procedural-realism SKILL.md skillA
procedural-realism from dogum/procedural-art is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add dogum/procedural-art/procedural-realism@v1.2.0Pins v1.2.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- dogum/procedural-art
- Path
skills/procedural-realism/SKILL.md- Versions recorded
- 6
- Latest version
- v1.2.0, committed Oct 20, 2026
- First version recorded
- Sep 25, 2026
- Size
- 16,659 bytes
- Repository stars
- 9
- License
- Apache-2.0
Make photographic-style images with pure code and physics, no generative image model. Ray-marched terrain of any real mountain with physical sky, haze, shadows, snow, mist and clouds; mirror lakes; forests and villages; blue hour with a lit city or a moonlit starry night; sunset timelapse videos along the real sun path. A from-scratch path tracer renders JSON still lifes (glass, prisms with rainbow caustics, copper, fruit). A painterly finisher turns any image, including an uploaded photo…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Procedural realism Four tools, numpy/scipy/pillow only, that push how close pure math gets to a photograph or a painting: | Tool | Best at | Time on 1 CPU | |---|---|---| | `scripts/pbr_terrain.py` (+ `post_terrain.py`) | Real mountains from real elevation data: atmosphere, golden light, shadows, snow, mist, clouds; optional lake reflections, trees and villages, blue hour with city lights along real streets (OpenStreetMap), moonlit night | 7 s at 600×200 · ~2.5 min at 3000×1000 plain · 5–13 min with water, trees or a city | | `scripts/timelapse.py` | Sun-angle video (golden hour to night) along the real solar path for a date and place, every frame rendered so shadows slide | ~15 s per 600×200 frame, ~50 s at 1200×400, one core each; frames render 4 at a time (`--jobs`), so a 20 s clip (480 frames) ≈ 2 h at 1200×400 on 4 cores, 6 h on one | | `scripts/pathtracer.py` (+ `post_pathtrace.py`) | Tabletop scenes from a JSON file: glass, liquids, metal, glossy fruit, soft or hard light, caustics (photon map), rainbow dispersion, depth of field | ~3 s per pass at 900×300; 30–70 s per pass at 2400×800; 60–80 adaptive spp (about an hour) for a clean final | …
Read the whole file at its exact version.
How to install
mdr add dogum/procedural-art/procedural-realism@sha256:e66d81b8f9a708baThe line at the top of this page pins the label v1.2.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_y34234ulerqcxcdh)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Sep 25, 2026 and Oct 20, 2026, about one every 5 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.2.0 latest | 2026-10-20 | 0f5ee25 | 16,659 B | A | view · diff |
| v1.2.0 | 2026-09-26 | e1d8f02 | 16,540 B | A | view · diff |
| v1.1.0 | 2026-09-26 | 2bb12a9 | 16,540 B | A | view · diff |
| v1.1.0 | 2026-09-25 | 4d59198 | 15,301 B | A | view · diff |
| v1.0.0 | 2026-09-25 | bedea8d | 15,301 B | A | view · diff |
| v1.0.0 | 2026-09-25 | 7cfc8c8 | 15,111 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (16659 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
dogum/procedural-art · 9 stars · license Apache-2.0 · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_y34234ulerqcxcdh GET https://markdownregistry.com/api/v1/resolve?ref=dogum/procedural-art/procedural-realism GET https://markdownregistry.com/api/v1/blob/e66d81b8f9a708bae4adae0cec238f85c730af6fc90b8858e136461f331e0e19
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.