New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Gameplay Design Sync

by tangziwen in tangziwen/CubeMiniGame

Assess whether completed CubeGame gameplay changes should be reconciled into Doc/GameplayIntent design documents.

MITAuto-check passedDevelopment

Install Gameplay Design Sync

skills CLI
$ npx skills add tangziwen/CubeMiniGame --skill gameplay-design-sync -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install tangziwen/CubeMiniGame gameplay-design-sync --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/tangziwen/CubeMiniGame.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/gameplay-design-sync .claude/skills/gameplay-design-sync && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gameplay-design-sync
GitHub stars
359
Token cost
~1.5k tokens
SKILL.md length
702 words
Files
2
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Assess whether completed CubeGame gameplay changes should be reconciled into Doc/GameplayIntent design documents.

  • Works in 4 steps: AGENTS.md → Doc/GameplayIntent/README.md → the relevant existing design docs in… → …
  • Pure engine changes
  • SKILL.md covers Purpose, Hard Scope Gate, Required Reads and Update Rules, plus 2 more sections
  • Calls git

What it does

Gameplay Design Sync is an agent skill from tangziwen/CubeMiniGame. Assess whether completed CubeGame gameplay changes should be reconciled into Doc/GameplayIntent design documents. Use implicitly only after C/C++ source or header file changes under CubeEngine/Application/CubeGame, such as .c, .cc, .cpp, .cxx, .h, .hh, .hpp, .hxx, .inl, or .ipp, and only when the change may alter gameplay design intent, concrete design mechanisms, concepts, object relationships, aliases, or Concept Code Anchors. Ignore doc-only, build-only, asset-only, config-only, generated, formatting, and…

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Development, covering Architecture decision records, Game design and Refactoring. It works with C++. The repository describes itself as: HomeBrew C++ 3D Game Engine based on OpenGL & Vulkan. The licence is MIT.

When your agent uses it

  • Pure engine changes
  • Pure rendering/backend changes
  • Ordinary bug fixes
  • Helper/config/data-only additions

Example prompts

  • “/gameplay-design-sync”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. AGENTS.md
  2. Doc/GameplayIntent/README.md
  3. the relevant existing design docs in Doc/GameplayIntent/
  4. the completed change context: user request, CodePlan docs when present, changed-file list, and only the source files needed to confirm…

What it can do on your machine

Read from SKILL.md and the folder at commit 33b364c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gameplay Design Sync loads about 1.5k tokens when it runs. Until then it costs about 239 tokens; SKILL.md has 702 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~239
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from tangziwen/CubeMiniGame at commit 33b364c, republished under its MIT licence (© tangziwen). 702 words, ~1,524 tokens.

Download SKILL.mdSave it as .claude/skills/gameplay-design-sync/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
gameplay-design-sync
description
Assess whether completed CubeGame gameplay changes should be reconciled into Doc/GameplayIntent design documents. Use implicitly only after C/C++ source or header file changes under CubeEngine/Application/CubeGame, such as .c, .cc, .cpp, .cxx, .h, .hh, .hpp, .hxx, .inl, or .ipp, and only when the change may alter gameplay design intent, concrete design mechanisms, concepts, object relationships, aliases, or Concept Code Anchors. Ignore doc-only, build-only, asset-only, config-only, generated, formatting, and other non-code-file changes unless the user explicitly asks to evaluate gameplay design docs. First filter out pure engine/non-gameplay changes, then list candidate concept changes and ask the user before editing design docs. Do not use for pure engine changes, pure rendering/backend changes, ordinary bug fixes, helper/config/data-only additions, or implementation-only refactors that do not change gameplay concepts.

Gameplay Design Sync

Purpose

Assess whether Doc/GameplayIntent/ should be updated after a completed change under CubeEngine/Application/CubeGame.

This skill is not a CodeMap sync. It records designer intent, game concepts, concept aliases, object relationships, and very thin Concept Code Anchors.

Concepts are designer/gameplay concepts, not a code type inventory. A concept may map to one canonical code anchor, but many code types should have no design concept entry.

Hard Scope Gate

Before editing anything, inspect the changed-file list from conversation context, git diff --name-only, or the relevant CodePlan File Operations.

