agentleFS
Sign inStart free
witi-projectswiti-projects/Skills/verifying-markdown-formatting/SKILL.md

verifying-markdown-formatting

Skill2 starsChanged 7 months agoMITView on GitHub

Verify that a Markdown file has correct formatting — headings, lists, links, code blocks, spacing, and consistent style. Use when the user says "/verifying-markdown-formatting", "verifying markdown formatting", or asks about verifying markdown formatting.

2 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check a Markdown file for formatting issues and fix them.

    line 9
  2. Distinctive:

    Read the target Markdown file

    line 63
  3. Distinctive:

    When fixing list markers, match whatever style the file already uses most

    line 73

≈ “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

Verifying Markdown Formatting

Check a Markdown file for formatting issues and fix them.

What to Check

Structure

  • Exactly one # H1 heading at the top of the file
  • Headings increment by one level (no jumping from ## to ####)
  • Blank line before and after every heading
  • Blank line before and after every code block, list, and blockquote
  • File ends with a single trailing newline

Lists

  • Consistent marker style within each list (- not mixed with * or +)
  • Nested items indented with 2 or 4 spaces (consistent throughout)
  • Blank line before the first item in a top-level list
  • No blank lines between items in a tight list (or all items separated — pick one)

Links & Images

  • All links have non-empty display text: [text](url) not [](url)
  • No bare URLs outside of code blocks — wrap in <url> or [text](url)
  • Reference-style links have matching definitions
  • Image alt text is present: ![alt](src) not ![](src)

Code Blocks

  • Fenced code blocks use triple backticks, not tildes
  • Language identifier is present on every fenced block (```python, ```bash, etc.)
  • Inline code uses single backticks for short references
  • No indented code blocks (use fenced instead for clarity)

Formatting

  • Bold uses **text** not __text__
  • Italic uses *text* not _text_
  • No trailing whitespace on any line
  • Lines under 120 characters where practical (prose, not tables)
  • Consistent use of ATX-style headings (# Heading, not underline style)

Tables

  • Header row has separator row with --- in each column
  • Cell content is trimmed (no excessive padding)
  • Column alignment markers (:---, :---:, ---:) used consistently if present

Horizontal Rules

  • Use --- on its own line with blank lines above and below
  • Consistent style (don't mix ---, ***, ___)

Workflow

  1. Read the target Markdown file
  2. Walk through each check above
  3. Fix any issues found using exact string replacements
  4. Re-read the file to confirm all fixes applied cleanly
  5. Report what was fixed and what was already correct

Notes

  • This skill is formatting-only — it does not validate content accuracy, broken links, or spelling
  • Preserve the author's intended structure; don't reorganize sections
  • When fixing list markers, match whatever style the file already uses most

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.

Check your setup, free