text state checks. Use for playable browser-game implementation or debugging." metadata: disable-model-selection: "true"
Build games in small verified steps: implement, run short input bursts, inspect text state plus screenshots, fix, repeat.
time, fullscreen.
Resolve the absolute directory containing this `SKILL.md`, then set `WEB_GAME_CLIENT` to `scripts/web_game_playwright_client.js` and `WEB_GAME_ACTIONS` to `references/action_payloads.json` beneath that directory. Read [references/setup.md](references/setup.md) when either path or Playwright availability is unclear.
1. Define one feature/behavior goal. 2. Make smallest coherent code change. 3. Run `$WEB_GAME_CLIENT` with short input bursts after each meaningful change. 4. Inspect latest text output, screenshot, and console errors. 5. Verify all affected controls and state transitions end-to-end. 6. Fix first concrete failure, then rerun. 7. Reset between unrelated scenarios.
Read only focused references needed for current game task.
Example:
node "$WEB_GAME_CLIENT" --url http://localhost:5173 --actions-file "$WEB_GAME_ACTIONS" --iterations 3 --pause-ms 250
Run packages directly with: Or install from the packages output. For example:
Optional persistent file-based planning for multi-phase or long-running work that benefits from recovery across sessions or…
Audit coding-agent sessions and mine cross-harness history for recurring corrections, skill-routing gaps, and harness faults. Use…
Design and audit agent instructions, skills, plugins, subagents, prompts, hooks, and provider configuration. Use for AI-tool…
Sketch interfaces, state, and module structure before code. Use for explicit design-led implementation or as a caller-owned…
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena,…
Bevy workflows for ECS, migrations, first-party UI/input/rendering/assets/shaders, plugin selection, scenes, scheduling, hot…