pr — Claude Code skill: what it does, how to install
This skill structures pull request bodies with a summary, evidence, and merge-risk notes. Use it when reviewers need a compact view of what changed and how the change was checked.
/plugin marketplace add mattpocock/skills
/plugin install mattpocock-skills@mattpocockWhat pr does
For Summary, the skill suggests a format that fits the change: pseudocode, a call tree, a component or file tree, Mermaid, or a diff. Evidence should compare before and after, using examples such as screenshots, output, or test results. Merge Danger covers whether the merge is reversible and the potential blast radius.
Keep the prose brief, skip the preamble, and use the project’s terms from GLOSSARY.md. It suits authors who want reviewers to see both the shape of a change and evidence that it works. Skip it if your team prefers unstructured PR descriptions.
What it helps with
- Show the call flow affected by a change
- Compare output before and after a fix
- Map component or file responsibilities in a PR
- Describe whether a merge is reversible
Example prompts for the agent
- Write a PR body for this change and show the call flow in Summary.
- Add before-and-after test results to Evidence.
- Use a diff for Summary and assess Merge Danger.
How to install pr
1Plugin marketplace
/plugin marketplace add mattpocock/skills/plugin install mattpocock-skills@mattpocockThis installs the whole mattpocock-skills plugin with all its skills
2Skills CLI (Vercel)
npx skills add mattpocock/skills --skill pr -a claude-code3Manually: put the files in place
~/.claude/skills/pr/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pr/
Manually: put the files in place
.agents/skills/pr/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/pr/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install mattpocock/skills pr2Manually: put the files in place
.github/skills/pr/SKILL.mdPlatform CLI
gemini skills install https://github.com/mattpocock/skills --path skills/engineering/prManually: put the files in place
.devin/skills/pr/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set32
The whole set →Similar
Questions about pr
How do I install pr in Claude Code?
Add the marketplace with /plugin marketplace add mattpocock/skills, then install with /plugin install mattpocock-skills@mattpocock. The provided options also include npx skills add mattpocock/skills --skill pr -a claude-code.
What does the pr skill do?
It helps write PR bodies with Summary, Evidence, and Merge Danger sections. For the summary, it recommends a representation that fits the change, such as a file tree or diff.
What can I use as evidence in a PR?
The skill calls for concrete before-and-after evidence, such as screenshots, program output, or test results.
Source text
SKILL.md · MIT
---
name: pr
description: "Use when writing a PR body."
metadata:
credits:
skill: show-me
author: Dex Horthy
organisation: Humanlayer
url: "https://github.com/humanlayer/skills/blob/main/plugins/show-me/skills/show-me/SKILL.md"
---
Use this template for writing the PR body:
```markdown
## Summary
<diagram, diff-sketch, or tree>
## Evidence
- **Before:** <screenshot/output/failing test run>
**After:** <screenshot/output/passing test run>
## Merge Danger
**Door:** <one-way or two-way>
<optional: description>
**Blast Radius:** <one-word description>
<optional: potential ramifications of merge>
```
## Sections
Skip all preambles and keep prose brief. Use the user's domain language from `GLOSSARY.md`.
### Summary
Pick the smallest view that makes the key point clear.
- Show logic or an algorithm as pseudocode:
```text
on(save)
if content is unchanged
return cached result
write new content
return fresh result
```
- Show runtime control flow as a call tree:
```text
submitForm
createSession
persistPrompt
launchAgent
navigateToSession
```
- Show UI structure as a component tree, including state and module boundaries that matter:
```text
<SessionPage> (apps/example/src/routes/session.tsx)
useSessionEvents()
<SessionToolbar>
<RunSkillButton> (packages/ui)
```
- Show file responsibility or a broad refactor as a shallow file tree:
```text
src/
├── commands/ # parses user actions
├── sessions/ # owns session state
└── transport/ # sends API requests
```
- Show component interaction, control flow, or data flow with Mermaid:
```mermaid
sequenceDiagram
participant User
participant UI
participant Daemon
User->>UI: choose command
UI->>Daemon: send expanded prompt
Daemon-->>UI: stream result
```
- Use `diff` when the point is what changes and the surrounding shape already exists. Match the diff shape to the topic.
For a component change:
```diff
<SessionPage>
useSessionEvents()
<SessionToolbar>
+ <RunSkillButton />
<SessionTimeline>
+ <SkillResultCard />
```
For a file-layout change:
```diff
src/
├── commands/
+│ └── show-me.ts # expands the slash command
├── sessions/
-└── transport.ts
+└── transport/
+ ├── client.ts
+ └── stream.ts
```
For a call-tree or call-stack change:
```diff
submitForm
createSession
persistPrompt
+ expandSkillMention
launchAgent
- navigateToSession
+ navigateToSession
+ subscribeToEvents
```
For a state or control-flow change:
```diff
on(save)
- write content
+ if content is unchanged
+ return cached result
+ write new content
+ invalidate cache
```
- Show the whole block when most of it is new, when omitted context would hide ownership or order, or when the user needs a copyable target shape:
```ts
function expandSkill(command: string): string {
const skillName = command.slice(1);
return `use the ${skillName} skill`;
}
```
#### Guidance
Place each visual next to the short text it supports. Keep only the calls, files, props, states, and boundaries needed to answer the user's current question or the options to resolve the current discussion point.
You may use one of these, you may use several, it is unlikely you will use all of them. Use your judgement and don't overwhelm the user.
### Evidence
Concrete evidence that the change works. Show a before and after.
Screenshots are S-tier - when the environment is set up for it and the change is visual.
Execution-based evidence is A-tier. Test results, console output. Show the exact test that now fails and passes, using pseudocode.
### Merge Danger
Describe whether it's a one-way or two-way door. You can walk back through two-way doors, but not one-way doors. A PR that is cheap to roll back is lower risk. Changes that involve destructive actions or hard-to-reverse decisions are one-way doors.
The blast radius is the potential impact or scope of the changes introduced by this PR. Consider all possibilities. Examples are layout shift, breakages for consumers, mobile responsiveness, etc.
© Matt Pocock · MIT · mattpocock/skills