بنقرة واحدة
review-fix
Review uncommitted changes, fix actionable correctness issues, and verify the result.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Review uncommitted changes, fix actionable correctness issues, and verify the result.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Duplicate code detection using similarity-rs. Identifies refactoring candidates based on semantic similarity.
Duplicate code detection using similarity-rs. Identifies refactoring candidates based on semantic similarity.
Run performance benchmarks with criterion. Compare against baselines and profile hotspots.
Implementation verification - runs format, lint, test, and build checks on the workspace.
Production readiness audit - checks unwrap elimination, error handling, clippy, docs, channel usage, and test count.
Release deployment process for ccswarm. Version update, quality gates, build, tag, publish.
| name | review-fix |
| description | Review uncommitted changes, fix actionable correctness issues, and verify the result. |
| user-invocable | true |
| context | fork |
| agent | review-fix-agent |
When subagents are enabled in Codex, prefer delegating this workflow to the review-fix-agent custom agent.
Review uncommitted changes, fix actionable issues, and verify the result.
git status --short and git diff --stat HEAD to determine what changed.Run build and lint to establish a clean starting point:
cargo clippy --workspace -- -D warnings 2>&1 | tail -20
cargo test --workspace --no-run 2>&1 | tail -5
If the baseline already fails, report the failures and stop. Do not mask pre-existing breakage.
Inspect the diff and new untracked files. Check for:
| Category | What to look for |
|---|---|
| Stale references | Deleted modules, commands, docs, or templates still referenced |
| Code duplication | Identical structs or functions across files worth extracting |
| Provider abstraction gaps | Hard-coded CLI names instead of the AgentProvider trait |
| Dead async | Async work discarded and then repeated synchronously |
| Sort instability | Utc::now() used as a fallback sort key |
| Hardcoded paths | Filesystem paths that should be relative to repo_path |
| Unused params | Accepted CLI arguments silently ignored |
| Security | Path traversal, credential leaks, unchecked user input |
Classify each finding:
For each fix-level finding:
cargo clippy --workspace -- -D warnings
cargo test --workspace --no-run
If clippy or test compilation fails, revert the offending edit and downgrade it to a warning.
Output a structured summary:
## Review + Fix Report
### Fixed
- <file>:<line> - <description>
### Warnings
- <file>:<line> - <description>
### Notes
- <description>
### Verification
- clippy: PASS / FAIL
- test compile: PASS / FAIL
- files modified: N