agentleFS
brittbritt/agent-skills/skills/markdown-formatting/SKILL.md

markdown-formatting

Skill11 starsChanged 6 days agoMITView on GitHub

Use when writing PR descriptions, issue bodies, documentation, or notes - applies consistent Markdown conventions (heading levels, list markers, code-block languages, link text) and provides PR and issue templates

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 2 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    Use ## for main sections (reserve # for document title)

    line 43
  2. Very specific:

    Use ### sparingly for subsections

    line 44
  3. Very specific:

    Never skip levels (no ## to ####)

    line 45
  4. Very specific:

    Use - for unordered lists (not *)

    line 49
  5. Very specific:

    Use 1. for ordered/sequential steps

    line 50
  6. Distinctive:

    Keep list items parallel in structure

    line 52
  7. Very specific:

    Always specify language: `typescript, bash, ``json

    line 58
  8. Distinctive:

    Never combine bold and italics

    line 64

≈ “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

Markdown Formatting Skill

Apply consistent Markdown formatting to all outputs. Structure content for readability and professionalism.

When to Use

Activate when producing:

  • PR descriptions and issue bodies
  • Documentation and guides
  • Notes and summaries
  • Structured artifacts that will be saved or published (reports, READMEs, changelogs)

Not for conversational chat replies — normal responses don't need templates or strict formatting rules.

Core Principles

  1. Lead with the point - TL;DR or summary first, details after
  2. Use structure - Headings, lists, and whitespace aid scanning
  3. Be consistent - Same patterns across all outputs
  4. Respect context - PRs need checklists, docs need examples

Formatting Rules

Document Structure

# Title (standalone documents only)

Brief summary or TL;DR (1-2 sentences)

## Section Heading

Content organized by topic...

Headings

  • Use ## for main sections (reserve # for document title)
  • Use ### sparingly for subsections
  • Never skip levels (no ## to ####)

Lists

  • Use - for unordered lists (not *)
  • Use 1. for ordered/sequential steps
  • Nest with 2-space indent
  • Keep list items parallel in structure

Code

  • Inline: backticks for commands, filenames, variables
  • Blocks: triple backticks with language identifier
  • Always specify language: typescript, bash, ```json

Emphasis

  • Bold for key terms, warnings, important points
  • Italics sparingly for emphasis or introducing terms
  • Never combine bold and italics

Links

  • Descriptive text: [installation guide](url) not [click here](url)
  • Reference issues/PRs with #123 format

Templates

PR Description

## Summary

[One-line description of the change]

## Changes

- [Change 1]
- [Change 2]

## Test Plan

- [ ] [Test case 1]
- [ ] [Test case 2]

Issue Body

## Problem

[What is wrong or missing]

## Steps to Reproduce

1. [Step 1]
2. [Step 2]

## Expected

[What should happen]

## Actual

[What actually happens]

Example: Filled-in PR Description

## Summary

Add retry with exponential backoff to the `fetchUser` API client.

## Changes

- Wrap `fetchUser` in a retry helper (3 attempts, 200ms base delay)
- Surface a `RetryExhaustedError` after the final attempt
- Add unit tests covering success-after-retry and exhaustion paths

## Test Plan

- [x] `npm test` passes, including new `retry.test.ts` cases
- [x] Manual check: killed the mock server mid-request, saw retries in logs (#87)

Note the applied rules: ## headings, - list markers, backticks for code identifiers, #87 issue reference, and a one-line summary leading the document.

Anti-patterns

  • Walls of text without structure
  • Inconsistent list markers (*, -, + mixed)
  • Code blocks without language identifiers
  • Headings used as emphasis
  • Trailing whitespace or excessive blank lines

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.