Skip to content
Back to skills

Sandtable Stories

ASecurity

Generate coherent Sandtable Stories editorial illustration sets with a reusable conceptual visual system. Use when illustrating articles, blogs, newsletters, essays, or social posts that need macro editorial landscape sculptures in fine dry sand, with raked channels, carved ridges, small turquoise markers and directional low light that reveals the passage's physical relationship.

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 19, 2026
ai-agents

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned October 19, 2026

npx -y skills add hahayang888/zyncli-template --skill sandtable-stories --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Sandtable Stories?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Sandtable Stories
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hahayang888-sandtable-stories/badge)](https://www.skillsdirectory.com/skills/hahayang888-sandtable-stories)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: sandtable-stories
description: "Generate coherent Sandtable Stories editorial illustration sets with a reusable conceptual visual system. Use when illustrating articles, blogs, newsletters, essays, or social posts that need macro editorial landscape sculptures in fine dry sand, with raked channels, carved ridges, small turquoise markers and directional low light that reveals the passage's physical relationship."
---

# Sandtable Stories

Create a coherent set of article illustrations with the Sandtable Stories visual system. Raked sand, channels, and small paths make flow, erosion, and obstacles tactile. Make a route bend around a ridge, narrow at a pass, or erode an obstacle. The sand should show the force at work. Keep the turquoise markers small so they clarify the route without turning it into a map.

Read [references/style-guide.md](references/style-guide.md) before planning or generating. Use the images in `assets/examples/` only for low-frequency visual calibration; never copy their composition, people, objects, or wording.

## Workflow

1. Read the full article or supplied passage.
2. Identify the core argument, contrasts, turning points, system relationships, and conclusion.
3. Select 1-9 cognitive anchors. Do not illustrate paragraphs at even intervals.
4. Write a shot plan before generating. Give each image one core idea, one structure, and a different primary composition.
5. Compile every shot with the visual DNA and negative constraints from the style guide.
6. Use the host agent's available image-generation tool. Generate one standalone 16:9 image per request.
7. Inspect every output against the QA checklist. Regenerate or make one targeted edit when a failure signal appears.
8. Deliver ordered files and preserve original generated files.

## Shot plan

For every proposed image, specify:

- Placement after the relevant passage
- Theme and core idea
- Purpose in the article
- Structure type
- Composition and reading direction
- Suggested elements
- Essential short labels, or none

Prioritize the core argument, contrasts, turning points, system relationships, cause and effect, and a memorable conclusion. Avoid decorative filler, repeated claims, and paragraphs already concrete without a visual.

## Generation rules

- Output one standalone 16:9 horizontal editorial image.
- Keep one core idea per image.
- Make the article-specific relationship visible without relying on a headline.
- Change both the main metaphor object and spatial arrangement between consecutive images.
- Preserve identity through material, palette, hierarchy, and composition grammar rather than repeating a scene.
- Use real supplied labels only. Never invent statistics, quotations, dates, brand marks, or interface copy.
- Respect every `must`, `never`, and negative constraint in the style guide.

## QA and iteration

Reject an output when it is generic, off-style, repetitive, text-heavy, anatomically broken, semantically wrong, or dependent on decoration instead of the article idea.

When revising:

- Generic: replace the stock scene with one article-specific physical relationship.
- Complex: remove secondary elements and preserve one focal idea.
- Repetitive: change both the object family and composition pattern.
- Off-style: return to the exact visual DNA in the style guide.
- Text-heavy: remove the headline and keep only essential supplied labels.

## Delivery

Name files in article order using `{order}-{topic-slug}.png`. Report where each image belongs in the article and preserve the original generated outputs.

Files in this skill

  • SKILL.md3.5 KB
  • agents/openai.yaml223 B
  • references/style-guide.md3.8 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.