pr · yeachan-heo — Claude Code skill: what it does, how to install
pr — a Claude Code skill that drafts pull request descriptions from the session paper trail. It compiles verified test evidence, visual summaries, and rollback risks into a markdown body.
MIT 161 installs ★ 40,997 updated 2026-10-24
npx skills add Yeachan-Heo/oh-my-claudecode --skill pr -a claude-codeWhat pr does
Assembles a pull request description using only artifacts already recorded in the working session. The generated text includes a one-sentence summary paired with a minimal visual proof, such as pseudocode, a component tree, or a Mermaid diagram.
Pulls test and build results directly from the verification pass as before-and-after pairs. It does not re-run tests or invent unverified claims. Terms follow GLOSSARY.md or CONTEXT.md. Rollback difficulty is classified through the ADR test, marking two-way doors or naming why a reversion would be costly alongside a one-line blast radius.
What it helps with
- draft a pull request body from session records
- attach minimal visual proof for code changes
- compare before and after test results in PR notes
- evaluate PR rollback cost and blast radius
Example prompts for the agent
- Draft a PR body from the latest verification pass and diff
- Generate the PR description for this feature branch
- Prepare the PR markdown with ADR reversibility checks
How to install pr
1Skills CLI (Vercel)
npx skills add Yeachan-Heo/oh-my-claudecode --skill pr -a claude-code2Manually: put the files in place
~/.claude/skills/pr/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pr/
1Skills CLI (Vercel)
npx skills add Yeachan-Heo/oh-my-claudecode --skill pr -a codex2Manually: put the files in place
.agents/skills/pr/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Yeachan-Heo/oh-my-claudecode --skill pr -a cursor2Manually: put the files in place
.cursor/skills/pr/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Yeachan-Heo/oh-my-claudecode skills/pr2Manually: put the files in place
.github/skills/pr/SKILL.md1Skills CLI (Vercel)
npx skills add Yeachan-Heo/oh-my-claudecode --skill pr -a gemini-cli2Platform CLI
gemini skills install https://github.com/Yeachan-Heo/oh-my-claudecode --path skills/prManually: put the files in place
.devin/skills/pr/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Yeachan-Heo/oh-my-claudecode --skill pr -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about pr
How to install pr in Claude Code?
Run npx skills add Yeachan-Heo/oh-my-claudecode --skill pr -a claude-code. The skill file is placed in ~/.claude/skills/pr/SKILL.md.
What does pr do?
It creates a structured pull request body from session evidence, diff inspection, and project glossary terms. It outputs ready-to-paste markdown containing evidence checks and reversibility risks.
What is required for pr to work?
It relies on completed verification protocol outputs (build, lint, test) and project terms defined in GLOSSARY.md or CONTEXT.md.
Source text
SKILL.md · MIT
---
name: pr
description: Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
metadata:
credits:
summary-visuals: show-me
author: Dex Horthy
organisation: Humanlayer
url: "https://github.com/humanlayer/skills/blob/main/plugins/show-me/skills/show-me/SKILL.md"
merge-danger: mattpocock/skills
merge-danger-url: "https://github.com/mattpocock/skills"
---
# PR Body
When work lands behind a review, the PR body is the one artifact a reviewer outside the session reads. Everything it needs already exists in the paper trail — this skill assembles it and adds nothing that was not already established. The summary-visual discipline is inspired by show-me (credited in the frontmatter).
## Template
```markdown
## Summary
<one-line claim, then the smallest visual that proves it>
## Evidence
- **Before:** <output / failing check>
**After:** <output / passing check>
## Reversibility
<Rollback: cheap via <mechanism> | expensive because <reason>>
<Blast radius: one line>
```
## Sections
### Summary
State the change in one sentence, then show the smallest view that makes the point. Match the visual to the change:
- logic or an algorithm → pseudocode
- runtime control flow → a call tree
- UI structure → a component tree
- file responsibility or a broad refactor → a shallow file tree
- component interaction or data flow → a Mermaid diagram
- the delta itself → a diff shaped like the change (component, layout, call tree, or state machine)
Show the whole block only when most of it is new, omitted context would hide ownership, or the reviewer needs a copyable target shape. One visual usually suffices; never all forms.
### Evidence
Consume the verify protocol's output — BUILD, TEST, LINT, FUNCTIONALITY evidence, freshness rule inherited. Present before/after pairs: the exact check that failed before and passes after, quoted from the output itself. When the change is visual, prefer a captured screenshot; `qa-tester` can drive the runtime for one. Never re-collect evidence here and never claim evidence the verify pass did not produce.
### Reversibility
Run the ADR test on the diff itself — the same three questions launch applies to decisions: hard to reverse? surprising without context? the result of a real trade-off? A no on all three is a cheap rollback: say by what mechanism (revert the merge, toggle the flag). Any yes means an expensive rollback: say why. Classify the door first: a two-way door (undo is cheap and ordinary) needs no ceremony beyond naming the undo; a one-way door says so explicitly and names what makes the step irreversible. Link the ADR when the change implements or touches one. Close with the blast radius in one line — what else this change can move.
### Language
Terms come from `GLOSSARY.md` where a glossary exists (legacy yards not yet migrated keep it in `CONTEXT.md`). The PR is read outside the session; the glossary is the only vocabulary the reader shares with it.
## Triggers
- launch Phase 5, when the platform reviews through PRs: the completion report carries a PR body drafted by this skill.
- Any session that opens or materially updates a PR.
## Output
- The PR body, ready to paste
- The paper-trail pointers it relies on (verify evidence, ADRs, spec)
© Yeachan-Heo · MIT · Yeachan-Heo/oh-my-claudecode
Similar skills
All skills for Git and GitHub →pr by other authors comes first.