agentsclimarketplace
Sign in

Render markdown

Skill 1stvamp/agent-skills/render-markdown

Render markdown files as nicely styled, self-contained HTML pages in /tmp and open them in the user's default browser. Use whenever the user says render-markdown, render-md, show-markdown, show-md, or asks to render, preview, view, show, or open a markdown file (a README, notes, report, plan, or any .md doc) in the browser, "as HTML", "styled", or "prettified". Also use when the user asks to see or be shown a markdown document the agent just wrote, e.g. "show me that report" or "open the plan you just made" — if no file is named, render the markdown the agent created or edited most recently in this session.From its SKILL.md

Install
npx -y skills add 1stvamp/agent-skills --skill render-markdown

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.6 KB, 727 tokens by cl100k_base, as published. Nobody here has run it

Render Markdown

Convert one or more markdown docs to styled, self-contained HTML in /tmp/render-md/ and open them in the default browser. A bundled script does the conversion so output is consistent across runs; your job is picking the right files, a quick sanity check of the output, and opening it.

1. Pick the files

  • Paths named by the user win, always.
  • No file named: use the markdown file(s) you created or edited most recently in this session. This is the common case ("show me what you just wrote").
  • No file named and none touched this session: ask which file. Don't guess by rendering whatever README is lying around; opening the wrong doc in the user's browser is worse than a one-line question.

2. Render

python3 <skill-dir>/scripts/render_md.py FILE [FILE...]

Prints one output path per input. Notes:

  • First run may auto-install python-markdown and pymdown-extensions into ~/.cache/render-markdown/libs (stderr says so). This is expected. The pymdownx extensions give GitHub-flavoured behaviour: fenced code inside list items, - [ ] task lists as real checkboxes, ~~strikethrough~~.
  • Exit code 3 means neither python-markdown nor pandoc is available and the auto-install failed; install one (pip install markdown) and rerun.
  • Output paths are stable per source file, so re-rendering overwrites in place and an already-open browser tab can just be refreshed.

3. Fast review

Read the head and a slice of the body of the generated HTML. You're checking that conversion actually worked, not proofreading: the <title> is sensible, headings became <h1>/<h2> elements, and no raw markdown leaked through (literal ## or ``` fences visible in body text usually mean unusual syntax in the source). If something is broken, fix the source markdown or tell the user; don't hand-write replacement HTML, because the whole point is repeatable output.

Skip this step when re-rendering a file you already reviewed this session.

4. Open

python3 <skill-dir>/scripts/render_md.py --open FILE.md

--open renders and opens in one go (use it directly on a re-render, or once you trust the output). The script picks the right opener per platform: xdg-open on Linux, open on macOS, os.startfile on Windows, wslview under WSL. Passing an already-rendered .html path just opens it without converting anything.

Afterwards, tell the user the /tmp/render-md/... path(s) so they can reopen or share the file later.

Terminal wrapper

scripts/render-md is a bash wrapper so the user can do render-md doc.md from a shell: it resolves the file path(s) and calls claude -p with this skill and the needed tools allowed. With -o/--offline it skips the claude CLI entirely and runs the bundled render script directly (render and open, nothing else). It gets installed as ~/bin/render-md. You normally don't need it from inside a session; it exists for the terminal.

What ships with it: 3 files

14.2 KB alongside SKILL.md, 2 of them executable

evals/

scripts/

Gives 0 of the 12 instructions most docs writing skills give in 727 tokens

Counted across 1,637 of the 3,044 authors here whose files we hold, read 2026-08-07

  • Announce the skill at startin 54 of 1637, across 26 files
  • Convert legacy doc files before editingin 45 of 1637, across 7 files
  • Predict questions readers might askin 42 of 1637, across 4 files
  • Generate clarifying questions for initial contextin 42 of 1637, across 3 files
  • Create document scaffold with placeholder textin 42 of 1637, across 3 files
  • Brainstorm content options for each sectionin 42 of 1637, across 3 files
  • Test the document with a fresh context-less instancein 42 of 1637, across 3 files
  • Include exact file paths in every taskin 42 of 1637, across 15 files
  • Ask interview questions one at a timein 42 of 1637, across 27 files
  • Apply surgical edits during refinementin 41 of 1637, across 2 files
  • Offer structured workflow or freeformin 40 of 1637, across 1 file
  • Ask for document meta-contextin 40 of 1637, across 2 files

Said here and by no other author read

  • prioritize file paths named by the user
  • use most recently edited file if none specified
  • ask which file if no source is identified
  • review the generated HTML head and body slice
  • fix the source markdown if conversion breaks
  • open the HTML file using the script flag

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,852. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.