agentleFS
y-a-v-ay-a-v-a/skills/html/SKILL.md

html

Skill0 starsChanged 18 days agoMITView on GitHub

Use this skill when the user wants to export the current "situation" — the state of the conversation, work done, findings, data, or context — to a standalone HTML file they can open in a browser. The agent decides what is most valuable to capture and visualize. Invoked as /html, optionally with hints about what to focus on.

18 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use thermo-nuclear-code-quality-review, prototype and 3 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • jaydubya818Skill

    thermo-nuclear-code-quality-review

    Use when the user requests an intentionally strict maintainability review.

    Also in 3 projects that use this

  • GoogleSkill

    prototype

    Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

    Also in 4 projects that use this

  • GoogleSkill

    to-spec

    Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 4 projects that use this

  • +1 more from google

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 1 is distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 17 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

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

    If arguments are present, treat them as a hint about what to emphasize or what kind of document to produce (e.g.

    line 19
  2. Very specific:

    Prefer signal over completeness.

    line 38
  3. Very specific:

    Use a default font size of 16px and use em font sizes throughout, but do not use font sizes below 1em.

    line 51
  4. Distinctive:

    If a visualization genuinely helps (timeline, flow, simple chart), draw it with inline SVG or CSS rather than pulling in a library.

    line 53
  5. Very specific:

    Ensure the markup is valid and the document is complete (<!DOCTYPE html>, <html>, <head> with <meta charset="utf-8"> and a viewport meta, …

    line 55
  6. Very specific:

    Write to index.html in the current working directory.

    line 61
  7. Very specific:

    After writing the file, output its location as a file:// URL with the absolute path, on its own line, so the user can cmd-click / …

    line 68

“Common” is measured: kept by at least 6 in 10 of the 17 edited versions of this file we could read. “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

HTML Export

Export the current situation to a self-contained index.html file in the current working directory and give the user a clickable link to open it.

Optional focus hints

Arguments provided: $ARGUMENTS

If arguments are present, treat them as a hint about what to emphasize or what kind of document to produce (e.g. /html focus on the architecture, /html as a slide-style summary). If there are no arguments, you decide everything.

Decide what to capture

This is the core of the skill: judge, from the current state of the conversation and context, what would be genuinely valuable to put in front of the user as an HTML page. You are not transcribing the chat — you are producing a useful artifact. Consider, and pick whatever fits:

  • A summary of the work done, decisions made, and their rationale.
  • Findings, analysis, or research results.
  • Code changes, file structures, or architecture (diagrams welcome).
  • Data worth visualizing as tables or charts.
  • Status / checklist of what is done vs. outstanding.
  • Anything else that is the real "payload" of this session.

Prefer signal over completeness. If one thing clearly dominates the session, build the page around that. Give the page a meaningful <title> and top-level heading that reflect the actual situation, not "HTML Export".

Build the file

  • Produce a single, self-contained HTML5 document: all CSS inline in a <style> block, no external stylesheets, fonts, scripts, or CDN links, so it opens correctly offline with a single click.
  • Make it clean and readable: a constrained content width (e.g. max-width: 1024px; margin: auto), comfortable line height, system font stack, sensible spacing, and styled tables/code blocks. Keep it tasteful, not flashy.
  • Use a default font size of 16px and use em font sizes throughout, but do not use font sizes below 1em.
  • If a visualization genuinely helps (timeline, flow, simple chart), draw it with inline SVG or CSS rather than pulling in a library.
  • Ensure the markup is valid and the document is complete (<!DOCTYPE html>, <html>, <head> with <meta charset="utf-8"> and a viewport meta, <body>).

Choose the filename (never overwrite)

Write to index.html in the current working directory. If index.html already exists, use index1.html; if that exists too, index2.html, and so on — pick the first name in that sequence that does not yet exist. Never overwrite an existing file.

Report the path

After writing the file, output its location as a file:// URL with the absolute path, on its own line, so the user can cmd-click / ctrl-click it to open it in a browser. For example:

file:///home/user/project/index1.html

Resolve the real absolute path of the working directory (do not hardcode the example above). Briefly mention what you chose to include and why.

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.

Reviews can't be read right now.

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.