agentleFS
vosslabvosslab/vosslab-skills/skills/planning/ideonomy-plain/SKILL.md

ideonomy-plain

Skill5 starsChanged 21 days agoMITView on GitHub

Expand, vary, invert, or recombine an idea with randomized ideonomy methods. Use for alternatives, opposites, unexpected angles, or fresh frameworks when output must remain portable plain text. Use `ideonomy-rich` for monospace art.

1 other project uses a version of this.

Adopted by

Most recently taken up by

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
  1. Distinctive:

    Run the picker from this skill directory:

    line 16
  2. Very specific:

    Use --more or --less to change tuple size, --print to list picks without their bodies, --seed N for a repeatable tuple, or --random-org …

    line 22
  3. Distinctive:

    Use ordinary Markdown headings, lists, and fenced ASCII tables or diagrams.

    line 39
  4. Distinctive:

    Keep labels meaningful without color, typography, or Markdown rendering.

    line 42
  5. Distinctive:

    Keep every file and generated artifact in this skill's plain workflow ASCII.

    line 43
  6. Very specific:

    Keep historical recipe sketches under examples/historical-recipes/ as inspiration only.

    line 58
  7. Distinctive:

    Use this skill while the user is exploring alternatives, inversions, dimensions, or unexpected frames.

    line 65

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ideonomy plain

Purpose

Expand an idea by treating its properties as dimensions that can be substituted, negated, combined, abstracted, or reinstantiated. Produce a structured plain-text artifact that remains readable through terminals, chat relays, email, and other low-format channels.

Select a method tuple

Run the picker from this skill directory:

bin/pick

Use --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 active primitive catalog is indexed in methods/README.md. Read and apply every method file returned by the picker.

Work in two passes

  1. Internally identify axes from every picked dimension prompt, apply every picked operator to those axes, and fit the results into the picked organon.
  2. Externally publish the organon as the artifact. Use headers named after the user's idea, the concrete operator move, or the organon's natural structure. Keep the procedure implicit.

The structure should reveal gaps, asymmetries, unnamed cases, or surprising neighbors. A flowing brainstorm without an organon does not complete the skill.

Portable rendering

  • Use ordinary Markdown headings, lists, and fenced ASCII tables or diagrams.
  • Build diagram borders from +, -, and | only.
  • Render charts as labeled lists when a two-dimensional table would not survive the channel.
  • Keep labels meaningful without color, typography, or Markdown rendering.
  • Keep every file and generated artifact in this skill's plain workflow ASCII.

Output contract

  • Name the selected operators, organon, and dimension prompts briefly.
  • Show the resulting structured artifact with intrinsic content headers rather than phase labels.
  • Identify the strongest new idea or useful gap surfaced by the structure.
  • Mention important directions the selected tuple did not explore when that helps the user continue.

Catalog discipline

The picker composes three primitive categories: operators, organons, and dimension prompts. Add a new primitive only when it is irreducible to existing methods, useful beyond one request, and supported by observed value. Extend the relevant directory and update methods/README.md.

Keep historical recipe sketches under examples/historical-recipes/ as inspiration only. They do not enter the active picker because saved combinations would become preferred defaults and reduce the randomized search space. examples/walkthrough.md shows the active workflow without defining a reusable tuple.

Use boundary

Use this skill while the user is exploring alternatives, inversions, dimensions, or unexpected frames. Once the desired idea is chosen and the task becomes implementation, return to the appropriate execution workflow. Use ideonomy-rich when expressive Unicode monospace rendering is part of the requested result.

Attribution

The operators, organons, and method framing derive from Grace Kind's essays on Patrick Gunkel's Ideonomy. Preserve that attribution when republishing or extending the catalog.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.