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

Game Performance

by CoWork-OS in CoWork-OS/CoWork-OS

Cross-engine game performance: draw call optimization, LOD, object pooling, GPU profiling, memory management, and platform-specific tuning.

MITAuto-check passedGame Development

Install Game Performance

skills CLI
$ npx skills add CoWork-OS/CoWork-OS --skill game-performance -a claude-code

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

GitHub CLI
$ gh skill install CoWork-OS/CoWork-OS game-performance --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/CoWork-OS/CoWork-OS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/resources/skills/game-performance .claude/skills/game-performance && 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
game-performance
GitHub stars
477
Token cost
~494 tokens
SKILL.md length
210 words
Files
3 (incl. scripts, references)
Skills in repo
46
Repo updated
First seen
Licence
MIT

At a glance

Cross-engine game performance: draw call optimization, LOD, object pooling, GPU profiling, memory management, and platform-specific tuning.

  • Tasks that involve Performance optimization
  • SKILL.md covers Purpose, Routing, Trigger Examples and Runtime Prompt

What it does

Game Performance is an agent skill from CoWork-OS/CoWork-OS. Cross-engine game performance: draw call optimization, LOD, object pooling, GPU profiling, memory management, and platform-specific tuning.

Its SKILL.md is about 490 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts and reference files (for example `references/full-guidance.md`).

It sits in Game Development, covering Performance optimization. The repository describes itself as: Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts. The licence is MIT.

When your agent uses it

  • Tasks that involve Performance optimization

Example prompts

  • “/game-performance”

What it can do on your machine

Read from SKILL.md and the folder at commit 0ace02b. 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

    Ships 1 file in scripts/, which the agent can run.

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

  • Network

    No URLs in SKILL.md.

    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

Game Performance loads about 494 tokens when it runs, and up to ~2.2k if it reads all its reference files. Until then it costs about 39 tokens; SKILL.md has 210 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~494
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.2k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from CoWork-OS/CoWork-OS at commit 0ace02b, republished under its MIT licence (© CoWork-OS). 210 words, ~494 tokens.

Download SKILL.mdSave it as .claude/skills/game-performance/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
game-performance
description
Cross-engine game performance: draw call optimization, LOD, object pooling, GPU profiling, memory management, and platform-specific tuning.
version
1.0.0
metadata.author
CoWork OS Contributors <info@coworkosapp.com>

Game Performance Optimization

Purpose

Cross-engine game performance: draw call optimization, LOD, object pooling, GPU profiling, memory management, and platform-specific tuning.

Routing

  • Use when: Use when the user asks about game performance optimization, FPS improvement, draw call reduction, LOD configuration, object pooling, GPU profiling, memory optimization, or frame time budgeting in any game engine.
  • Do not use when: Do not use for engine-specific coding tasks (use unity-development or unreal-development), or web/app performance optimization unrelated to games.
  • Outputs: Performance analysis, optimization strategies, profiling guidance, and engine-specific configuration.
  • Success criteria: Returns actionable optimization steps with measurable targets (FPS, draw calls, memory).

Trigger Examples

Positive
  • Use the game-performance skill for this request.
  • Help me with game performance optimization.
  • Use when the user asks about game performance optimization, FPS improvement, draw call reduction, LOD configuration, object pooling, GPU profiling, memory optimization, or frame time budgeting in any game engine.
  • Game Performance Optimization: provide an actionable result.
Negative
  • Do not use for engine-specific coding tasks (use unity-development or unreal-development), or web/app performance optimization unrelated to games.
  • Do not use game-performance for unrelated requests.
  • This request is outside game performance optimization scope.
  • This is conceptual discussion only; no tool workflow is needed.

Runtime Prompt

  • Current runtime prompt length: 979 characters.
  • Runtime prompt is defined directly in ../game-performance.json.

© CoWork-OS, 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 2 other files (scripts, references) in resources/skills/game-performance of CoWork-OS/CoWork-OS.

  • SKILL.md
  • references/full-guidance.md
  • scripts/.gitkeep

Open the folder on GitHubat commit 0ace02b

Compare with similar skills

Game Performance 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.

Game Performance compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Game Performance this skillCoWork-OS/CoWork-OS477—~494Automated safety check: PassMIT
Threejs Debug Profilervalkor-ai/loom1.2k1 repos~602Automated safety check: PassApache-2.0
Profiler Capture FrameIvanMurzak/Unity-MCP4.4k—~839Automated safety check: PassApache-2.0
Profiler Get Rendering StatsIvanMurzak/Unity-MCP4.4k—~833Automated safety check: PassApache-2.0
Profiler Get StatusIvanMurzak/Unity-MCP4.4k—~769Automated safety check: PassApache-2.0
Profiler Save DataIvanMurzak/Unity-MCP4.4k—~501Automated safety check: PassApache-2.0

Similar skills

  • Threejs Debug Profiler

    valkor-ai/loom

    Debug and profile Three.js browser games: blank canvases, render and runtime bugs, asset and audio loading, animation, resize, mobile input, plus performance profiling of draw calls, triangles…

    1.2k GitHub starsUsed in 1 repo~602 tokens
    Game DevelopmentAuto-check passed

  • Profiler Capture Frame

    IvanMurzak/Unity-MCP

    Capture the current frame's timing info (delta time, FPS, frame counts, runtime).

