Quality plugins

Comprehensive code review with best practices

1 command

Automatically write and fix unit tests

1 agent

Advanced debugging assistant

1 agent

Automated code review for pull requests using multiple specialized agents with confidence-based scoring

1 command

Multi-agent code review skill simulating JaziTheDev's review style — PR discipline, bugs and smells, project-rules compliance, historical context, code documentation, and tactical/strategic DDD. Posts findings as inline GitHub review comments. Invoked as /code-review:code-review.

1 skill

Behavioral guidelines that reduce common LLM coding mistakes — surface assumptions, keep changes simple and surgical, and define verifiable success criteria. Derived from Andrej Karpathy's observations on LLM coding pitfalls, packaged from the multica-ai skills collection.

1 skill

Audit a skill or plugin folder for supply-chain risks (LICENSE, allowed-tools, bash calls).

1 skill

Tell Application Services (CQRS handlers), Application Preconditions and Domain Services apart — classify an existing class or decide where new logic belongs, with GLASS, FOE and book-grounded heuristics, in CQRS + hexagonal PHP codebases

1 skill

Runs incremental Stryker.NET mutation testing only on changed C# behavior with verified existing unit tests, using temporary tooling and configuration.

1 skill

Strip the sycophancy. Makes Claude honestly audit its own claimed-complete work against 17 named under-delivery patterns instead of polishing a summary over half-finished tasks.

1 skill

Third-party (evolv Consulting, MIT). Executable frontend ship gate: 27 source checks and 9 rendered checks, with the taste-precedence overlay.

1 skill

Lint Markdown with one pinned markdownlint-cli2 while you write, before you commit and before you merge. Mirrored from the copy Equal Experts publishes in ee-skills, so a repository outside it can deploy DOC-001.

1 skill

Lint YAML with one pinned yamllint while you write, before you commit and before you merge, so a duplicate key fails rather than silently replacing a value. Mirrored from the copy Equal Experts publishes in ee-skills, so a repository outside it can deploy YML-001.

1 skill

Makes Claude prove its work before it says done: real checks, screenshots and a verdict computed from the evidence

1 skill

Deterministic guardrails: format and typecheck on every edit, block secrets and destructive commands, gate the turn on a green test suite.

Testing, security, and code quality experts - code review, penetration testing, QA automation

Testing, security, and code quality experts - code review, penetration testing, QA automation

Testing, security, and code quality experts - code review, penetration testing, QA automation

Testing, security, and code quality experts - code review, penetration testing, QA automation

Testing, security, and code quality experts - code review, penetration testing, QA automation

Output styles: kaomoji flair and ISO 24495 plain language.

Testing, security, and code quality experts - code review, penetration testing, QA automation. (VoltAgent, 25.3K★, MIT, fijado al commit auditado 82b7382 — mismas condiciones que voltagent-core-dev.)

AI-powered architectural review and code quality analysis

Multi-perspective code analysis covering architecture, security, and best practices

Performance analysis, test coverage review, and AI-powered code quality assessment

When a reviewer (Codex, agy, council) returns, reminds Claude that a finding without evidence does not count and must be reproduced before fixing

Nine skills that audit, critique, harden, distill, verify, humanize, and design-constrain backend code