Our review
Runs the frontclippy CLI to audit HTML files, URLs, snapshots, or manifests for UI issues, accessibility, and behavioral problems.
Strengths
- Supports multiple audit types (check, trace-check, matrix-check).
- Can output SARIF format for CI integration.
- Works with various input types (local files, URLs, snapshots, manifests).
- Includes baseline and suppression features.
Limitations
- Requires the frontclippy repository to be set up with the Rust toolchain.
- Only analyzes the provided targets; cannot crawl entire sites.
- Output depends on target quality; no built-in visual regression.
When you need a detailed audit of a frontend surface for accessibility, keyboard flow, or stress testing.
When you need full end-to-end automated testing or visual diff comparisons.
Security analysis
CautionThe skill executes cargo run on a local Rust project, which involves compilation and execution of potentially untrusted code. It also performs network requests if a URL target is provided. These actions are inherent to the tool's purpose but require trust in the repository and target.
- •Runs `cargo run` which compiles and executes arbitrary code from the local repository; could have side effects if repository is untrusted.
- •Target parameter may be a URL, leading to unintended network requests during analysis.
Examples
Run frontclippy check on https://example.com and summarize the findings.Audit the local file checkout-chaos.html with frontclippy and output SARIF format.Run a trace-check on fixtures/checkout-chaos.html and show the results.name: frontclippy-audit description: Run frontclippy against a local HTML file, live URL, snapshot JSON, suite, or manifest and summarize the findings. Use when the user asks to audit a UI, inspect frontclippy output, emit SARIF, or run capture plus analysis.
frontclippy-audit
Use this in the frontclippy repo when the user wants a real audit run instead of a theoretical explanation.
Workflow
- Work from the repo root.
- Choose the narrowest command for the artifact the user provided:
- Local HTML file or live URL:
cargo run -p frontclippy-cli -- check <target>
- Behavioral or keyboard-flow audit:
cargo run -p frontclippy-cli -- trace-check <target>
- Stress or matrix audit:
cargo run -p frontclippy-cli -- matrix-check <target>
- Snapshot JSON:
cargo run -p frontclippy-cli -- analyze <snapshot.json>
- Related snapshots:
cargo run -p frontclippy-cli -- suite-analyze <snapshot-a.json> <snapshot-b.json> [...]
- Manifest:
cargo run -p frontclippy-cli -- manifest-check <manifest.toml>
- Add
--format sarifwhen the user wants CI or code-scanning output. - Add
--config,--baseline,--suppressions, or--write-baselinewhen review state matters. - If no target is provided, use
fixtures/frontclippy.manifest.tomlfor a broad demo orfixtures/checkout-chaos.htmlfor a single-surface demo.
Response Pattern
Return:
- the exact command that ran
- the finding count and highest severity
- whether findings were configured, suppressed, or baselined
- the most relevant next step
Next.js App Router Expert
Development
A skill that turns Claude into a Next.js App Router expert.
README Generator
Development
Creates professional and comprehensive README.md files for your projects.
API Documentation Writer
Development
Generates comprehensive API documentation in OpenAPI/Swagger format.