    4.4k GitHub stars~839 tokensUpdated today
    Game DevelopmentAuto-check passed

  • Profiler Get Rendering Stats

    IvanMurzak/Unity-MCP

    Return current frame timing, FPS, vsync, target frame rate, threading mode, and graphics device type from Unity Time / QualitySettings / SystemInfo.

    4.4k GitHub stars~833 tokensUpdated today
    Game DevelopmentAuto-check passed

  • Profiler Get Status

    IvanMurzak/Unity-MCP

    Return the Unity profiler's current enabled state, active modules, max-used memory, and platform support flag.

    4.4k GitHub stars~769 tokensUpdated today
    Game DevelopmentAuto-check passed

  • Profiler Save Data

    IvanMurzak/Unity-MCP

    Save a snapshot of profiler-derived stats (status + memory + rendering + script + frame capture) to a JSON file.

    4.4k GitHub stars~501 tokensUpdated today
    Game DevelopmentAuto-check passed

  • Profiler Start

    IvanMurzak/Unity-MCP

    Enable Unity's runtime profiler and open the Profiler window.

    4.4k GitHub stars~432 tokensUpdated today
    Game DevelopmentAuto-check passed

More from CoWork-OS/CoWork-OS

All 46 skills in this repo

  • Calendly

    CoWork-OS/CoWork-OS

    Manage Calendly scheduling via the v2 API. An agent skill from CoWork-OS/CoWork-OS.

    477 GitHub stars~595 tokensUpdated today
    Auto-check passed

  • Humanizer

    CoWork-OS/CoWork-OS

    Rewrite AI-generated text to sound natural and human-written.

    477 GitHub stars~557 tokensUpdated today
    Auto-check passed

  • Marketing Strategist

    CoWork-OS/CoWork-OS

    Comprehensive marketing strategy across 25 disciplines — positioning, copywriting frameworks, buyer psychology, SEO, CRO, paid ads, funnel architecture, content strategy, growth loops, analytics…

    477 GitHub stars~893 tokensUpdated today
    Auto-check passed

  • Moltbook

    CoWork-OS/CoWork-OS

    Interact with Moltbook — the social network for AI agents. An agent skill from CoWork-OS/CoWork-OS.

    477 GitHub stars~579 tokensUpdated today
    Auto-check passed

  • Polymarket

    CoWork-OS/CoWork-OS

    Query Polymarket prediction markets — search events, check odds and prices, view trending markets, track price momentum, get orderbook depth, analyze volume, and monitor market resolution timelines.

    477 GitHub stars~616 tokensUpdated today
    Auto-check passed

  • Skill Creator

    CoWork-OS/CoWork-OS

    Create or update AgentSkills for CoWork-OSS. An agent skill from CoWork-OS/CoWork-OS.

    477 GitHub stars~493 tokensUpdated today
    Auto-check passed

Categories

Questions about Game Performance

What does Game Performance do?

Cross-engine game performance: draw call optimization, LOD, object pooling, GPU profiling, memory management, and platform-specific tuning. Game Performance is an agent skill from CoWork-OS/CoWork-OS. Cross-engine game performance: draw call optimization, LOD, object pooling, GPU profiling, memory management, and platform-specific tuning.

When should I use Game Performance?

Game Performance fits situations like: tasks that involve Performance optimization.

How do I install Game Performance in Claude Code?

Run `npx skills add CoWork-OS/CoWork-OS --skill game-performance -a claude-code`. Or copy the skill folder (resources/skills/game-performance in CoWork-OS/CoWork-OS) into .claude/skills/game-performance in your project. Claude Code loads it when a task matches its description.

How do I install Game Performance in Codex?

Run `npx skills add CoWork-OS/CoWork-OS --skill game-performance -a codex`. Or copy the skill folder (resources/skills/game-performance in CoWork-OS/CoWork-OS) into .agents/skills/game-performance in your project. Codex loads it when a task matches its description.

Can I use Game Performance 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 CoWork-OS/CoWork-OS --skill game-performance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/game-performance, .gemini/skills/game-performance, .github/skills/game-performance and .opencode/skills/game-performance in your project.

What does Game Performance need to run?

SKILL.md names no scripts, command-line tools or credentials: Game Performance is instructions for the agent only.

Does Game Performance access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Game Performance 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Game Performance use?

Game Performance 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 Game Performance use?

About 494 tokens (SKILL.md is roughly 2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.7k tokens, read only when the agent opens those files.

What are the alternatives to Game Performance?

Skills that share tags, products or a category with Game Performance: Threejs Debug Profiler (valkor-ai/loom, 1.2k stars), Profiler Capture Frame (IvanMurzak/Unity-MCP, 4.4k stars), Profiler Get Rendering Stats (IvanMurzak/Unity-MCP, 4.4k stars) and Profiler Get Status (IvanMurzak/Unity-MCP, 4.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Game Performance?

CoWork-OS (a GitHub organization) maintains it in CoWork-OS/CoWork-OS, which has 477 GitHub stars. The repository holds 46 skills in this directory. The repository was last updated on October 9, 2026.

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