agentleFS
tonytony/skills/.agents/skills/gh-rendered-markdown/SKILL.md

gh-rendered-markdown

Skill0 starsChanged 17 days agoMITView on GitHub

Use when a GitHub PR description, comment, or issue body looks broken: wrapped lines, bad code fences, long logs, links. Not for filing an issue.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Write the body so it renders, and link it so it still resolves in three years.

    line 13
  2. Very specific:

    Read references/rendered-markdown.md before drafting.

    line 16
  3. Very specific:

    Run "Preview before publishing" in rendered-markdown.md with that script.

    line 43
  4. Distinctive:

    If the text cannot be fixed (no body was given, or the surface is a commit message), reply with one sentence saying so and what the user …

    line 75

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Rendered markdown

Write the body so it renders, and link it so it still resolves in three years. Write it per references/prose-rules.md.

Read references/rendered-markdown.md before drafting. When the text has links, also read references/source-links.md and references/source-pins.md; when it names an upstream open-source project, references/project-links.md. For a pull-request description or a repository markdown file, also read references/pr-and-files.md.

Steps

  1. Identify the surface (comment, issue, or pull-request body; repository file). Read the project's AGENTS.md and CLAUDE.md when present: a house voice, slop rubric, or table rule there overrides these references (not link pinning or the sanitize step). A wrap convention applies only to repository files (see pr-and-files.md).
  2. Get the text. The script is references/issue.py; it resolves from this skill's directory to an absolute path written literally in each command, and scan and lint are documented in its docstring (its other subcommands serve create-issue). When the text is already on GitHub, fetch it from its issue, pull-request, or comment URL; writing the fixed text back is the user's call:

    $ python3 /absolute/path/to/scripts/issue.py fetch URL
  3. Draft or fix the text per rendered-markdown.md; pin and complete every link per the link references.
  4. Run "Preview before publishing" in rendered-markdown.md with that script. Without a shell, reread by eye. A 0 length row means trim the excerpt and link the full log (Length in that reference). Leave a table in someone else's body alone.

Reply

A status line (repository, and whether the preview ran), the rewritten body fenced with four backticks, then one sentence naming what the user must do before posting. No bullet list, command, or explanation of what changed.

Rewritten body for example/widgets, preview not run (gh is not logged in).

````markdown
The retry loop drops the timeout on the third attempt.

<details>
<summary>Full stack trace</summary>

```
TypeError: Cannot read properties of undefined (reading 'target')
```

</details>

See [`src/build.js`](https://github.com/example/widgets/blob/<SHA>/src/build.js#L38-L50).
````

Before posting, replace `<SHA>` with the commit where you saw the bug, or a release tag.

If the text cannot be fixed (no body was given, or the surface is a commit message), reply with one sentence saying so and what the user should send.

Portability notes

  • Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.

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.