smell
Skill8 starsChanged 35 days agoMITView on GitHub
Run smell-reviewer against a file, directory, or the current working-tree changes. Use when someone says: check for code smells, smell review, find structural issues, review for smells, smell check, look for god classes, find long methods, check for dead code, smell this file, smell-review PR #N. Also use after /implement or /review-pr when the user wants a dedicated structural pass. Do NOT use when the user wants a full review pipeline -- use /review-pr instead.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- smallnest/goal-workflowtheir own version, first seen Jul 3, 2026
- tarikhamilton/claude-skillstheir own version, first seen Jul 1, 2026
- jidechao/claude-codex-goal-workflowtheir own version, first seen Jun 4, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- smallnest/goal-workflow★ 283same name
- jidechao/claude-codex-goal-workflow★ 4same name
- tarikhamilton/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository30 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- backlogSkill
- conventionsSkill
- debugSkill
- devops-azureSkill
- devops-githubSkill
- devopsSkill
- hotfixSkill
- implementSkill
- interview-meSkill
- lint-agentsSkill
- memory-auditSkill
- memory-querySkill
- obsidian-briefSkill
- obsidian-captureSkill
- obsidian-dailySkill
- obsidian-recapSkill
- obsidian-searchSkill
- obsidianSkill
- onboardSkill
- pack-reviewSkill
- planSkill
- refactorSkill
- repo-mapSkill
- review-prSkill
- scaffoldSkill
- setup-projectSkill
- spec-intakeSkill
- system-checkSkill
- whatSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Run a targeted structural smell analysis on a specific target or the current working-tree changes.
- Distinctive: line 13
If the user supplied file paths, use those directly.
- Very specific: line 14
If the user supplied a directory, analyze all source files within it (skip bin/, obj/, node_modules/, dist/, migrations/).
- Very specific: line 16
If the user supplied a PR number, run gh pr diff <number> --name-only to get the changed files, then use those.
- Distinctive: line 18
If no target was supplied, run git diff main...HEAD --name-only (or git diff HEAD --name-only if on main) to discover changed files.
- Distinctive: line 27
If the filtered list is empty, tell the user: "No source code files found in the target — smell-reviewer analyzes application logic, not …
- Distinctive: line 50
Large directories: If the target contains more than 20 source files, warn the user that the review may take longer and offer to scope it to …
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Smell Review
Run a targeted structural smell analysis on a specific target or the current working-tree changes.
1. Determine the target
- If the user supplied file paths, use those directly.
- If the user supplied a directory, analyze all source files within it
(skip
bin/,obj/,node_modules/,dist/,migrations/). - If the user supplied a PR number, run
gh pr diff <number> --name-onlyto get the changed files, then use those. - If no target was supplied, run
git diff main...HEAD --name-only(orgit diff HEAD --name-onlyif on main) to discover changed files. Confirm the list with the user before proceeding.
Filter the file list to source code only:
- Include:
.cs,.ts,.vue,.tsx,.jsx,.py,.go,.java,.rb,.rs - Exclude: config files (
.json,.yaml,.toml,.xml), migrations, SQL scripts, test fixtures, generated files
If the filtered list is empty, tell the user: "No source code files found in the target — smell-reviewer analyzes application logic, not config or documentation."
2. Run smell-reviewer
Dispatch the smell-reviewer agent with:
- The filtered list of file paths
- Any relevant context the user provided (e.g., "focus on the service layer", "we just refactored this module")
- The contents of
docs/CONVENTIONS.mdif it exists (so the agent can read suppressions without a separate file read)
3. Present findings
The smell-reviewer agent will produce a severity-labeled report and offer CONVENTIONS.md suppression options directly. No synthesis step is needed — its output is the result.
Gotchas
- No changed files on a fresh branch:
git diff main...HEADreturns nothing if no commits exist. Ask the user to supply a target file or directory instead. - Large directories: If the target contains more than 20 source files, warn the user that the review may take longer and offer to scope it to a subdirectory or specific files.
- Smell review vs full review: This skill runs smell-reviewer only. For a
full quality pass (code quality + security + performance + smells), use
/review-prinstead. - Fixing findings: This skill surfaces structural issues — it does not fix
them. If the user asks to fix a Critical smell finding (e.g., "break apart
this God class"), route to
/refactoror invoke the appropriate engineer agent.
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.

