agentleFS
lfxiuilfxiui/usefulmint-skills/skills/sketch-notes/SKILL.md

sketch-notes

Skill0 starsChanged 31 days agoMITView on GitHub

Turn source notes into an original illustrated knowledge card with editable SVG diagrams.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create SVG knowledge card from the user's real material.

    line 8
  2. Distinctive:

    Do not publish, send messages, purchase assets or start paid generation without authorization.

    line 20

≈ “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

Sketch Notes

Create SVG knowledge card from the user's real material. Use the user's language. Read references/visual-system.md before composing.

Understand and compose

Identify the intended audience, the one message and the supplied assets. If the request is sufficient, state a brief assumption and proceed. Ask only for missing input that changes the result. Preserve factual claims and use authorized images; never invent metrics, customers or product capabilities.

Identify 3–5 ideas and the relationships between them. Draw a clear diagram instead of placing paragraphs in boxes. Use a distinct visual symbol for each idea and visible directional arrows. Use short labels under each figure. When an idea cannot be illustrated, preserve its exact meaning rather than inventing evidence.

Deliver and verify

Create a fresh output folder with editable source and a short source/usage note. Open the actual result in a browser, check every page and control, inspect desktop and phone width, and repair clipping or unreadable copy. Keep the original assets intact. Report actual formats and files; do not rename files to imply unsupported export.

Do not publish, send messages, purchase assets or start paid generation without authorization. A locally reviewed sample does not establish compatibility with tools that were not run.

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.