Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Pr Description

ASecurity

Write a clear pull request description. Use when the user says "write a PR description", "PR template", "pull request description", "how do I describe this change", "commit message for this", "document this change", "open a PR for", or is about to merge code and needs to communicate what changed and why - even if they don't explicitly say "PR description".

20 stars
0 votes
0 copies
0 views
Added 10/4/2026
ai-agentsgotesting

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add qa-aman/claude-skills --skill pr-description --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pr Description?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Pr Description
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/qa-aman-pr-description/badge)](https://www.skillsdirectory.com/skills/qa-aman-pr-description)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: pr-description
description: >
  Write a clear pull request description. Use when the user says "write a PR description",
  "PR template", "pull request description", "how do I describe this change",
  "commit message for this", "document this change", "open a PR for",
  or is about to merge code and needs to communicate what changed and why
  - even if they don't explicitly say "PR description".
---

## Overview

Based on **"The Pragmatic Programmer"** by Hunt & Thomas. Hunt & Thomas: "It's not just code you're writing - it's communication." A PR description is a letter to your reviewers (and to your future self). It should answer: what changed, why it changed, how to verify it, and what to watch out for. A reviewer who has to read all the code to understand the PR is doing your job for you.

## Workflow

### Step 1: Write the title
Format: `[type]: [short description in imperative mood]`

Types: `feat`, `fix`, `refactor`, `test`, `chore`, `docs`

Rules:
- Imperative mood: "add pagination" not "added pagination" or "adds pagination"
- Under 72 characters
- Specific: "fix null pointer in payment processing" not "fix bug"

### Step 2: Write the Summary
2-4 sentences. Answer: what does this PR do?

Write for someone who hasn't seen the issue, ticket, or conversation. They should understand the change from this paragraph alone.

### Step 3: Write the Motivation (Why)
Why was this change needed? Link the ticket but don't rely on the link - links rot.

If it's a bug fix: what was broken and what impact did it have?
If it's a feature: what user need or business goal does it serve?
If it's a refactor: what was wrong with the old approach and what does the new approach enable?

### Step 4: Write the Approach (How)
For non-trivial changes: describe the key technical decisions.
- Why this approach over the alternative?
- What tradeoffs were made?
- What did you try that didn't work?

Don't explain what the code does (reviewers can read it). Explain what the code does that isn't obvious from reading it.

### Step 5: Write the Testing section
What did you do to verify this works?
- Unit tests added/updated?
- Manual testing steps?
- Environments tested on?

If there are no tests: say why (legacy code, trivial change, etc.).

### Step 6: Add screenshots or recordings (for UI changes)
Before/after screenshots are worth 1000 words. If the change is visual, include them. Always.

### Step 7: Note anything special for reviewers
- Areas of concern you want extra eyes on
- Known limitations of this approach
- Follow-up work deferred to a future PR

## Template

```markdown
## Summary
[2-4 sentences: what this PR does]

## Motivation
[Why this change was needed. Don't rely on the ticket link alone.]

## Approach
[Key technical decisions and why. What's non-obvious about the implementation.]

## Testing
- [ ] Unit tests: [added / updated / not applicable - reason]
- [ ] Manual testing: [steps taken]
- [ ] Environments: [local / staging / production]

## Screenshots (if UI change)
[Before] [After]

## Notes for reviewers
[Areas of concern, known limitations, follow-up work]
```

## Anti-Patterns

**1. Title that describes the ticket, not the change**
Bad: "JIRA-1234 user stuff"
Good: "feat: add email verification on user signup"

**2. Motivation that just links the ticket**
Bad: "See JIRA-1234"
Good: "Users could sign up with typo'd email addresses and never receive activation emails, causing support tickets. This adds verification before account creation."

**3. No testing section**
Bad: PR with no mention of how it was tested.
Good: Even "tested manually by logging in as a new user on staging" is better than nothing.

**4. 2000-line PRs**
Bad: One massive PR with 15 features and 4 bug fixes.
Good: PRs should be reviewable in 30 minutes. If it's larger, split it.

## Quality Checklist

- [ ] Title: type prefix + imperative mood + under 72 chars
- [ ] Summary explains the change to someone with zero context
- [ ] Motivation explains why (not just what ticket number)
- [ ] Approach explains non-obvious decisions
- [ ] Testing section describes what was tested and how
- [ ] Screenshots included for any UI changes
- [ ] PR size is reviewable (under 400 lines of meaningful changes)

Attribution

qa-amanqa-aman
View sourceSee grades on GitHubMore from qa-aman →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →