Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Write a reviewer-first pull-request description from the actual branch diff. Use when opening a PR or asked to write/improve a PR description.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 5% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-19 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-22 | ✗→✓ | ▲ Improved | -8% | 0% |
The reader is a reviewer deciding how to review, not a historian. Write from the diff, not from memory of the conversation.
git log main..HEAD --oneline andgit diff main...HEAD --stat. Read the diff of every file a reviewer will question.
("Checkout fails for SSO users" beats "Update auth flow").
first, then refactors, then mechanical churn (renames, formatting) called out explicitly so reviewers can skim past it.
covers it, say which jobs; if manual, give the click-path.
plan. One line each. Omit the section only if genuinely none.
the risky part") — reviewers allocate attention where the author points.
markdownFixes checkout failing for SSO users (#412). **What** - Treat IdP-initiated sessions as authenticated in the cart guard (behavior) - Extract session checks into `session.ts` (refactor, no behavior change) **Verify**: `npm test` (all green) + manual SSO login → add to cart → checkout. **Risk**: session guard touches every authed route; revert is a single commit. Focus review on `session.ts:40-75`.
Other measured skills in the registry, with their headline benchmark lift.