agentleFS
Sign inStart free
shashidharbabushashidharbabu/rocketride-design-skills/skills/mdxcn/SKILL.md

mdxcn

Skill0 starsChanged 2 days agoLicence not identifiedView on GitHub

Install and use mdxcn (mdxcn.dev): a free, MIT, very young (v0.0.1, Aug 2026) library by Keshav Bagaade under the community "Shadcn Labs" org, which is not affiliated with shadcn. It has 51 shadcn-registry items that draw ASCII-styled "figures" for MDX. Each figure is a dashed monospace frame with a [ TITLE ] on the top edge, filled by plain Markdown written inside the tag. The set includes Callout, Steps, Terminal, Annotate, Changelog, Decision, Env, Endpoint, Faq, Keys, and about 34 Graph* data figures such as Table, Spec, Timeline, Flow and Diff. A withMdxcn() wrapper turns GitHub alerts, console fences and footnotes into framed versions, and the same figures exist as fenced ASCII blocks for READMEs. It is NOT a docs-site kit: there are no tabs, no syntax highlighting, no colour swatches, no props tables and no live previews, so hand-built specimen components still carry those. Key trap: install single items with the shadcn CLI after registering the namespace (`npx shadcn@latest registry add @mdxcn=https://mdxcn.dev/r/{name}.json`), never all.json. The CLI flattens the files and breaks re-export paths; all.json gives 60 type errors and is missing a file. Use this whenever a task involves mdxcn.dev or an @mdxcn/ install command; documenting a design system or writing its docs pages; a changelog page, ADR or decision record, install steps, an env-var table or API endpoint doc in MDX; callouts or admonitions, GitHub alerts or terminal blocks in MDX; an ASCII figure for a README or PR; "framed figure", GraphTimeline, GraphFlow, Comark or Knap; or making a write-up scan faster with a figure. Install fixes, Tailwind v3 port and surface/QA traps are in references/integration.md, and the figure chooser is in references/chooser.md.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “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.

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.

Check your setup, free