Agent skill
review-correctness
Analyze code for bugs and correctness problems using strict determination criteria. Returns structured findings without applying fixes. Use when the user asks to "review correctness", "scan my code for bugs", "find bugs in my changes", "look for bugs", "check for bugs", or "run a correctness review".
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/review-correctness
SKILL.md
Review Correctness
Analyze code for bugs and correctness problems. Return structured findings.
Step 1: Determine the Scope
Determine what to review:
- If a specific diff command was provided (e.g.,
git diff --cached,git diff main...HEAD), use that. - If a file list or directory was provided, review those files directly (read the full files, not a diff).
- If neither was provided, default to diffing against the repository's default branch (detect via
gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name').
Step 2: Review
- For diff scope: run the diff command to obtain the changes. For file scope: read the specified files.
- For each file, read enough surrounding context to understand the code
- Apply the bug determination criteria and return findings in the output format below
Bug Determination Criteria
Flag an issue only when ALL of these hold:
- It meaningfully impacts the accuracy, performance, security, or maintainability of the code
- The bug is discrete and actionable (not a general codebase issue or combination of multiple issues)
- Fixing it does not demand rigor beyond what exists in the rest of the codebase
- In diff mode: the bug was introduced in the changeset (do not flag pre-existing bugs). In file scope mode: this criterion does not apply
- The author would likely fix the issue if aware of it
- The bug does not rely on unstated assumptions about the codebase or author's intent
- Speculation is insufficient — identify the parts of the code that are provably affected
- The issue is clearly not an intentional change by the original author
Comment Standards
- Be clear about why the issue is a bug
- Communicate severity accurately — do not overstate
- Keep the body to one paragraph maximum
- No code chunks longer than 3 lines. Use markdown inline code or code blocks
- Explicitly communicate the scenarios, environments, or inputs needed for the bug to arise
- Use a matter-of-fact tone, not accusatory or overly positive
- Write so the author can immediately grasp the idea without close reading
- No flattery ("Great job...", "Thanks for...")
Priority Levels
- P0 — Drop everything. Blocking release or operations. Only for universal issues that do not depend on assumptions about inputs
- P1 — Urgent. Should be addressed in the next cycle
- P2 — Normal. To be fixed eventually
- P3 — Low. Nice to have
What to Ignore
- Trivial style unless it obscures meaning or violates documented standards
- In diff mode: pre-existing issues not introduced by this changeset
Output Format
Return findings as a numbered list. For each finding:
### [P<N>] <title (imperative, ≤80 chars)>
**File:** `<file path>` (lines <start>-<end>)
<one paragraph explaining why this is a bug, what scenarios trigger it, and the impact>
After all findings, add:
## Overall Verdict
**Correctness:** <correct | incorrect>
<1-3 sentence explanation>
If there are no qualifying findings, state that the code looks correct and explain briefly.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?