agentsclimarketplace

Wavedash

Skill wvdsh/ai/providers/openai/plugin/skills/wavedash

Use when building, integrating, testing, uploading, publishing, or preparing a browser game for Wavedash, including CLI setup, Wavedash SDK features, multiplayer, achievements, leaderboards, cloud saves, player identity, user-generated content, store metadata, monetization, and content guidelines.From its SKILL.md

Install
npx -y skills add wvdsh/ai --skill wavedash

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

  • 1 stars1 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

3.2 KB, 662 tokens by cl100k_base, as published. Nobody here has run it

Wavedash

Use this skill to get a game from local project to tested, uploaded, and publishable on Wavedash. Official docs are canonical; this skill routes the agent to the right docs and highlights traps agents commonly miss.

Always do this

  1. Identify whether the user is starting from an existing game or from zero. If no game exists yet, create a small browser-playable game first.
  2. Identify the engine/framework, build command, output directory, and requested Wavedash features.
  3. If the Wavedash MCP server is available, call wavedash_implementation_planner before making architecture claims, selecting SDK features, or writing Wavedash integration code. Treat the planner's docs list and boundaries as the routing source for the next steps.
  4. Read the relevant reference file before changing code or giving detailed instructions. Do not invent SDK methods, event names, constants, CLI flags, monetization rules, or content-policy exceptions.
  5. Prefer the CLI for local testing and scripted upload/publish workflows.
  6. Publish only when the user explicitly asks to make a build live.
  7. Use WAVEDASH_TOKEN and --json --no-color --no-update-check in CI, cloud-agent, or other headless automation contexts.

Routing

User taskRead first
Start a new game from zero, scaffold a browser game, choose a frameworkreferences/project-start.md
Install CLI, authenticate, initialize, test locally, upload, publishreferences/cli.md
Add or fix SDK calls, player identity, load lifecycle, eventsreferences/sdk.md
Add multiplayer, lobbies, networkingreferences/sdk.md
Add achievements, stats, leaderboards, cloud saves, UGC, paid contentreferences/sdk.md
Prepare store page, metadata, monetization, content policy, launch checklistreferences/publishing.md
Fix launch-quality issues like shader stutter, Escape key, audio, memoryreferences/game-quality.md
Determine engine-specific build/export stepsreferences/engines.md
Need all docs URLs or raw Markdown linksreferences/docs-map.md

Critical rules

  • Every Wavedash game must call Wavedash.init() or the engine binding equivalent; otherwise the game can stay hidden behind the loading screen.
  • A new game must produce static browser files with an index.html; Wavedash is not a server runtime for native binaries or backend services.
  • Test with wavedash dev when possible, then smoke-test the uploaded build on Wavedash after upload.
  • Do not use Escape as the only pause/menu key; browsers reserve it for fullscreen and pointer-lock exit.
  • Warm up shaders/materials before gameplay to avoid first-use stutter.
  • Do not present crypto, NFT, real-money gambling, malware, hateful, sexual, or otherwise disallowed content as acceptable for Wavedash.
  • Never commit API keys, tokens, private user data, or generated credentials.

What ships with it: 7 files

18.5 KB alongside SKILL.md

references/

Keep looking

Skills are one crate of 326,144. 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.