Not in the top 1,000 by GitHub stars
Lortbyron/gpt-image-realism-engine
Realism skill for ChatGPT Images: AI photos that look like someone took them. By @lortbyron · imageeen.com
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 4176e06a7d27
No earlier version was observed for comparison.
10GitHub stars
Not availablestars in 7 days
1skill in this repository
1commit in 30 days
Heat
Insufficient historyNot enough history yet to measure heat. It appears after a few days of data.
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
gpt-image-realism-engine
When your agent uses it
Realism layer for OpenAI image models (ChatGPT Images 2.5, gpt-image-2.5-flare, gpt-image-2.5-sunburst, gpt-image-2). Turns a photographic request into a ready-to-paste prompt built so the output looks like a found photograph, not AI. Use whenever the user wants a real-looking photo of people, families, streets, interiors, food, products, events or places, in any language and any country, including "a woman in her 30s in Mumbai", "una familia en su casa", "a street in Seoul at dusk", "a market in Lagos", "make it look real, not AI", "que no parezca IA", when a generated image looks fake, plastic or AI-generated, or when writing prompts for someone else to paste into ChatGPT or the Image API. DO NOT use for illustration, anime, pixel art, voxel, stylized 3D, logos, icons, diagrams, infographics or UI mockups - this discipline damages them.
What it loads into context
Frontmatter
227 tokensAlways available to the agent
SKILL.md
4,934 tokensWhen the skill is activated
Reference documents
3,151 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Workflow
- 2. Gates
- 3. Scene Type
- 4. Realism Level
- 5. Provenance
- 6. Framing and API Settings
- 7. Physical Facts, Then Constraints
- 8. Detail Anchors
- 9. People and Culture
- 10. Consistency Across Images
- 11. Output Format
- 12. QC
- 13. Final Check
Files
.gitignoreasset30 bytesLICENSEasset1,105 bytesREADME.es.mddoc5,983 bytesREADME.mddoc6,272 bytesSKILL.mdcore20,578 bytesSKILL.mdcore20,578 bytesassets/comparar-ia.jpgasset75,755 bytesassets/comparar-real.jpgasset100,740 bytesassets/escena-calle.jpgasset96,290 bytesassets/escena-comida.jpgasset106,676 bytesassets/escena-grupo.jpgasset88,519 bytesassets/escena-producto.jpgasset103,352 bytesassets/galeria-1.jpgasset128,557 bytesassets/galeria-2.jpgasset115,363 bytesassets/galeria-3.jpgasset131,241 bytesassets/galeria-4.jpgasset135,488 bytesdist/gpt-image-realism-engine.skillasset9,095 bytes
Read SKILL.md
# GPT Image Realism Engine
**Target:** ChatGPT Images 2.5 and the API models `gpt-image-2.5-flare` (default) and `gpt-image-2.5-sunburst` (fine detail, slower). `gpt-image-2` also works. Facts checked against OpenAI docs on 2026-10-30.
**Staleness:** if the user names a newer model, re-verify Section 6 (API settings) and Section 7 (exclusions) against OpenAI's docs before applying them. Everything else is model-agnostic.
**Language:** answer and label the output in the user's language. Write the prompt itself in English.
**Governing rule: describe physics, not vibes.** "Overhead fluorescents, one tube dimmer than the rest" beats "atmospheric lighting". Every measurable fact is something the model can draw. Every mood adjective is something it must guess, and its guess is porcelain skin, teal-orange grading and perfume-ad light.
---
## 1. Workflow
Run these steps in order, silently, in one response.
Skills included
- gpt-image-realism-engine
Repository facts
- License
- MIT
- Created
- Nov 4, 2026
- Last pushed
- Nov 4, 2026
- Forks
- 3
- Open issues
- 0
- Project activity
- Active
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 1 note
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 13 network referencesin 3 files: README.es.md:7 README.md:7 LICENSE:3
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 13 signals by file
LICENSE
- Network accessline 3
Copyright (c) 2026 lortbyron (https://www.instagram.com/lortbyron/)
README.es.md
- Network accessline 7
[Sitio web](https://imageeen.com/?lang=es) · [English](README.md) · Creado por [@lortbyron](https://www.instagram.com/lortbyron/) - Network accessline 59
git clone https://github.com/lortbyron/gpt-image-realism-engine ~/.claude/skills/gpt-image-realism-engine - Network accessline 68
### Sin instalar nada Usa el constructor gratis en **[imageeen.com](https://imageeen.com/?lang=es)**: es el mismo método en forma de formulario, y arma el prompt mientras escribes. - Network accessline 69
Usa el constructor gratis en **[imageeen.com](https://imageeen.com/?lang=es)**: es el mismo método en forma de formulario, y arma el prompt mientras escribes. - Network accessline 89
La skill es universal a propósito. Haz un fork y hazla tuya: un pack regional con la luz, la comida, las calles y los errores típicos de la IA en tu país; un pack por rubro para restaurantes, inmobiliarias o moda; un adaptador para otro mod - Network accessline 97
Creado por **[@lortbyron](https://www.instagram.com/lortbyron/)** · Parte de **[imageeen.com](https://imageeen.com/?lang=es)**, skills para que la IA deje de parecer IA.
README.md
- Network accessline 7
[Website](https://imageeen.com) · [Español](README.es.md) · Created by [@lortbyron](https://www.instagram.com/lortbyron/) - Network accessline 59
git clone https://github.com/lortbyron/gpt-image-realism-engine ~/.claude/skills/gpt-image-realism-engine - Network accessline 68
### No install at all Use the free builder at **[imageeen.com](https://imageeen.com)**: it's the same method as a form, and it builds the prompt while you type. - Network accessline 69
Use the free builder at **[imageeen.com](https://imageeen.com)**: it's the same method as a form, and it builds the prompt while you type. - Network accessline 105
This skill is intentionally universal. Fork it and make it yours: a regional pack with the local light, food, streets and the usual AI mistakes where you live; an industry pack for restaurants, real estate or fashion; an adapter for another - Network accessline 113
Created by **[@lortbyron](https://www.instagram.com/lortbyron/)** · Part of **[imageeen.com](https://imageeen.com)**, skills that make AI stop looking like AI.
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 12 facts
- Network access in prose of documentationREADME.es.md:7Low confidence
- Network access in code of documentationREADME.es.md:59Low confidence
- Network access in prose of documentationREADME.es.md:68Low confidence
- Network access in prose of documentationREADME.es.md:69Low confidence
- Network access in prose of documentationREADME.es.md:89Low confidence
- Network access in prose of documentationREADME.es.md:97Low confidence
- Network access in prose of documentationREADME.md:7Low confidence
- Network access in code of documentationREADME.md:59Low confidence
- Network access in prose of documentationREADME.md:68Low confidence
- Network access in prose of documentationREADME.md:69Low confidence
- Network access in prose of documentationREADME.md:105Low confidence
- Network access in prose of documentationREADME.md:113Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
