How this skill is triggered — by the user, by Claude, or both
Slash command
/code-quality:find-bugsThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Review the entire codebase for bugs and write a summary to `bugs-summary.md` in the project root.
Review the entire codebase for bugs and write a summary to bugs-summary.md in the project root.
Detect the project stack: Read build/manifest files (e.g., package.json, build.gradle.kts, Cargo.toml,
go.mod, pyproject.toml, pom.xml) to identify the language, framework, and build tool.
Discover source files: Glob for production source files using patterns appropriate to the detected stack (e.g.,
src/**/*.ts, **/src/main/**/*.kt, **/*.go, src/**/*.py).
Discover test files: Glob for test files using the project's test directory conventions.
Read build configuration to understand dependencies, plugins, and build setup.
Read every source file to understand the full codebase before looking for issues.
Read every test file to understand what is already tested and whether tests are correct.
Run the test suite using the project's test command (e.g., npm test, ./gradlew test, cargo test,
go test ./..., pytest) to check for failing tests.
Identify bugs by looking for:
Check for design issues worth noting:
Write bugs-summary.md: Create or overwrite bugs-summary.md in the project root with the following structure:
# Bug Summary
## Open
### 1. Short title
**File:** `path/to/file.ext`
Description of the bug, why it's a problem, and what the expected behavior should be.
### 2. ...
## Design Observations (not bugs, but worth noting)
### Short title
Description.
bugs-summary.md exists, read it first and preserve any items marked as "FIXED" in a
Fixed section at the topReport: Summarize how many bugs were found and give a brief overview of the findings.
npx claudepluginhub mattbobambrose/mattbobambrose-claude-skills --plugin code-qualityRuns a structured 14-dimension bug hunt using Draft context (architecture, tech-stack, product) to eliminate false positives. Generates severity-ranked reports with code evidence, data flow traces, and optional regression tests.
Identifies code defects with language detection, documents them via repro plans and evidence trails, proposes idiomatic fixes, and outlines verification. For bug reviews, reports, pre-releases, audits.
Proactively hunts for bugs by analyzing codebase risk (complexity, coverage, structure), then spawns investigators that write reproducing tests to validate suspected bugs. Advisory only — produces findings and tickets, no fixes.