  • Treat only C/C++ source or header files as trigger files: .c, .cc, .cpp, .cxx, .h, .hh, .hpp, .hxx, .inl, and .ipp.
  • For implicit post-change use, if there are no changed trigger files under CubeEngine/Application/CubeGame/, stop and report that no gameplay intent sync is needed.
  • If the user explicitly asks to evaluate or update gameplay design docs, the skill may still run without trigger files, but treat non-code changes as supporting context and classify skip unless they clearly express a gameplay design change.
  • Ignore changed files with other extensions, including docs, build files, assets, generated files, scripts, config, shaders, and data files, when deciding whether the skill should run implicitly.
  • If changes are pure engine, renderer, backend, asset, build, formatting, or bug-fix work, stop unless the user explicitly says the gameplay design changed.
  • Ignore changes outside CubeEngine/Application/CubeGame/ when deciding design-doc content.
  • Do not update Doc/GameplayIntent/ for implementation-only refactors that preserve the same gameplay concepts.
  • Do not propose a new concept merely because a new code type exists.
  • Treat helper, config, data, view, visual, manager, and other auxiliary types as non-concepts by default unless the user request or design text makes them gameplay concepts.
  • Allow implementation-adjacent concepts when they directly participate in gameplay mechanisms, player actions, or design semantics.

Be conservative. No update is better than recording a transient or accidental design.

After the hard scope gate, do not edit design docs immediately. First summarize the candidate design changes, list any proposed new or changed concepts, and ask the user whether to sync them.

Required Reads

Read:

  1. AGENTS.md
  2. Doc/GameplayIntent/README.md
  3. the relevant existing design docs in Doc/GameplayIntent/
  4. the completed change context: user request, CodePlan docs when present, changed-file list, and only the source files needed to confirm concept-level changes

Do not scan unrelated gameplay files broadly.

Show full SKILL.md (316 more words)Show less

Update Rules

Update only long-lived design facts:

  • new or changed gameplay design intent
  • new or changed concrete design mechanisms under a Design section
  • new, renamed, merged, or split game concepts
  • changed object relationships or design boundaries
  • new concept aliases
  • changed thin concept-to-code-anchor mapping in Concept Code Anchors

Do not write:

  • function flow
  • implementation strategy
  • class internals
  • directory mirrors
  • complete file lists
  • temporary implementation notes
  • validation details

Concept names may have aliases, but Concept Code Anchors should list only canonical code anchors that exist in the current code.

Do not add helper/config/data-only types to Game Concepts or Concept Code Anchors unless they are explicitly part of the gameplay design vocabulary.

If a code type or structure has no direct design concept but is critical for TD-level orientation, especially important XXXSystem, manager, or helper types, put it in Critical Code Anchors instead of Game Concepts or Concept Code Anchors.

Use the document heading order from Doc/GameplayIntent/README.md: Design Intent, Experience, Design, Game Concepts, Concept Code Anchors, Design Boundaries. GameplayDesign.md may also contain Code Rules for broad gameplay code organization principles. Documents may contain Critical Code Anchors for important non-concept system/manager/helper names. Do not create a separate Non-goals heading.

Reconcile Workflow

  1. Classify the change as skip, needs-update, or blocked.
  2. If skip, explain briefly and stop.
  3. If blocked, ask for the missing design decision.
  4. If needs-update, summarize the proposed design-doc update, including the exact concepts or aliases to add/change, and ask the user for explicit confirmation.
  5. Only after confirmation, patch the smallest relevant design doc.
  6. Keep headings stable and preserve existing accepted design text unless the completed change replaces it.
  7. Run git diff --check for edited design docs.

Output

End with:

  • classification and reason
  • gameplay files considered
  • proposed concepts or aliases, if any
  • whether user confirmation was requested or received
  • design docs updated, if any
  • confirmation that pure non-gameplay changes were ignored
  • verification performed

© tangziwen, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/gameplay-design-sync of tangziwen/CubeMiniGame.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 33b364c

Compare with similar skills

Gameplay Design Sync next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gameplay Design Sync compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gameplay Design Sync this skilltangziwen/CubeMiniGame359—~1.5kAutomated safety check: PassMIT
Architecture FirstAnastasiyaW/codex-claude-code-config154—~2kAutomated safety check: PassMIT
Improve Codebase Architectureywwynm/EverythingDone14415 repos~1.3kAutomated safety check: PassGPL-3.0
Learning OpportunitiesDrCatHicks/learning-opportunities2.5k—~2.5kAutomated safety check: PassCC-BY-4.0
Extempore JIT Debugging Guidedigego/extempore1.5k—~4.4kAutomated safety check: PassNone
OpenROAD Bug FixerThe-OpenROAD-Project/OpenROAD3.2k—~784Automated safety check: PassBSD-3-Clause

Similar skills

  • Architecture First

    AnastasiyaW/codex-claude-code-config

    Decide module boundaries before the first file: what modules exist, which way dependencies point, who owns state, and what each module may know.

    154 GitHub stars~2k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Improve Codebase Architecture

    ywwynm/EverythingDone

    Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/.

    144 GitHub starsUsed in 15 repos~1.3k tokens
    DevelopmentAuto-check passed

  • Learning Opportunities

    DrCatHicks/learning-opportunities

    Facilitates deliberate skill development during AI-assisted coding.

