Code-Quality plugins

Set up, run and fix MegaLinter on any repository: 100+ linters for 69+ languages, 23+ formats and 21+ tooling formats, from CI or locally.

25 skills

Auto-invoked skills and slash commands for coding standards, style guides, and best practices across 30+ languages. References resources from Airbnb, Google, Uber, OWASP, and more.

2 skills

Analyze recently-changed code for Change Risk Anti-Patterns. Multi-language (TS/JS, Python, Java, Kotlin, Go, Ruby, C#, Rust, PHP) with auto-discovered coverage toolchain. Part of DAE's Light Verify tier (Checkpoint 7).

1 skill

Architecture analysis, code quality, and development workflow skills by Ovid

15 skills · 1 agent

CodeDNA v0.9 protocol enforcement — adds /codedna:init, /codedna:check, /codedna:manifest, /codedna:impact skills + automatic annotation validation on every file write

4 commands · 1 agent · hooks

Perform structured security audits using OWASP Top 10, ASVS, cheat sheets, framework checks, and DevSecOps controls.

1 skill

Run an extremely strict maintainability and structural code quality review — flags abstraction issues, spaghetti growth, and boundary leaks

1 skill

Review the diff since a fixed point along two axes — Conventions (does the code follow this repo's coding standards and Tidy First practices?) and Intent (does the change do what it claims to do?). Runs both reviews in parallel sub-agents and reports them side by side.

1 skill

Web accessibility (a11y) skills for Claude Code: audit a site for WCAG 2.2 conformance, scan a page with the rule engine, run hands-on keyboard and screen-reader checks, fix violations, and catch regressions in CI. Live-DOM audits auto-launch Chrome; no manual setup.

5 skills · 1 MCP server

Two adversarial review gates. plan-readiness-review asks whether a PRD, spec or RFC is implementable without inventing anything. production-readiness-review asks whether the code is actually built, wired, tested and safe to deploy, backed by a deterministic repo scanner.

2 skills

CodeScene Code Health analysis — review, refactor, and safeguard code quality with AI-friendly tools.

9 skills · 1 MCP server

Project-wide PR readiness, targeted test authoring, security review, architecture tracing, and code evolution analysis for Claude Code.

19 skills · 6 agents · 6 MCP servers

Codebase vital signs — hotspot detection, ROI-ranked diagnosis, co-change coupling, knowledge risk, trend tracking, and AI provenance

1 skill · hooks

Apply SOLID principles and design patterns to backend code without over-engineering, with a configurable rigor dial.

Comprehensive code review skill with 53 specialized agents for architecture, code quality, error handling, types, comments, tests, accessibility, localization, concurrency, performance, simplification, security, and 30 platform-specific reviews with automatic detection and confidence scoring.

1 skill

Peer validation system using OpenAI Codex CLI. Two AI perspectives catch more issues than one.

1 skill · 1 command · 1 agent · hooks

Two Claude Code engineering skills bundled as one plugin: review-loop (cross-LLM iterative code review with Codex or Gemini as peer) and harness (cybernetics-based Planner→Generator→Evaluator→Retro orchestration for complex tasks).

2 skills · 5 agents

AI code review skills. A single-pass GitLab merge request reviewer that posts inline comments and a summary (in CI) or displays them locally, a risk-tiered review panel with one reviewer subagent per lens and skeptic subagents that verify each finding, and a security-only diff review with a false-positive filter per finding.

3 skills

CodeRabbit review triage and project-conformant unit test generation

2 skills

Protocols for highly efficient and directed remediation of known issues — refit onboarding, the swab/scour/buff/sail loop, and barnacle friction reporting as a skill and slash commands.

1 skill · 8 commands

CodeEraser passive guard + erase skill: PreToolUse duplicate-write interception (plus the tombstone and flow legs), PostToolUse settle, Stop audit, SessionStart health, and guided safe deletion of findings — backed by a per-project winnowing clone index daemon. The starter resolves ce and the ce-core judgment core in three steps: a verified local copy, a SHA256-pinned download from GitHub Releases (manifest.env pins), then PATH.

1 skill · 1 command · 1 MCP server · hooks

Keeps what the agent makes from reading as AI slop, in two skills. anti-slop-ui covers interfaces: no gradient-everything, rainbow palettes, pulsing badges for states that never change, fingernail-striped cards, emoji icons, default fonts, uppercase labels, scroll effects, screens with no hierarchy or no empty, loading, and error states, or landing-page hype on working screens. anti-slop-text covers prose: no invented details, inflated significance, promotional tone, weasel attributions, not-X-but-Y contrasts, manufactured rhythm, AI vocabulary, chat residue, restating conclusions, or PR text about what was left unchanged. Each checks its output against a catalog of known tells before it ships.

2 skills

Comment discipline for code the agent writes — every comment stays within a line or two, carries information the code does not, and describes the current state only, with no iteration labels, finding numbers, wave or task IDs, project phase names, or narration of how the code got here; regressions are pinned by tests instead.

1 skill

Opinionated Go writing discipline — idiomatic Go from Effective Go, the Google style guide, the Go Proverbs and the Gruntwork guide, with a stated house preference for natural-language, wrappable error messages, hand-written Fn-field mocks that fail loudly, comment and simplification discipline folded in, and a per-change checklist the agent runs before calling Go code done.

1 skill

Memory profiling MCP server with built-in rules and AI-actionable code suggestions for .NET applications

1 skill · 1 MCP server

Specialized agents and commands for exploring, analyzing, and reviewing CPython's C source code. Regex scanners for include-graph mapping, complexity, refcounts, error paths, GIL, and NULL safety, plus tree-sitter-based crash-class detectors (recursion-guard, destructor exception-clobber, uninitialized-dealloc), an informed-explore loop, and a known-issues regression command.

7 commands · 23 agents

Audit a website for UX issues, bugs, accessibility problems, and unexpected behavior. site-mapper crawls once via Playwright MCP to produce sitemap.json; ux-analyst, accessibility-auditor, performance-auditor, and bug-script-runner then run in parallel against the shared artifact. bug-script-runner generates a Playwright spec on the fly using real selectors and executes it via npx playwright test.

1 skill · 5 agents · 1 MCP server · hooks

Code-quality audit bundle — find unused code, find breaking REST API changes, and audit logging quality. All three skills are read-only and produce prioritised reports.

3 skills

Code review for a branch, PR, or path — structured output with severity labels and cross-file analysis

1 skill · 1 agent

Structured code explainer — layered explanations of files, functions, directories, or concepts

1 skill