style-checker
Skill1 starsChanged 30 days agoMITView on GitHub
Use when checking, reviewing, or auditing code style, formatting, or naming conventions — even if the user just says 'check my code style' or 'does this follow Google style'.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- microsoft/apm-sample-packagetheir own version, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- microsoft/apm-sample-package★ 18same 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 repository11 other files it gives its agents.
- addressing-findingsSkill
- analyze-codeSkill
- brainstormSkill
- coding-disciplineSkill
- designing-interfacesSkill
- guiding-manual-testingSkill
- knowledge-baseSkill
- researchSkill
- test-driven-developmentSkill
- using-software-specialistsSkill
- writing-unit-testsSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 38
If no supported-language files are detected, report this and exit.
- Distinctive: line 42
If the user asks a style question rather than requesting a scan (e.g., "how should I name constants in Go?"), answer directly from the …
- Distinctive: line 93
If a file has many violations of the same rule, report the first 3 occurrences and note "and N more".
- Distinctive: line 101
Reporting test/spec files when not asked: when the user says "check my code", they almost always mean source files — deprioritize tests …
≈ “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
Google Style Checker
Reviews code against Google's official style guidelines for formatting and naming only. Does not check logic, architecture, or code quality (SOLID, smells). Does not auto-fix — reports violations to fix.
Supported languages: C++, C#, Go, Haskell, HTML/CSS, Java, JavaScript, JSON, Kotlin, Python, TypeScript, Shell, Markdown.
Workflow
When invoked from analyze-code: return a flat findings list (severity + file:line + rule). Skip the full report template in Step 4 — the outer audit owns the report shape.
Step 1: Identify languages and load references
Scan the repo (or the path the user provided) and, for each supported language present, load its reference file before scanning code.
| Language | Reference file | Detection |
| Python | references/python.md | *.py |
| Java | references/java.md | *.java |
| JavaScript | references/javascript.md | *.js, *.jsx, *.mjs |
| TypeScript | references/typescript.md | *.ts, *.tsx |
| Go | references/go.md | *.go |
| Shell | references/shell.md | *.sh, *.bash |
| Markdown | references/markdown.md | *.md |
| C++ | references/cpp.md | *.cc, *.cpp, *.cxx, *.h, *.hh, *.hpp |
| C# | references/csharp.md | *.cs |
| Haskell | references/haskell.md | *.hs, *.lhs |
| HTML/CSS | references/htmlcss.md | *.html, *.htm, *.css, *.scss, *.sass, *.gss |
| Kotlin | references/kotlin.md | *.kt, *.kts |
| JSON | references/json.md | *.json (data and API payloads; the reference lists tool config files to skip) |
Always skip: vendor/, node_modules/, .git/, *.pb.go, *_generated.go, and any file whose first lines contain // Code generated or # Generated. Deprioritize test/spec files (*_test.go, *.spec.*, test_*.py) unless the user explicitly asks to include them.
If no supported-language files are detected, report this and exit.
Step 2: Advisor mode (optional)
If the user asks a style question rather than requesting a scan (e.g., "how should I name constants in Go?"), answer directly from the loaded reference. You can also answer, then offer to scan relevant files.
Step 3: Scan for violations
For each file, check against the reference rules. Focus on:
- Naming conventions (case style for identifiers, packages, files)
- Formatting (indentation, line length, brace style)
- Import/module organization
- Comment and documentation style
Step 4: Produce the report
# Google Style Check Report
## Summary
- Files scanned: N
- Languages: [list]
- Total violations: N (Critical: N, High: N, Medium: N, Low: N)
## Critical
### <Language>
- `path/to/file.go:12` — **Rule**: Expected `lowerCamelCase` for unexported function, found `my_Function`
## High
### <Language>
- `path/to/file.py:45` — **Rule**: Class names must use `CapWords`, found `my_class`
## Medium
### <Language>
- `path/to/file.java:88` — **Rule**: Line exceeds 100 characters (found 117)
## Low
### <Language>
- `path/to/file.ts:10` — **Rule**: Use `import type` for type-only imports
## Clean files
List any files with zero violations. Omit this section if all files have violations.Severity Classification
| Severity | What it covers |
| Critical | Wrong exported/unexported casing in Go; tabs vs spaces; fundamental structure violations |
| High | Wrong case style for identifiers (classes, functions, constants, variables) |
| Medium | Line length, indentation size, brace placement, import ordering |
| Low | Comment formatting, blank lines, minor whitespace, optional style preferences |
Tips
- If a file has many violations of the same rule, report the first 3 occurrences and note "and N more".
- Go projects:
gofmtcompliance is the source of truth — note if runninggofmtwould auto-fix issues. - See expected_outputs/sample-report.md for a full example.
Common Mistakes
- Wrong severity for Go constants:
UPPER_SNAKE_CASEin Go is Critical (breaks the fundamental MixedCaps rule), not High. - Scanning generated or vendored code: the Step 1 skip list is mandatory, not optional.
- Reporting test/spec files when not asked: when the user says "check my code", they almost always mean source files — deprioritize tests unless explicitly requested.
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.