    2.5k GitHub stars~2.5k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Extempore JIT Debugging Guide

    digego/extempore

    Debugging guide for Extempore covering its three layers, compilation paths, startup sequence and the batch, eval and interactive modes used to isolate JIT problems.

    1.5k GitHub stars~4.4k tokensUpdated 17 days ago
    DevelopmentAuto-check passed

  • OpenROAD Bug Fixer

    The-OpenROAD-Project/OpenROAD

    Fixes an OpenROAD bug from a GitHub issue or error code: finds the root cause, implements the fix, adds a regression test and prepares a signed-off commit.

    3.2k GitHub stars~784 tokensUpdated today
    DevelopmentAuto-check passed

  • Code Changes

    JanDeDobbeleer/oh-my-posh

    Workflow for any task that ends in code changes: issue analysis or triage, pull request review comments, features, bug fixes, refactors.

    24k GitHub stars~1.1k tokensUpdated today
    DevelopmentAuto-check passed

More from tangziwen/CubeMiniGame

All 12 skills in this repo

  • Cp Plan

    tangziwen/CubeMiniGame

    Create or update a CodePlan design.md from clarified requirements, repository observations, constraints, and architecture intent.

    359 GitHub stars~928 tokensUpdated 21 days ago
    Auto-check passed

  • Build Project

    tangziwen/CubeMiniGame

    Build the project using the CMake presets defined for this repository.

    359 GitHub stars~407 tokensUpdated 21 days ago
    Auto-check passed

  • Cp Apply

    tangziwen/CubeMiniGame

    Apply exactly one CodePlan step to the repository, with preflight idempotency checks and progress.md updates.

    359 GitHub stars~566 tokensUpdated 21 days ago
    Auto-check passed

  • Cp Explore

    tangziwen/CubeMiniGame

    Explore and clarify a prospective CodePlan before writing design.md.

    359 GitHub stars~535 tokensUpdated 21 days ago
    Auto-check passed

  • Cp Refine

    tangziwen/CubeMiniGame

    Refine a CodePlan design.md into precise step1.md through stepX.md files and progress.md.

    359 GitHub stars~512 tokensUpdated 21 days ago
    Auto-check passed

  • Cp Review

    tangziwen/CubeMiniGame

    Review CodePlan documents, including explored requirements, design.md, progress.md, and step files.

    359 GitHub stars~475 tokensUpdated 21 days ago
    Auto-check passed

Works with

Categories

Questions about Gameplay Design Sync

What does Gameplay Design Sync do?

Assess whether completed CubeGame gameplay changes should be reconciled into Doc/GameplayIntent design documents. Gameplay Design Sync is an agent skill from tangziwen/CubeMiniGame. Assess whether completed CubeGame gameplay changes should be reconciled into Doc/GameplayIntent design documents.

When should I use Gameplay Design Sync?

Gameplay Design Sync fits situations like: pure engine changes; pure rendering/backend changes; ordinary bug fixes; helper/config/data-only additions.

How do I install Gameplay Design Sync in Claude Code?

Run `npx skills add tangziwen/CubeMiniGame --skill gameplay-design-sync -a claude-code`. Or copy the skill folder (.agents/skills/gameplay-design-sync in tangziwen/CubeMiniGame) into .claude/skills/gameplay-design-sync in your project. Claude Code loads it when a task matches its description.

How do I install Gameplay Design Sync in Codex?

Run `npx skills add tangziwen/CubeMiniGame --skill gameplay-design-sync -a codex`. Or copy the skill folder (.agents/skills/gameplay-design-sync in tangziwen/CubeMiniGame) into .agents/skills/gameplay-design-sync in your project. Codex loads it when a task matches its description.

Can I use Gameplay Design Sync in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tangziwen/CubeMiniGame --skill gameplay-design-sync -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gameplay-design-sync, .gemini/skills/gameplay-design-sync, .github/skills/gameplay-design-sync and .opencode/skills/gameplay-design-sync in your project.

What does Gameplay Design Sync need to run?

Going by SKILL.md and its folder, Gameplay Design Sync needs the command-line tools its instructions call (git).

Does Gameplay Design Sync access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Gameplay Design Sync safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Gameplay Design Sync use?

Gameplay Design Sync is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gameplay Design Sync use?

About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gameplay Design Sync?

Skills that share tags, products or a category with Gameplay Design Sync: Architecture First (AnastasiyaW/codex-claude-code-config, 154 stars), Improve Codebase Architecture (ywwynm/EverythingDone, 144 stars), Learning Opportunities (DrCatHicks/learning-opportunities, 2.5k stars) and Extempore JIT Debugging Guide (digego/extempore, 1.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gameplay Design Sync?

tangziwen (a GitHub user) maintains it in tangziwen/CubeMiniGame, which has 359 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 19, 2026.

Source: tangziwen/CubeMiniGame on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.