skills/caveman-review/SKILL.md
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
npx skillsauth add fmflurry/settings-opencode caveman-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.
Format: L<line>: <problem>. <fix>. — or <file>:L<line>: ... when reviewing multi-file diffs.
Severity prefix (optional, when mixed):
🔴 bug: — broken behavior, will cause incident🟡 risk: — works but fragile (race, missing null check, swallowed error)🔵 nit: — style, naming, micro-optim. Author can ignore❓ q: — genuine question, not a suggestionDrop:
nit: insteadq:Keep:
❌ "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 for: security findings (CVE-class bugs need full explanation + reference), architectural disagreements (need rationale, not just a one-liner), and onboarding contexts where the author is new and needs the "why". In those cases write a normal paragraph, then resume terse for the rest.
Reviews only — does not write the code fix, does not approve/request-changes, does not run linters. Output the comment(s) ready to paste into the PR. "stop caveman-review" or "normal mode": revert to verbose review style.
development
Scaffolds and extends Angular 18+ standalone features using Clean Architecture with DDD layering (presentation/application/domain/infrastructure), custom signal-based stores, facade pattern, and ports/adapters dependency inversion. Use when creating new Angular features/domains, adding use cases/facades/stores/ports/adapters, refactoring legacy NgModule/NgRx code toward clean architecture, or working with cross-domain communication via context registry.
development
Pre-merge code review for Angular + TypeScript pull requests. Diffs current branch against a target branch, applies Angular-specific checklists (signals, RxJS, clean architecture, flurryx, TS strict), runs lint + tsc, and emits a tiered report (verbose for juniors, terse for seniors). Auto-loads project AGENTS.md rules. Use when user runs /cop-review, says "pre-merge review", "review before merging", "check my PR against <branch>", or invokes the merge-cop agent.
testing
Use this skill for any git work such as creating branches, staging changes, writing commit messages, pushing branches, or preparing pull requests. Delegates git execution to the git-specialist agent.
development
Signal-first reactive state management for Angular. Bridge RxJS streams into cache-aware stores, keyed resources, mirrored state, and replayable history. Use when generating or modifying Angular code that uses flurryx for state management, or when scaffolding new feature modules that follow the flurryx facade pattern.