agentleFS
KonHKonH/GlobalStrategy/.agents/skills/generate-image/SKILL.md

generate-image

Skill3 starsChanged 2 months agoMITView on GitHub

Generate project-bound raster assets with this repository's local ComfyUI and FLUX setup. Use when asked to create game icons, character portraits, card art, map thumbnails, or other PNG assets that should be saved in the Unity project rather than merely previewed in chat.

37 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use edit-image, scientific-slides and 6 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SamurAIGPTSkill

    edit-image

    Edits an existing image using natural language instructions via MuAPI. Use when the user wants to modify, change, transform, or retouch an existing image.

    Also in 3 projects that use this

  • ZanderRussSkill

    scientific-slides

    Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.

    Also in 3 projects that use this

  • nicepkgSkill

    team

    根据任务快速组建临时 AI Agent 团队协作。自动从 .claude/agents/ 中选择最合适的成员组队。

    Also in 3 projects that use this

  • AnthropicSkill

    pptx

    Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.

    Also in 5 projects that use this

  • AnthropicSkill

    pdf

    Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

    Also in 4 projects that use this

  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 5 projects that use this

  • +1 more from anthropics

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 4 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the local ComfyUI server and the repository's reusable scripts.

    line 8
  2. Very specific:

    Do not use this skill from a Ralph code-only or full-env-headless run.

    line 12
  3. Very specific:

    Keep generated project assets under their intended Assets/ path and do not overwrite an existing asset unless the request explicitly calls …

    line 13
  4. Distinctive:

    Never substitute a hosted generator, placeholder service, stock-image URL, or emoji glyph for a required game asset.

    line 14
  5. Very specific:

    If it is unavailable and ComfyUI/run_nvidia_gpu.bat exists, start it in a hidden detached process, then poll the endpoint for up to two …

    line 19
  6. Distinctive:

    If it is unavailable and ComfyUI is not installed, run the bundled resumable installer in the background:

    line 20
  7. Very specific:

    Read the log periodically.

    line 30
  8. Distinctive:

    If startup or installation fails, report the log error rather than silently switching tools.

    line 32
  9. Very specific:

    Run the existing script with the project virtual environment.

    line 37

“Common” is measured: kept by at least 6 in 10 of the 31 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Generate Game Image

Use the local ComfyUI server and the repository's reusable scripts. This skill is the canonical Codex workflow for the embedded image-generation setup.

Environment rules

  • Do not use this skill from a Ralph code-only or full-env-headless run. Those environments must leave Unity and image work untouched.
  • Keep generated project assets under their intended Assets/ path and do not overwrite an existing asset unless the request explicitly calls for it.
  • Never substitute a hosted generator, placeholder service, stock-image URL, or emoji glyph for a required game asset.

Ensure ComfyUI is ready

  1. Check http://127.0.0.1:8188/system_stats.
  2. If it is unavailable and ComfyUI/run_nvidia_gpu.bat exists, start it in a hidden detached process, then poll the endpoint for up to two minutes.
  3. If it is unavailable and ComfyUI is not installed, run the bundled resumable installer in the background:

    Start-Process -FilePath ".venv\Scripts\python.exe" `
      -ArgumentList ".agents\skills\generate-image\scripts\setup_comfyui.py --project-root ." `
      -WorkingDirectory (Get-Location) -WindowStyle Hidden `
      -RedirectStandardOutput ".tmp\comfyui_setup.log" `
      -RedirectStandardError ".tmp\comfyui_setup.err"

    Read the log periodically. The installer downloads the portable NVIDIA build and the non-gated FLUX.1-schnell checkpoint, VAE, and text encoders; it resumes partial downloads. When it reports === All done ===, start ComfyUI and repeat the endpoint check.

  4. If startup or installation fails, report the log error rather than silently switching tools.

Generate one asset

  1. Choose an output path and a size appropriate for the Unity use case. Use 512x512 for character portraits unless the request says otherwise.
  2. Run the existing script with the project virtual environment. Prefix the command with PYTHONUTF8=1 when the prompt contains non-ASCII text.

    $env:PYTHONUTF8 = '1'
    & ".venv\Scripts\python.exe" "scripts\utils\generate_image.py" "<output-path>" "<width>x<height>" "<prompt>"
  3. Inspect the generated PNG before reporting it. For a Unity-bound asset, follow the relevant Unity import and .meta rules, then refresh Unity and check the console when an interactive Editor is available.

Generate several assets

For a batch, create .tmp/images.json with entries shaped as { "output", "size", "prompt" }, then run:

$env:PYTHONUTF8 = '1'
& ".venv\Scripts\python.exe" "scripts\utils\generate_images_batch.py" ".tmp\images.json"

The batch stops with an error when any entry fails. Report successful and failed paths separately; do not claim a partial batch is complete.

Prompt and asset guidance

  • State the subject, intended in-game use, visual style, composition, palette, and exclusions. Require no text or watermark unless text is explicitly needed.
  • For icons, ask for a simple high-contrast silhouette that remains legible at its rendered size.
  • For portrait prompts and regional/role wording, read portrait-recipes.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.