ideonomy-rich
Skill5 starsChanged 21 days agoMITView on GitHub
Expand an idea with randomized ideonomy methods and expressive monospace art. Use when the channel supports Unicode box drawing, figlet banners, density gradients, and visible reasoning structure. Use `ideonomy-plain` for portable text.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- latentwill/ideonomy-skilltheir own version, first seen Sep 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- latentwill/ideonomy-skill★ 41same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agents-md-fixerSkill
- arch-docsSkill
- book-to-markdownSkill
- docset-updaterSkill
- humanizerSkill
- news-release-docsSkill
- pdf-guideSkill
- readme-docsSkill
- screenshot-docsSkill
- see-also-docsSkill
- setup-install-usage-docsSkill
- bptools-writer-expertSkill
- color-accessibility-expertSkill
- css-creative-expertSkill
- game-design-expertSkill
- geometry-expertSkill
- glass-expertSkill
- hic-human-interact-expertSkill
- openscad-3d-printing-expertSkill
- podman-expertSkill
- postgresql-expertSkill
- pyside6-engineerSkill
- rust-code-expertSkill
- solid-js-expertSkill
- svg-creator-expertSkill
- typescript-engineerSkill
- ui-ux-engineerSkill
- vision-expertSkill
- wasm-rust-expertSkill
- webwork-writer-expertSkill
- delegate-manager-to-subagentsSkill
- gas-town-workflowSkill
- hang-checkSkill
- html-game-parallel-builderSkill
- parallel-planSkill
- stay-busySkill
- repo-rules-readerSkill
- blueprint-plan-drafterSkill
- ideonomy-plainSkill
- make-goalSkill
- modest-plan-drafterSkill
- audit-code-reviewerSkill
- old-python-code-reviewSkill
- prune-testsSkill
- unit-test-starterSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Run the picker from this skill directory:
- Very specific: line 22
Use --more or --less to change tuple size, --print to list picks without their bodies, --seed N for a repeatable tuple, or --random-org …
- Very specific: line 36
Read rendering/README.md for the visual hierarchy, width, banner, legend, dimension, operator-divider, and trail contracts.
- Distinctive: line 68
Keep every line at or below 100 characters and preview the final block in a monospace context.
- Distinctive: line 70
Use one box-drawing style per diagram while varying styles between hierarchy levels when helpful.
- Distinctive: line 71
Use motion, density, or enclosure only when it represents a real relationship.
- Distinctive: line 72
Keep prose short enough that the composition remains the primary explanation.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Ideonomy rich
Purpose
Expand an idea by varying its properties along dimensions, applying randomized operators, and rendering the result as an expressive monospace artifact. The visible structure should teach the reader how the ideas relate, not merely decorate prose.
Select a method tuple
Run the picker from this skill directory:
bin/pickUse --more or --less to change tuple size, --print to list picks without their bodies,
--seed N for a repeatable tuple, or --random-org when network-backed entropy is requested.
The catalog is indexed in methods/README.md; the picked method files are the
instructions to apply.
Work in two passes
- Internally apply every picked dimension prompt, then every picked operator, and finally fit the results into the picked organon. Hold intermediate reasoning rather than publishing a process log.
- Externally render one coherent artifact whose headers name the actual idea, operator moves, and organon. The reader should be able to infer which dimensions and operations produced each part.
Load rendering guidance
Read rendering/README.md for the visual hierarchy, width, banner, legend,
dimension, operator-divider, and trail contracts. Then read the matching focused guide when the
picked organon is one of these:
- Atlas:
rendering/atlas.md - Chart:
rendering/chart.md - Cycle:
rendering/cycle.md - Dictionary:
rendering/dictionary.md - List:
rendering/list.md - Scale:
rendering/scale.md - Tree:
rendering/tree.md
For another organon, apply the shared rendering principles to its natural structure. Unicode glyph examples live in these rendering references so this entrypoint remains ASCII.
Visible artifact contract
Render these five layers as one composition:
- A compact title banner, using local
figletortoiletwhen available and a plain title when neither tool exists. - A tuple legend naming the selected operators, organon, and dimension prompts.
- A dimensions block showing the explored axes and marking any pivotal dimension.
- The organon body, divided by operator-named headers that state each concrete transformation.
- An ideonomy trail that summarizes the moves and names at least one promising direction not surfaced by the current tuple.
The artifact's main header names the organon. Use intrinsic content headers instead of phase labels. Make the operator and its specific move visible together.
Rendering constraints
- Keep every line at or below 100 characters and preview the final block in a monospace context.
- Give each glyph, line weight, density, and marker one consistent semantic role within the piece.
- Use one box-drawing style per diagram while varying styles between hierarchy levels when helpful.
- Use motion, density, or enclosure only when it represents a real relationship.
- Keep prose short enough that the composition remains the primary explanation.
- Preserve readable fallback meaning in labels and spacing even when color is unavailable.
Completion
Return the rendered artifact and a short plain-language interpretation of its most useful new
directions. The tuple, dimensions, operator moves, organon, and not surfaced trail line must all be
visible. If the requested channel cannot preserve Unicode monospace output, use ideonomy-plain
instead.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

