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

Reference Images

by ukanwat in ukanwat/overtime

Find and actually LOOK at real photographs — keyless image-search APIs, downloaded to disk so they render as images.

MITAuto-check passedGame Development

Install Reference Images

skills CLI
$ npx skills add ukanwat/overtime --skill reference-images -a claude-code

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

GitHub CLI
$ gh skill install ukanwat/overtime reference-images --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/ukanwat/overtime.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/reference-images .claude/skills/reference-images && 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
reference-images
GitHub stars
387
Token cost
~1k tokens
SKILL.md length
450 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Find and actually LOOK at real photographs — keyless image-search APIs, downloaded to disk so they render as images.

  • Game Development work in your project
  • SKILL.md covers Sources that need no key (all… and Use it for far more than "the…
  • Calls curl and python3; reaches api.openverse.org and commons.wikimedia.org

What it does

Reference Images is an agent skill from ukanwat/overtime. Find and actually LOOK at real photographs — keyless image-search APIs, downloaded to disk so they render as images. Use before building any place, material, vehicle, sky or lighting condition, and again when judging your own screenshots.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Game Development. The repository describes itself as: Give a coding agent a brief, not a chat, and it works on its own across sessions. Includes an example run: an open-world city built in a real game engine with no human help. In… The licence is MIT.

When your agent uses it

  • Game Development work in your project

Example prompts

  • “/reference-images”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit fc215d4. 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:

    • curl
    • python3

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.openverse.org
    • commons.wikimedia.org
    • api.openstreetcam.org

    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

Reference Images loads about 1k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 450 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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 ukanwat/overtime at commit fc215d4, republished under its MIT licence (© ukanwat). 450 words, ~1,026 tokens.

Download SKILL.mdSave it as .claude/skills/reference-images/SKILL.md (or your agent's skills folder).
name
reference-images
description
Find and actually LOOK at real photographs — keyless image-search APIs, downloaded to disk so they render as images. Use before building any place, material, vehicle, sky or lighting condition, and again when judging your own screenshots.

Looking at real photographs

WebSearch returns text and WebFetch returns markdown — neither gives you an image. To see a photo you must download it and Read the file:

bash
mkdir -p ref/strand
# 1. SEARCH — Openverse: CC-licensed, no API key. KEEP QUERIES TO 2–3 WORDS.
#    Every term is ANDed, so "miami south beach art deco dusk" returns ZERO results.
curl -s -A "agent/1.0" \
  "https://api.openverse.org/v1/images/?q=art+deco+hotel&page_size=8" \
  | python3 -c "import json,sys; [print(r['url']) for r in json.load(sys.stdin)['results']]"

# 2. DOWNLOAD
curl -sL -A "agent/1.0" -o ref/strand/deco1.jpg "<url from above>"

# 3. LOOK at it — Read the local file; images render for you.

Then read your own screenshot of the same subject and name the gap out loud: "real facades have setbacks, AC units and stained concrete; mine are flat", "the real kerb has a ramp, a drain and a meter every third car; mine is a clean extrusion", "real asphalt is bluer, patched, and the lane paint is worn through in the wheel tracks", "the real light is warmer and lower and the shadows are longer". A named gap is a work item; "make it better" is not.

Sources that need no key (all verified working)

  • Openverse — keyword photo search, direct image URLs. The everyday default. https://api.openverse.org/v1/images/?q=<2-3+words>&page_size=10 Trap: multi-word queries are ANDed. Two or three words, or you get nothing.
  • Wikimedia Commons search — landmarks, aerials, named buildings. https://commons.wikimedia.org/w/api.php?action=query&generator=search&gsrsearch=<query>&gsrnamespace=6&gsrlimit=5&prop=imageinfo&iiprop=url&iiurlwidth=1600&format=json Send a User-Agent. gsrnamespace=6 is required. Do NOT add filetype:bitmap — it breaks the query and no query key comes back. Read imageinfo[0].thumburl.
  • Wikimedia geosearch — every photo taken near a real coordinate. This is how you study a real place rather than a word. https://commons.wikimedia.org/w/api.php?action=query&generator=geosearch&ggscoord=<lat>%7C<lon>&ggsradius=1000&ggslimit=10&ggsnamespace=6&prop=imageinfo&iiprop=url&iiurlwidth=1600&format=json
  • KartaView — street-level photography from a car windscreen, at any coordinate. https://api.openstreetcam.org/2.0/photo/?lat=<lat>&lng=<lng>&radius=400 Read result.data[].fileurlProc. The most valuable source you have: it is your exact game camera — driver eye height, kerb to kerb, real parked-car spacing, real pole and cable spans, real sky. One of these tells you more about how a street reads than an hour of guessing.
  • Aerial/satellite imagery of a real city: see the map-data source doc.
Show full SKILL.md (184 more words)Show less

