review-code-smells
Skill73 starsChanged 5 days agoApache-2.0View on GitHub
Review touched code for maintainability smells such as duplication, awkward indirection, suspicious clones, dead code, poor naming, and Boy Scout cleanup opportunities. Use when a broad review needs a dedicated maintainability pass or when the user asks for code-smell review specifically.
In this repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- add-learningSkill
- bump-rfcSkill
- closeoutSkill
- create-github-issueSkill
- create-planSkill
- create-pr-descriptionSkill
- fixSkill
- flag-compiler-bugSkill
- fleet-auditSkill
- hello-worldSkill
- loopSkill
- orchestrate-parallel-workSkill
- ralph-loopSkill
- review-and-fixSkill
- review-architectureSkill
- review-docs-claimsSkill
- review-incan-source-qualitySkill
- review-orchestrateSkill
- review-rfcSkill
- review-rust-proseSkill
- review-scopeSkill
- reviewSkill
- review-test-styleSkill
- start-workSkill
- testSkill
- write-commit-messageSkill
- write-rfcSkill
- yeet-prSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
Write a slice report at:
- Very specific: line 34
Do not write to the canonical .agents/state/review-report.md.
- Distinctive: line 44
Keep this pass practical. Do not invent refactors unrelated to the touched surface.
- Distinctive: line 53
Keep slice reports findings-first.
- Distinctive: line 76
If there are no findings, say so explicitly.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Review Code Smells — Incan Compiler
Purpose
/review-code-smells is a file-focused report-only reviewer for local maintainability issues.
Own:
- duplication
- dead code
- awkward or unnecessary indirection
- suspicious clones
- poor naming in touched code
- touched-code cleanup opportunities that satisfy the Boy Scout rule
Do not own:
- architecture-level placement decisions
- docs truthfulness
- test style details
- final branch-clean judgment
Output artifact
Write a slice report at:
.agents/state/review-report.code-smells.md
Do not write to the canonical .agents/state/review-report.md.
Workflow
- Review the touched code files assigned by the orchestrator.
- Flag:
- duplicated branches or helpers
- no-op/unused/dead surfaces
- awkward APIs or naming in touched code
- needless complexity relative to the actual requirement
- Keep this pass practical. Do not invent refactors unrelated to the touched surface.
- Classify each finding as either:
maintainabilitydesign-tension- or
bugThis classification is for downstream handling only. It must not be used to hide the finding.
Slice report shape
Keep slice reports findings-first. Only list clean surfaces when that clean call is non-obvious or useful for the orchestrator.
# Review Slice Report
- role: code-smells
- worker: <agent-id or stable label>
- status: in_progress | clean | blocked
## Scope
- assigned files:
- loaves/toolchain/incan-cli/src/lib.rs
## Findings
- [ ] warning | maintainability | dead cli surface | loaves/toolchain/incan-cli/src/lib.rs:313
`--bin` is exposed publicly but has no effect.
## Reviewed Clean Surfaces
- loaves/toolchain/incan-cli/src/commands/init.rs — maintainability reviewed; no findingsIf there are no findings, say so explicitly.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

