agentleFS
illegalstudioillegalstudio/elephc/.claude/skills/analyze-using-rustrover/SKILL.md

analyze-using-rustrover

Skill812 starsChanged 42 days agoMITView on GitHub

Run RustRover IDE inspections on the codebase and produce a structured report of errors, warnings, and code quality issues.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the Glob tool to find every .rs file in the project:

    line 19
  2. Very specific:

    Run mcp__rustrover__get_file_problems with errorsOnly: true on every discovered .rs file.

    line 28
  3. Very specific:

    Run mcp__rustrover__get_file_problems with errorsOnly: false on every discovered .rs file.

    line 36
  4. Distinctive:

    Run these commands to cross-validate RustRover findings:

    line 47
  5. Distinctive:

    Run inspections in parallel to save time (batch up to 6 files per tool call)

    line 120
  6. Very specific:

    Always cross-check RustRover errors with cargo build — false positives are common on large files

    line 121
  7. Distinctive:

    Do NOT fix any code. Only report findings.

    line 122
  8. Very specific:

    If no MCP RustRover tools are available, inform the user and suggest running cargo clippy instead

    line 123

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Analyze Using RustRover

You are a code quality analyst. Use the RustRover MCP tools to inspect the elephc codebase and produce a structured report.

Scope

By default, analyze all .rs source files in the project. If the user specifies a file or directory, limit the analysis to that scope.

Steps

1. Discover all source files

Use the Glob tool to find every .rs file in the project:

pattern: "src/**/*.rs"

This ensures the analysis covers all files, including any newly added modules.

2. Errors pass

Run mcp__rustrover__get_file_problems with errorsOnly: true on every discovered .rs file. Always pass projectPath set to the current working directory.

Batch calls in parallel (up to 6 per message) to save time. Use relative paths from the project root (e.g., src/codegen/mod.rs).

Collect all errors.

3. Warnings pass

Run mcp__rustrover__get_file_problems with errorsOnly: false on every discovered .rs file.

Batch calls in parallel. Collect all warnings.

Categorize warnings into:

  • Duplicated code: note the file, line, and fragment length
  • Unnecessary path prefixes: note the file and the prefix that could be simplified
  • Other warnings: anything else RustRover flags

4. Verify with compiler

Run these commands to cross-validate RustRover findings:

cargo build 2>&1 | tail -5
cargo clippy 2>&1 | grep "warning:" | grep -v "generated"

This confirms whether RustRover errors are real or false positives. RustRover sometimes fails to resolve impl blocks in large files — if cargo build succeeds, those are false positives.

5. Also analyze tests and main

Include src/main.rs and all files in tests/ in the analysis:

pattern: "tests/**/*.rs"

Output Format

## RustRover Inspection Report

**Files analyzed:** N

### Build Validation
- `cargo build`: CLEAN / N warnings
- `cargo clippy`: CLEAN / N warnings
- Clippy details: (list if any)

### Real Errors
(Errors confirmed by both RustRover and cargo build)

| File | Line | Severity | Description |
|------|------|----------|-------------|
| ... | ... | ERROR | ... |

If none: "No real errors found."

### False Positives
(RustRover errors that cargo build does not reproduce)

| File | Count | Likely cause |
|------|-------|-------------|
| ... | ... | Large file / impl block resolution |

### Code Quality Warnings

#### Duplicated Code
| File | Line | Fragment length | Description |
|------|------|-----------------|-------------|
| ... | ... | N lines | ... |

Summary: N duplicated fragments across M files. Top candidates for extraction: (list the most impactful)

#### Unnecessary Path Prefixes
| File | Line | Current | Suggested |
|------|------|---------|-----------|
| ... | ... | `self::functions::` | `functions::` |

#### Other Warnings
| File | Line | Description |
|------|------|-------------|
| ... | ... | ... |

### Summary
- Files analyzed: N
- Real errors: N
- False positives: N
- Code quality warnings: N (M duplications, K path prefixes, J other)
- Recommendation: (actionable next steps if any)

Important

  • Discover files dynamically with Glob — never use a hardcoded file list
  • Run inspections in parallel to save time (batch up to 6 files per tool call)
  • Always cross-check RustRover errors with cargo build — false positives are common on large files
  • Do NOT fix any code. Only report findings.
  • If no MCP RustRover tools are available, inform the user and suggest running cargo clippy instead

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.