// Walks a diff against a 5-point review checklist. Use when the user asks "review this diff", "what should I check in this PR", or pastes code with a question like "anything wrong with this?". Reads files via Glob/Grep/Read; never edits.
| name | code-review-checklist |
| description | Walks a diff against a 5-point review checklist. Use when the user asks "review this diff", "what should I check in this PR", or pastes code with a question like "anything wrong with this?". Reads files via Glob/Grep/Read; never edits. |
Walk this diff against the five questions below. Stop after the first failure; the human can re-run after fixing.
Read the full diff first. Don't comment on individual hunks before you've seen the whole change. Use Read on each touched file to see surrounding context.
Five questions, in order. Stop at the first failure.
a. Does it pass the type-check / lint? If a CI signal exists, cite it. If not, scan for obvious type errors yourself.
b. Are there tests? New behavior without a test is a smell. Existing behavior changed without a test update is a smell.
c. What's the riskiest line? Pick ONE — the line that, if wrong, breaks production. Verify it explicitly.
d. Backwards compat? Did any public API change shape (params, return, schema)? Find callers via Grep.
e. Performance / blast radius? Does it add a loop in a hot path? A new DB query in a request handler? A retry without backoff?
Output format.
## Review verdict — <ship | hold | request-changes>
**Riskiest line:** <path:line> — <one sentence why>
**Notes:**
- <path:line> — <issue>
- <path:line> — <issue>
Anti-patterns.
REPLACE THIS — one-line trigger summary that tells Claude when to load this skill. Write it like a tool docstring, not a title. Concrete trigger phrases beat abstract descriptions. Example "Triggers when the user asks about <specific recurring task in your domain>; expects <input shape>; produces <output shape>."
Walks a diff against a 5-point review checklist. Use when the user asks "review this diff", "what should I check in this PR", or pastes code with a question like "anything wrong with this?". Reads files via shell; never edits.
Grounded retrieval over cohort 4 memory seeds (roster, lesson designs, dossiers, transcripts). Use when answering any question about what was taught, who's in the cohort, what dossiers exist, or what was said in a past session.
Q&A flow that produces a complete colleague-target.md and starter Constitution from a 5-field dossier. Use this when a cohort 4 student says they want help defining their AI coding colleague's target task, or when "dossier" / "colleague target" / "what should I build" comes up. Released as homework artifact at end of Lesson 1.