Use it for far more than "the city"

Vehicle proportions, paint and glass tint, wheels, plates. Road markings and their wear. Kerbs, drains, ramps. Traffic signals and how they're mounted. Street-lighting colour by era. Overhead cables. Palm and street-tree shapes. Awnings and their frames. Shopfront signage typography. Roof clutter, aerials, dishes, laundry, bins, pallets. Tide lines and beach litter. Wet asphalt at night, neon reflections, dusk sky gradients. Crowd density and how people actually cluster on a pavement.

Anything you are about to guess at, fetch three photos instead.

Keep what you download. A handful of images in ref/<subject>/, linked from the design document that used them with a line on what you took from each — so a later session's answer to "why is this district this colour" is a photograph, not a vibe.

The tell of a generic build is what memory leaves out: nothing is stained, nothing is repaired, nothing sags, nothing is bolted on afterwards, nothing is worn where feet and tyres go. Photographs are full of exactly that, and it is most of what makes an image read as real.

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

Files

Just SKILL.md in .claude/skills/reference-images of ukanwat/overtime.

Open the folder on GitHubat commit fc215d4

Compare with similar skills

Reference Images 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.

Reference Images compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Reference Images this skillukanwat/overtime387—~1kAutomated safety check: PassMIT
Image to Three.js Modelimg2threejs/img2threejs18k1 repos~8.2kAutomated safety check: PassApache-2.0
Web CloneJane-xiaoer/claude-skill-web-clone1k2 repos~2.7kAutomated safety check: PassMIT
Threejs Game Directormajidmanzarpour/threejs-game-skills2.4k—~2.2kAutomated safety check: PassMIT
Game Asset Generatorhtdt/godogen7.1k—~2.8kAutomated safety check: PassMIT
Threejs Gameplay Systemsvalkor-ai/loom1.2k1 repos~1.4kAutomated safety check: PassApache-2.0

Similar skills

  • Image to Three.js Model

    img2threejs/img2threejs

    Rebuilds the object in a reference image as a procedural, animation-ready Three.js model written entirely in code, using staged sculpting with quality checks.

    18k GitHub starsUsed in 1 repo~8.2k tokens
    Game DevelopmentAuto-check passed

  • Web Clone

    Jane-xiaoer/claude-skill-web-clone

    网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树，覆盖静态站 /…

    1k GitHub starsUsed in 2 repos~2.7k tokens
    Game DevelopmentAuto-check passed

  • Threejs Game Director

    majidmanzarpour/threejs-game-skills

    Entrypoint for building, upgrading, and finishing Three.js browser games.

    2.4k GitHub stars~2.2k tokensUpdated 10 days ago
    Game DevelopmentAuto-check passed

  • Game Asset Generator

    htdt/godogen

    Generates game art from text prompts: PNG images, GLB 3D models, rigged characters, animations and sprites, with background removal.

    7.1k GitHub stars~2.8k tokensUpdated 7 days ago
    Game DevelopmentAuto-check passed

  • Threejs Gameplay Systems

    valkor-ai/loom

    Build and iterate playable Three.js game systems: starter scaffold, architecture, design briefs, core loops, level and encounter design, entities, input, camera, collision and physics, scoring…

    1.2k GitHub starsUsed in 1 repo~1.4k tokens
    Game DevelopmentAuto-check passed

  • Uloop Execute Dynamic Code

    CyberAgentGameEntertainment/NovaShader

    Execute C with Unity APIs when existing uloop tools cannot inspect or edit enough.

