claude

tiny-anvil

Skills for building whole apps and games autonomously, evidence first: a .NET + Vue web app with CI/CD and deployment, or a Godot game with Blender assets and audio, from one setup round to a verified result.

1 on GitHubby Tiny Anvilv0.2.0MITupdated 6 days agodevelopment
/

Plugin tiny-anvil from marketplace tiny-anvil in Tiny-Anvil/agent-skills. Commands read from the repo's manifest — 5 days ago.

What it installs

Skills (15)

  • building-blender-assets-by-script

    Use when creating game assets in Blender by Python script for a Godot game (modular kits, props, physics props, first-person rigs, characters, baked textures), when preparing generated, purchased or mocap models for the game, or when Blender exports reach Godot with wrong axes, missing collision, lo

  • deploying-container-images

    Use when a versioned container image already in a registry has to reach an environment (test, acc, prod) — bumping the image tag in a GitOps repo (Kustomize or Helm, Argo CD or Flux) through a pull request, deploying to Azure Container Apps, or another target — or when a pipeline is green but the en

  • designing-app-listing-images

    Use when an app needs the images it is listed with — App Store or Google Play screenshot sets, a Play feature graphic, a link-preview (Open Graph) image, PWA install-dialog screenshots or a landing-page hero — made from its real screens, on demand or in an app run's finish pass; when store screensho

  • designing-game-store-pages

    Use when a game needs its store-page kit — Steam capsules (header, small, main, vertical), library art (capsule, header, hero, logo), community icons, gameplay screenshots, a gameplay trailer, an itch.io cover — made from the real game, on demand or in a game run's finish pass; when capsule art brea

  • dotnet-vue-test-harness

    Use when a .NET minimal API + Vue.js app needs tests that prove behaviour through the real stack — API integration tests against a real Postgres (Testcontainers), real-JWT and scope tests, guard tests, Vue component tests, Playwright end-to-end flows and screenshots, load numbers, or a preview copy

  • github-cicd-dotnet-vue

    Use when setting up or changing GitHub Actions for a .NET API + Vue.js app — PR build/test gates, security scanning, licence checks, Dependabot, and building versioned container images (single or multi-arch) and publishing them to GHCR or another registry from a GitHub release — or when a gate silen

  • godot-scenario-harness

    Use when a Godot 4 project needs unattended screenshots or clips from the real game, scripted bot scenarios, input record/playback, or measured feel/solidity/performance tests (camera jitter, snap, tunnelling, stuck, frame time); when capture runs hang, come out blank or show the wrong pose; or when

  • iterating-with-look-checkpoints

    Use when building or polishing anything in a game whose correctness is visible or felt (art, shaders, VFX, lighting, animation, camera, movement feel, UI, audio feedback); before reporting such work done or writing "eyes-on pending"; when comparing before/after a visual fix; or when successive visua

  • iterating-with-verified-increments

    Use when building or polishing a web application (.NET API, Vue.js frontend) whose correctness must be shown by running it — features, UI screens, auth, data flows, performance, deployment; before reporting such work done or writing "needs manual testing"; when comparing before/after a fix; or when

  • running-autonomous-app-builds

    Use when asked to build a whole web application or a large standalone feature (.NET backend, Vue.js frontend, GitHub CI/CD) autonomously from an idea to a finished, verified, deployed result — "build it end to end", "make it as good as you can", "work on it overnight" — or when resuming such a run a

  • running-autonomous-game-builds

    Use when asked to build a whole game (or a large standalone feature) autonomously from an idea to a finished, verified result — "build it end to end", "make it as good as you can", "work on it overnight" — or when resuming such a run after a pause, a review or a context limit.

  • sourcing-and-processing-game-audio

    Use when a game needs sound effects, ambience loops or music from real recordings or free libraries (Pixabay, Freesound and similar) — choosing and downloading them, recording their licences, editing and levelling them, making seamless loops, wiring them into Godot — or when a loop clicks, levels ar

  • tripo-cli

    Use when generating, texturing, rigging, retargeting or converting 3D models with Tripo3D (text or image to 3D) through the `tripo` CLI — checking access or credit balance, validating a request before spending credits, or handling a Tripo exit code or error.

  • writing-app-briefs

    Use when turning a web application, service, milestone or major feature idea (.NET API, Vue.js frontend) into the document another agent or session will build from unattended, when a spec's requirements have no measurable pass criteria, or when "done" would otherwise be decided by "the owner clicks

  • writing-game-briefs

    Use when turning a game, prototype, milestone or major feature idea into the document another agent or session will build from unattended, when a spec's requirements have no measurable pass criteria or no required captures, or when "done" for visual/feel work would otherwise be decided by "the owner

Slash commands (7)

  • /tiny-anvil:build-app

    Build a whole web app (.NET API + Vue SPA + CI/CD) autonomously, from one setup round to a verified, deployed result.

  • /tiny-anvil:build-game

    Build a whole game (Godot 4, Blender assets, audio) autonomously, from one setup round to a verified result.

  • /tiny-anvil:deploy

    Deploy a published image version to one environment (GitOps PR, Azure Container Apps or other) and verify it runs there.

  • /tiny-anvil:listing-images

    Make an app's listing images (App Store / Google Play screenshots, link preview, PWA install screenshots) from its real screens.

  • /tiny-anvil:resume-run

    Resume an autonomous app or game run in this directory after a pause, a review or a context limit.

  • /tiny-anvil:store-page

    Make a game's store-page kit (Steam capsules, library art, screenshots, gameplay trailer, itch.io cover) from the real game.

  • /tiny-anvil:write-brief

    Turn an app or game idea into a brief with numbered, measurable tests, without starting a build.

View source on GitHub

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

nextjs

claude

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

6 skills

vercel/next.js 143,495

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

Maintain tiny-anvil?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted