Paper Operators skill
A Codex skill that turns a paragraph into a 16:9 illustration where a folded-paper operator performs the key action.
- 105 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- The skill only prepares prompts and a plan, with a connected model drawing the pictures
- The article text goes to the image-generation model
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/paper-operatorsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill only prepares prompts and a plan, with a connected model drawing the pictures
- The article text goes to the image-generation model
This is third-party code. Review the repository files before installing.
What it does
Paper Operators finds the sentence, conflict, turn or argument worth showing in a text and turns the abstract structure into a physical action of a paper operator: reveal, route, weigh, frame, filter, repair, archive or transform. The project rule is simple: if the image is not weaker without the operator, the operator should not be there. Before drawing the skill picks the asset type: article figure, story or book card, data story, centre illustration or reference-informed explainer. It chooses a world metaphor for the topic (literature, product, business, engineering, AI, education, psychology), preserves numbers, labels and recognisable details and keeps one visual language across a series. Labels are readable by default, in Chinese or English. `agent-guides/` holds guides for Claude Code and Cursor and an `.mdc` rule for other environments.
Who it is for. Article authors, teachers and product teams who need expressive illustrations for a text without hunting for stock pictures.
Good fit when
- Three illustrations for an essay are planned first without generating.
- A classic book is retold in one card with characters, conflict and turns.
- Dry status figures are explained with a picture where the values stay exact.
- A series of images for a course keeps one visual language.
Not a fit when
- Strict charts are needed: the skill supports data storytelling rather than exact chart rendering.
- Photorealism or a brand style without the paper aesthetic is required.
- The agent has no image-generation model.
Example request
Use $paper-operators to plan three article body illustrations for this essay. Do not generate images yet.Limitations
The skill prepares the concept, prompts and checks while an image-generation model draws the pictures. The authors name Codex the best environment for final rendering, and in other tools the quality of paper texture and labels may be lower. The main language of examples and README is Chinese with an English version. The aesthetic is fixed: the paper operator has no face by default and a face is allowed only to convey state. The repository was last updated on 8 July 2026 and uses the MIT licence.
How to disable. Delete the `~/.codex/skills/paper-operators` folder. For other agents remove the project rules or instructions you added. Finished pictures stay.
FAQ
Is it Codex only?
No. The ready skill is for Codex, while Claude Code, Cursor, Hermes Agent and OpenClaw work from the same guides in `agent-guides/`.
What does the skill do before drawing?
Finds the idea to visualise in the text, picks the asset type and world metaphor and fixes numbers and labels.
What pictures come out?
16:9 illustrations for articles, story and book cards, data stories, centre illustrations and reference-informed explainers.
Are exact numbers preserved?
Yes, values and labels stay exact and the operator action shows the implication, for example turning a warning into a review action.
How to verify installation?
`agent-guides/smoke-test.md` holds smoke prompts, and `$paper-operators` asked to plan illustrations without generating shows the skill is visible.
Discussion
No questions or reviews yet.
Related
SkillsSkill for editorial images in a minimal-zine style: paper, ink, series and a check of the finished bitmap.
A Codex skill that draws 16:9 scenes with the Xiaohei character among real objects for Chinese articles
A skill for Codex and Claude Code that makes medical comics, illustrations and schematics backed by traceable anatomy sources.
A skill that turns your photo or description into a hand-drawn character and uses it for diagrams, knowledge cards and slides
A de-AI writing skill: it repairs the narrative architecture of fiction and edits professional documents by their venue rules
A Codex skill that turns a Chinese article into a series of hand-drawn 16:9 illustrations on white background with the Xiaohei character
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Paper Operators (this card) | no | 105 | |
| paper-craft-skills | no | 1,475 | a set of skills for scientific papers: method analysis, slides and a retelling from PDF; here illustrations with a paper operator for any text |
| Guizang Material Illustration | no | 1,257 | material illustrations for an article header; here a scene with an operator action and label checks |
README in short
The README shows a showcase of examples made in Codex: a Christmas Carol card, a visual reasoning engine and data as a status board.