plugins/autonomous-dev/skills/code-review/SKILL.md
10-point code review checklist covering correctness, tests, error handling, type hints, naming, security, and performance. Use when reviewing PRs or evaluating code quality. TRIGGER when: code review, PR review, review checklist, code quality check. DO NOT TRIGGER when: writing new code, debugging, refactoring without review context.
npx skillsauth add akaszubski/autonomous-dev code-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.
Ensures every code review is thorough, consistent, and produces actionable feedback. Used by the reviewer agent.
Every review MUST evaluate all 10 items. No shortcuts.
except:)?Optional, Union, List, Dict correctly?snake_casePascalCaseUPPER_SNAKE_CASEexcept: that swallows errors silentlyNotImplementedError in shipped codepass as the sole body of a functionTODO without a linked issue numberEvery review MUST conclude with exactly one of:
FORBIDDEN:
REQUIRED:
## Review: [file or PR title]
### Checklist
1. Correctness: PASS/FAIL — [details]
2. Test Coverage: PASS/FAIL — [details]
3. Error Handling: PASS/FAIL — [details]
4. Type Hints: PASS/FAIL — [details]
5. Naming: PASS/FAIL — [details]
6. Security: PASS/FAIL — [details]
7. Style: PASS/FAIL — [details]
8. Documentation: PASS/FAIL — [details]
9. No Stubs: PASS/FAIL — [details]
10. Complexity: PASS/FAIL — [details]
### Findings
- [BLOCKING] file.py:42 — description
- [Nit:] file.py:88 — suggestion
### Test Results
[from STEP 8 artifact provided in context — do NOT re-run pytest]
### Verdict: APPROVED / REQUEST_CHANGES
"Looks good to me, ship it!"
Missing: checklist, line references, test results, security review.
## Review: lib/auth.py
### Checklist
1. Correctness: PASS — token validation logic matches RFC 7519
2. Test Coverage: PASS — 12 tests, all pass, covers expiry edge case
...
6. Security: FAIL — API key on line 34 is hardcoded
### Findings
- [BLOCKING] auth.py:34 — Hardcoded API key, move to env var
### Verdict: REQUEST_CHANGES
Spending 10 comments on variable naming while an off-by-one error goes unnoticed.
Approving with known BLOCKING issues and a verbal promise to fix. If it is BLOCKING, it blocks.
development
One topic, one home. Routes content to its canonical store (CLAUDE.md, PROJECT.md, MEMORY.md, docs/, memory/) and audits for duplication. TRIGGER when: auditing CLAUDE.md/PROJECT.md/MEMORY.md sizes, deduplicating docs, applying the content-allocation pattern to a new repo, running /align --content. DO NOT TRIGGER when: implementing features, writing tests, routine code edits, debugging.
development
GenAI-first testing with structural assertions, congruence validation, and tier-based test structure. Use when writing tests, setting up test infrastructure, or validating coverage. TRIGGER when: test, pytest, coverage, TDD, test patterns, congruence, validation. DO NOT TRIGGER when: production code implementation, documentation, config-only changes.
testing
Prompt engineering patterns for writing agent prompts and skill files — constraint budgets, register shifting, HARD GATE patterns, anti-personas. Use when writing or reviewing agents/*.md or skills/*/SKILL.md. TRIGGER when: agent prompt, skill file, prompt engineering, model-tier compensation, HARD GATE, prompt quality. DO NOT TRIGGER when: user-facing docs, README, CHANGELOG, config files.
testing
7-step planning workflow for pre-implementation design. Enforced by plan_gate hook, critiqued by plan-critic agent. Use when creating plans, design documents, or architecture decisions before implementation. TRIGGER when: plan, planning, /plan, design document, architecture decision. DO NOT TRIGGER when: implementation, coding, testing.