agentleFS
hashiiiiihashiiiii/rules-for-ai/skills/hashiiiii-explain-pr/SKILL.md

hashiiiii-explain-pr

Skill10 starsChanged 3 months agoMITView on GitHub

Use when a user asks to understand or explain a pull request's purpose, diff, or relationship to an issue.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Read the title, body, commits, and complete diff.

    line 12
  2. Distinctive:

    Read related issues linked from the PR metadata or body when available.

    line 13
  3. Distinctive:

    Read surrounding code at those revisions when needed.

    line 14
  4. Distinctive:

    If a source is inaccessible or the diff is incomplete, state that limit.

    line 15

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Explain a pull request

Explain the reviewed diff in the user's requested language and scope. Work read-only.

Gather evidence

  • Read the title, body, commits, and complete diff. Record the base and head revisions.
  • Read related issues linked from the PR metadata or body when available.
  • Read surrounding code at those revisions when needed. Check dependency versions before choosing documentation.
  • If a source is inaccessible or the diff is incomplete, state that limit.

Explanation

Background and purpose

Describe the problem and goal in about ten lines, using fewer when evidence is sparse. Use related issue requirements when available; otherwise use the PR body, commits, and implementation before and after the change. Cite the evidence, label inferred motivations, and identify unknowns.

Changes by meaning

Explain each independent changed statement, setting, condition, or test case in its own entry. Keep a multiline expression together; split function bodies by statement and branch. Cover scoped code, tests, and documentation. Group equivalent edits and list their locations.

Each entry gives the location (path, line, excerpt, and revision link), syntax meaning, behavior before and after, purpose, and supporting references. Use base locations for removed lines and head locations for added lines. Link related requirements when available. Say when a change has no established link to the goal or leaves a requirement unmet.

Verify documentation URLs, sections, and versions before citing them. Use official references for language, framework, library, or tool behavior, and repository code for project logic. Say when no official reference is available. Separate expected behavior from test or runtime evidence; code inspection alone does not prove deployment or issue closure.

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.