Quality plugins

Static lint for Claude Code plugins and skills, with experimental LLM scoring for skills

1 skill · 3 commands · 2 agents

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

2 commands · 3 agents

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

2 commands · 2 agents

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

Comprehensive code review with best practices

1 command

Automatically write and fix unit tests

1 agent

Advanced debugging assistant

1 agent

Independent adversarial honesty reviewer: scrutinizes a DRAFT output's claims-vs-evidence (no fabrication / overreach / invented IDs) before a human approves. Snaps onto agentic-sop-kit run dirs (FULL, uses the trace) or reviews any plain document (DEGRADED). Deterministic checks + a capped advisory LLM pass; the report is a DRAFT — the human owns the verdict.

1 skill · hooks

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

2 commands · 3 agents

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

2 commands · 2 agents

AI-powered architectural review and code quality analysis

1 command · 1 agent

Quality assurance: Playwright end-to-end tests proven stable by repeated headless runs, and WCAG 2.1 AA accessibility audits that report the success criterion behind every finding.

2 skills · 1 agent

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

2 commands · 3 agents

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

2 commands · 2 agents

AI-powered architectural review and code quality analysis

1 command · 1 agent

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

2 commands · 3 agents

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

2 commands · 2 agents

AI-powered architectural review and code quality analysis

1 command · 1 agent

Code review, refactoring, linting, dependency auditing, dead code detection, test quality, complexity metrics, and static analysis

19 skills

Skill evaluation and benchmarking - test skill effectiveness with behavioral eval cases, grade results, and track quality improvements

7 skills · 3 agents · hooks

Structured codebase health attributes with severity-based agent routing and dashboard

3 skills

Code quality pipeline — SOLID refactoring, TDD workflow, GoF design patterns, performance optimization, and 6 specialist review agents

15 skills · 6 agents · hooks

Automatic frontend quality router. Describe the outcome — implement this mock, check this page, audit its design and colour, check a Flutter or Android app's accessibility, turn these criteria into tests — and it picks one of 13 bundled workflows and runs its deterministic gates to green. No API key: the gates are Playwright + pixel math, and the agent's own vision is the only VLM.

14 skills

Non-régression et validation de contrat — évalue chaque skill contre skill_output.schema.json.

Code-review toolkit: nine agents, read-only over the reviewed code, plus orchestration skills for the quality gate and fan-out, a pull-request change digest with an interactive view (/review:explain-change), a merge-risk rating with a demote-only flag (/review:merge-risk), a fan-out sweep workflow (/review:fanout-sweep), and CI lane commands (/review:code-review, /review:security-review) for org reusable workflows.

8 skills · 9 agents · hooks

Correctors that re-anchor a rule, audit work in flight, and fix drift: do-your-research, follow-our-standards, point-dont-copy, reason-dont-recite, tighten-your-output, recheck-against-upstream, pick-for-the-problem, mind-your-maxims, script-the-deterministic-work, use-your-skills, reuse-or-replace, scrutinize-dont-coast. sweep-all runs them as one batch. wait-what re-pitches a message that did not land. hold-my-hand shows work one phase at a time. be-ambitious raises one request's ambition.

17 skills

Read-only code measures for a change, with cited references and no verdict: lines per file (audit size), cyclomatic, cognitive, and Halstead complexity (audit complexity), duplication (audit-duplication), per-function coverage and CRAP from existing lcov, Cobertura, coverage.py, or Go artifacts (audit-coverage), TypeScript and Python type debt (audit type-debt), metric literacy (principles), and setup. Uses only collectors already installed; never installs or runs tests.

6 skills

Writing quality and change-safety toolkit: cut AI tells (unslop), remove code slop (deslop), and prove blast radius before shipping.

3 skills

Audita Agent Skills: spec, autocontenção, claims e tamanho. Porta de entrada da família: fixa a ordem das fases, é somente leitura por padrão (reparo só com autorização) e entrega relatório com comando e rc. Triggers — auditar skill, auditoria completa de skills, skill no padrão, validar SKILL.md, skills-ref, skill pronta para publicar.

4 skills

Pre-PR review with severity grading and tiered model routing. Detects TOCTOU races, accessibility gaps, hardcoded secrets, silent-blinding sensors (swallowed errors, negative verdicts, gates aimed at the wrong file), docs drift, and dead code via a whole-repo sweep. Report carries an Overall Grade table + Recommended Actions. Stack-agnostic, TypeScript/React defaults. Triggers — code review, pre-PR, secrets scan, accessibility audit, dead code, silent failure, code health.

2 skills