templates/skills/core/rulebook-terse-review/SKILL.md
Ultra-compressed code review comments. One line per finding: location, problem, fix. Use when user says 'review this PR', 'code review', 'review the diff', or invokes /rulebook-terse-review. Independent of the base rulebook-terse mode.
npx skillsauth add hivellm/rulebook Rulebook Terse ReviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Write code-review comments terse and actionable. One line per finding. Location, problem, fix. No throat-clearing.
L<line>: <severity> <problem>. <fix>.
For multi-file diffs:
<file>:L<line>: <severity> <problem>. <fix>.
Use when mixing severities in the same review. Optional when all findings are the same severity.
| Prefix | Meaning |
|--------|---------|
| 🔴 bug: | Broken behavior; will cause an incident. |
| 🟡 risk: | Works but fragile (race, missing null check, swallowed error, unvalidated input). |
| 🔵 nit: | Style, naming, micro-optim. Author can ignore without consequence. |
| ❓ q: | Genuine question, not a suggestion. |
❓ q:.🔵 nit: instead.why if the fix isn't obvious from the problem statement."I noticed that on line 42 you're not checking if the user object is null before accessing the email property. This could potentially cause a crash if the user is not found in the database. You might want to add a null check here."
L42: 🔴 bug: user can be null after .find(). Add guard before .email.
"It looks like this function is doing a lot of things and might benefit from being broken up into smaller functions for readability."
L88-140: 🔵 nit: 50-line fn does 4 things. Extract validate/normalize/persist.
"Have you considered what happens if the API returns a 429? I think we should probably handle that case."
L23: 🟡 risk: no retry on 429. Wrap in withBackoff(3).
Drop terse mode and write full prose for:
why, not just the what.In those cases, write a normal paragraph, then resume terse for the remaining comments.
Review-only. Does NOT:
Output is the comment(s), ready to paste into the PR review UI.
Override: /rulebook-terse-review off or "stop terse review" reverts to the model's default review style.
research
Create structured analyses with numbered findings, execution plans, and task materialization
research
Author a rulebook task spec interactively — research, draft, ask the user clarifying questions, confirm, then create the tasks in rulebook ready for /rulebook-driver. Use when the user wants to plan/spec a feature before implementing.
development
Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'.
data-ai
Autonomous AI agent loop for iterative task implementation (@hivehub/rulebook ralph)