claude-code-plugins-marketplace

Run all code review agents in parallel (bugs, coverage, maintainability, simplicity, type-safety if typed, CLAUDE.md adherence, docs). Respects CLAUDE.md reviewer configuration.

Audit code for logical bugs, race conditions, edge cases, and error handling issues.

Verify code changes comply with CLAUDE.md instructions and project standards.

Verify test coverage for code changes. Analyzes diff against main and reports coverage gaps.

Audit documentation accuracy against code changes. Reports discrepancies without modifying files.

Audit code for DRY violations, dead code, complexity, and consistency issues.

Audit code for over-engineering, premature optimization, and cognitive complexity.

Audit code for testability design patterns. Identifies business logic entangled with IO and suggests functional core / imperative shell separation.

Audit TypeScript code for type safety issues—any/unknown abuse, invalid states, missing narrowing.

Research external topics via web search with structured hypothesis tracking and source evaluation.

Audit UI/UX changes in a focus area against design guidelines for accessibility, consistency, and usability issues.

Captures writing style/voice into AUTHOR_VOICE.md so AI can write like the user. Use when asked to match tone, write like me, replicate voice, or capture writing style for content generation.

Create a BRAND_GUIDELINES.md that defines how to communicate with your customer. Requires CUSTOMER.md to exist first. Covers voice, tone, language rules, messaging framework, and copy patterns.

Create a DESIGN_GUIDELINES.md that defines how to design UI/UX for your customer. Requires CUSTOMER.md to exist first. Covers aesthetic direction, design tokens, typography, color, motion, components, and layout patterns. Bakes in frontend-design skill principles to avoid generic AI aesthetics.

Generate text in your voice using your AUTHOR_VOICE.md document. Provide a topic or prompt as argument.

Review and analyze LLM prompts using the 10-Layer Architecture. Provides detailed assessment without modifying files.

Single-model consultation using consultant agent. Defaults to gpt-5.2-pro.

Multi-model ensemble consultation. Runs 3 models in parallel for diverse perspectives.

Deep bug investigation using consultant agent. Identifies root causes and fix suggestions.

Production-level PR review using consultant agent. 10-category framework focused on correctness.

Autonomous execution from definition file. Works toward acceptance criteria, auto-verifies, prevents premature stopping. Use when you have a definition file from /define and want hands-off execution.

Internal completion marker. Called by /verify when all criteria pass. Outputs summary and allows stop.

Internal escalation handler. Called by /do when genuinely stuck after verification. Requires structured evidence of attempts.

Autonomous implementation from spec file. Works toward acceptance criteria, auto-verifies, prevents premature stopping. Use when you have a spec file from /spec and want hands-off implementation.

Internal verification runner. Executes all verification methods from definition against codebase. Called by /do, not directly by users.

Find and remove AI-generated slop (useless comments, verbose patterns, unnecessary abstractions).

Update main/master from origin, rebase current branch on it, resolve conflicts, and push.

Create or update CLAUDE.md with best practices - brevity, universal applicability, progressive disclosure

Implements scroll-driven storytelling experiences with pinned sections, progressive reveals, and scroll-linked animations. Use when asked to build scrollytelling, scroll-driven animations, parallax effects, narrative scroll experiences, or story-driven landing pages.