القائمة
Code review with automatic fix. Detects bugs, stale references, code duplication, provider abstraction gaps, and sort instability — then fixes and verifies.
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 | Code review with automatic fix. Detects bugs, stale references, code duplication, provider abstraction gaps, and sort instability — then fixes and verifies. |
| user-invocable | true |
| context | fork |
| agent | review-fix-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 still referenced in routing, docs, templates |
| Code duplication | Identical structs/functions across multiple files (> 10 lines, > 90% similarity) |
| Provider abstraction gaps | Hard-coded CLI names (claude, codex, gh copilot) instead of AgentProvider trait |
| Dead async | Async operations whose results are discarded (let _ = tokio::...await.ok() then re-done synchronously) |
| Sort instability | Utc::now() used as fallback sort key (non-deterministic) |
| Hardcoded paths | Filesystem paths that should be relative to repo_path |
| Unused TODO params | CLI arguments accepted but silently ignored (_param: T) |
| Security | Path traversal in user-supplied IDs, credential leaks |
Classify each finding:
For each 🔴 finding:
cargo clippy --workspace -- -D warnings
cargo test --workspace --no-run
If clippy or test compilation fails, revert the offending edit and report it as 🟡 instead.
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