Code-Quality plugins

Analyzes code for bugs, security issues, performance problems, and readability improvements

1 skill · 1 agent

Code quality improvement and refactoring patterns with SOLID principles and clean code practices

1 command · 1 agent

Fix PHPStan, Larastan and Psalm errors properly and raise a project's analysis level, without ignores, baseline growth or type lies.

2 skills

Réduit, synthétise, supprime ou humanise les commentaires générés par IA — sans jamais toucher au code

1 skill · 1 command

sonarqube-rules (SonarQube / SonarCloud setup, quality gates, CI) and sonar-rules (Sonar rule catalogue and sweep for every touched code file) skills

2 skills

Reviews pull requests for code readability against your project's style guides. Uses parallel review agents, confidence scoring, and false positive filtering.

1 skill

Documentation-only pass that fights comment-slop: drops, trims, moves, and de-duplicates comments and docstrings, leaving only the ones that earn their place. Never changes code.

1 skill

Applies Clean Architecture principles (SOLID, component cohesion/coupling, the Dependency Rule, Humble Object) when planning or reviewing software structure.

1 skill

Adds a /review skill for quick code reviews

1 skill

Suite health for QA architects: trust verdict, what the regression covers (coverages, options, jurisdictions, flows, suites), branch review, trend, portfolio, weekly, release plans, client coverage statement — HTML, Excel, PR comment, JSON

1 skill

Benchmark your modules against the best open-source implementations on GitHub

1 skill

Check and fix lint issues for changed Python files by commit, range, or working tree

1 skill

Validate JAX/Pallas source, Jaxpr, StableHLO and Mosaic TPU IR with five standalone scripts.

1 skill

Find and fix bare `except:` clauses and overly broad `except Exception` catches across a Python codebase. Narrows to specific exception types (ImportError, ConnectionError, ValueError, pydantic.ValidationError, etc.) and adds logging where exceptions were silently swallowed. Leaves test files alone.

1 skill

Read the diff of a bug-fix (PR/MR, branch, or working tree), infer the root-cause anti-pattern it removed, then sweep the whole codebase for sibling occurrences of the same defect. Read-only: it reports and ranks, it does not edit.

1 skill

Runs ruff, mypy, and bandit on Python files to find and auto-fix lint violations, type errors, and security issues

1 skill

Optional Legion code-intelligence diagnostics. Runs repo-native TypeScript and Pyright checks, filters changed-file diagnostics, emits legion.code-intel.v1 artifacts, and can append legion.span.v1 telemetry for benchmarkable pre-PR gates without making LSP servers a core dependency.

1 skill

JavaScript/TypeScript linter

1 skill

JSON syntax validator

1 skill

Markdown style and syntax linter

1 skill

Tool · Cost-free, Ollama-first code review — multi-angle finders, adversarial verify, structured verdict.

Cost-free, Ollama-first code-review agent for Claude Code — reviews a git diff in-repo via a multi-angle finder/verify harness and returns a structured, machine-readable report.

Code review, integrated review orchestration, test-engineering, review publishing, and specialist subagents that catch correctness, security, maintainability, and test-quality issues with actionable guidance.