Code-Quality plugins

Teaches Claude to write, review, and audit tests worth having — behavior-focused design, disciplined test doubles, browser and component testing, a plan-gated pipeline that turns a ticket or PR into tests of the described behavior, a check on whether pushed code still matches the description that specified it, and a repo-scale map of where test protection is weakest

7 skills · 4 commands · 5 agents

Interactive, human-in-the-loop QA walkthroughs of finished functionality — drives a browser, an API, and a CLI against a ticket's acceptance criteria and its merged PR, with an adversarial critic pass on both the behavior spec and the step plan, drafter/critic revision rounds, and a report with embedded screenshots. Not automated test-code authoring; that's what the testing plugin is for

5 skills · 1 command · 7 agents · 1 MCP server · hooks

Red-flag detection, design-it-twice interface design and strategic change planning.

7 skills · 3 agents · 1 MCP server · hooks

4인 병렬 코드 리뷰 (Design/Logic/Performance/Test) 에이전트 + 통합 리뷰 스킬

2 skills · 5 agents

Post-generation engineering quality. Codesavers removes avoidable complexity from changed code; Specsavers authors and reviews technical software specifications for precision, information density, and decision completeness.

2 skills · 3 agents

Software engineering knowledge graph — design patterns, laws, code smells, and refactorings with graph traversal and AI-powered code analysis.

5 skills

OxLint, Biome, and Prettier configuration, linting skills, and pre-commit hooks for consistent code quality.

2 skills · 2 commands

Self-documenting naming and minimal, high-signal comments for AI coding agents.

3 skills

Detect false-positive tests (tests that pass even when the code breaks) across Python, TypeScript, JavaScript, and Robot Framework. HIGH/LOW confidence findings with evidence and fix hints.

2 skills

Audit an app project against Apple App Store Review Guidelines and Google Play Developer Program Policy.

1 skill · 1 agent

Drive CodeAnt AI from inside Claude Code via the CodeAnt MCP server. Read-only by default; write tools (trigger scan, resolve PR thread, write API requests) gated behind CODEANT_READ_ONLY=0.

1 skill · 1 MCP server

Finds shallow modules in the areas the git history changes most, publishes a ranked report with before/after diagrams, lets you pick one candidate and hands it to brainstorming. Includes codebase-design, the shared deep-module vocabulary for designing and deepening interfaces.

2 skills

Teaches Claude to spot code smells (classic, architectural, and test smells) and apply disciplined, behavior-preserving refactoring

1 skill

Comprehensive branch review before push or PR. Diffs against the base branch and reviews plan adherence, code quality, commit hygiene, and regression testing. Produces a PASS/FAIL verdict with a prioritized remediation plan on failure.

1 skill

Transitive impact analysis for complex refactorings. Maps all affected files, classifies breaking vs cosmetic changes, identifies risks like dynamic references and cross-boundary impacts, and produces a safe execution order with checkpoint boundaries.

1 skill

Set up scrut snapshot-based CLI integration testing for a CLI project.

1 skill

Best practices for handling user-provided secrets in CLI tools: secure input methods, credential storage, secret masking, and language-specific libraries.

1 skill

Detect project linters and formatters, run them with auto-fix, resolve remaining issues, then commit and push the fixes.

1 skill

Audit a codebase without reading it line by line. Call graph plus free checkers point at the risky functions, sub-agents read only those, every finding is verified, then it stops and asks you what to fix.

1 skill

Bundles the four Qualimetry skills (coding-standards, review-check, analysis-issues, dependency-check), registers the Qualimetry MCP server, adds /compliance-* slash commands, a compliance-reviewer subagent, and a PostToolUse hook that surfaces review findings the moment a reviewed file is opened.

5 skills · 6 commands · 1 agent

The review and git workflow commands: /commitmsg, /code-review, /code-refinement, /dependency-review, /review-pr, /git-history-cleanup and /efficient-orchestration.

7 skills

Lint, security-scan, and sign SKILL.md / .aif Agent Skill files. Catches missing sections, empty steps, prompt-injection patterns, broken references before deploy. Ed25519 signing for skill integrity.

6 commands

Dead code detection for JS/TS repos using Knip — finds unused files, exports, types, and dependencies. Produces HTML/Markdown/JSON reports with run history and delta tracking; optional --fix opens a draft PR that safely removes the dead code via an isolated git worktree, never touching your working tree.

1 command · 4 agents · hooks

Claude + Gemini (default) or + Codex/GPT (opt-in) review your diff in parallel, then merge, dedup, and refute findings.

1 skill · 2 commands · 2 agents

Functional programming enforcement: rules, violation scanning, and skills to validate, repair, learn, assimilate, and wire fp-enforcer into a project.

5 skills

Analyzes your code against SOLID, DRY, KISS, YAGNI, Law of Demeter, and other design principles — with actionable refactoring suggestions and an encouraging tone

1 skill

Strict no-emoji Agent Skill for Claude Code.

1 skill

Teaches the agent to write readable, understandable, maintainable code: intent-revealing naming, small single-purpose functions, guard clauses over nesting, minimal comments, pragmatic DRY, SOLID design, code smells, and clean tests.

1 skill

RTK-inspired output contract for building token-efficient CLI, skill, hook, and script developer tools.

1 skill

Code review for reuse, simplification, efficiency, and altitude

1 skill