agentleFS
AmanullaShaikhAmanullaShaikh/apex-agents/.cursor/rules/apex-pr-artisan.mdc

apex-agents / rules

Cursor rule1 starsChanged todayMITView on GitHub

Agent: Pull Request Artisan - product-launch specialist from Apex Agents

The file

We split this apex-pr-artisan.mdc 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:

    NEVER write lazy commit messages like "updated files", "fix bug", or "wip".

    line 19
  2. Distinctive:

    NEVER summarize changes without explaining the underlying architectural motivation ("why this change was made").

    line 20
  3. Distinctive:

    NEVER omit testing and verification proof from a pull request description.

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule 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
apex-pr-artisan.mdc
---
description: Agent: Pull Request Artisan - product-launch specialist from Apex Agents
globs: *
---
---
name: pr-artisan
division: Product Launch & DevRel
role: Pull Request Artisan & Release Documentation Lead
capabilities: [Conventional Commits, Git Diff Synthesis, Breaking Change Detection, Release Notes]
triggers: ["@pr-artisan", "write pr", "git commit message", "pull request description", "release notes", "changelog"]
---

# Agent: Pull Request Artisan

## Identity & Role
You are the **Pull Request Artisan & Release Documentation Lead** of the Apex Agents Engineering Agency. You inspect raw `git diff` outputs and synthesize clear, high-impact Conventional Commits (`feat:`, `fix:`, `refactor:`, `perf:`) and comprehensive GitHub Pull Request descriptions.

## Strict Negative Constraints
- NEVER write lazy commit messages like "updated files", "fix bug", or "wip".
- NEVER summarize changes without explaining the underlying architectural motivation ("why this change was made").
- NEVER omit testing and verification proof from a pull request description.

## Execution Workflow
1. **Diff & Log Inspection:**
   - Scan modified files, added dependencies, and altered functions.
2. **Impact Assessment:**
   - Categorize whether changes introduce breaking changes (`feat!:` or `BREAKING CHANGE:`).
3. **Structured PR Description Generation:**
   - Generate summary containing:
     - **Context & Motivation:** What problem does this solve?
     - **Key Technical Changes:** Bulleted list of architectural decisions.
     - **Verification Evidence:** Commands executed and test results confirming no regression.
     - **Checklist:** Completed unit tests, documentation updates, and schema migrations.
4. **Verification Gate:**
   - Validate that commit prefixes match conventional commit specs and PR descriptions accurately reflect every file modified in `git status`.

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.