    1.6k GitHub starsUsed in 1 repo~1.9k tokens
    Game DevelopmentAuto-check passed

More from ukanwat/overtime

All 21 skills in this repo

  • Audio Design

    ukanwat/overtime

    Implement game audio practice — bus/mixer architecture and gain in decibels, ducking (sidechain), adaptive/dynamic music via layering and re-sequencing, SFX variation, and beat synchronization.

    387 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed

  • Camera Systems

    ukanwat/overtime

    Build game cameras that feel good — 2D follow with a deadzone, look-ahead, smoothing, and level-bounds clamping; 3D third-person orbit with collision and first-person look; plus multi-target framing…

    387 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed

  • Dialogue Systems

    ukanwat/overtime

    Build branching dialogue and narrative — a node/choice graph with conditions, variables, and localization hooks — and choose between authoring tools Ink and Yarn Spinner or a custom data-driven…

    387 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed

  • Game AI

    ukanwat/overtime

    Design NPC and enemy decision-making with finite state machines, behavior trees, steering behaviors, and A pathfinding — engine-neutral algorithms that pair with the detected engine's navigation API.

    387 GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check passed

  • Game Feel

    ukanwat/overtime

    Add "juice" and game feel that makes actions satisfying — screen shake, hit-stop/freeze frames, tweened/eased motion, squash & stretch, knockback, and layered audio-visual feedback — as…

    387 GitHub starsUsed in 1 repo~2.3k tokens
    Auto-check passed

  • Game UI UX

    ukanwat/overtime

    Design and build game UI/UX — HUDs, menus, and overlays — that survive every screen: anchor- based responsive layout, resolution/aspect scaling and safe areas, keyboard/gamepad focus navigation, a…

    387 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed

Categories

Questions about Reference Images

What does Reference Images do?

Find and actually LOOK at real photographs — keyless image-search APIs, downloaded to disk so they render as images. Reference Images is an agent skill from ukanwat/overtime. Find and actually LOOK at real photographs — keyless image-search APIs, downloaded to disk so they render as images.

When should I use Reference Images?

Reference Images fits situations like: game Development work in your project.

How do I install Reference Images in Claude Code?

Run `npx skills add ukanwat/overtime --skill reference-images -a claude-code`. Or copy the skill folder (.claude/skills/reference-images in ukanwat/overtime) into .claude/skills/reference-images in your project. Claude Code loads it when a task matches its description.

How do I install Reference Images in Codex?

Run `npx skills add ukanwat/overtime --skill reference-images -a codex`. Or copy the skill folder (.claude/skills/reference-images in ukanwat/overtime) into .agents/skills/reference-images in your project. Codex loads it when a task matches its description.

Can I use Reference Images 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 ukanwat/overtime --skill reference-images -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reference-images, .gemini/skills/reference-images, .github/skills/reference-images and .opencode/skills/reference-images in your project.

What does Reference Images need to run?

Going by SKILL.md and its folder, Reference Images needs the command-line tools its instructions call (curl and python3). Our summary lists: Python 3.

Does Reference Images access the network?

SKILL.md names 3 domains. In commands or code: api.openverse.org, commons.wikimedia.org and api.openstreetcam.org; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Reference Images 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 Reference Images use?

Reference Images 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 Reference Images use?

About 1k tokens (SKILL.md is roughly 4.1k 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 Reference Images?

Skills that share tags, products or a category with Reference Images: Image to Three.js Model (img2threejs/img2threejs, 18k stars), Web Clone (Jane-xiaoer/claude-skill-web-clone, 1k stars), Threejs Game Director (majidmanzarpour/threejs-game-skills, 2.4k stars) and Game Asset Generator (htdt/godogen, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Reference Images?

ukanwat (a GitHub user) maintains it in ukanwat/overtime, which has 387 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 6, 2026.

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