claudemd-optimizer

Multi-agent code analysis orchestration using claudemem. Share claudemem output across parallel agents. Enables parallel investigation, consensus analysis, and role-based command mapping.

⚡ PRIMARY TOOL for semantic code search AND structural analysis. NEW: AST tree navigation with map, symbol, callers, callees, context commands. PageRank ranking. ANTI-PATTERNS: Reading files without mapping, Grep for 'how does X work', Modifying without caller analysis.

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.

Claude Code plugin enforcing operational guidelines, terse responses, sequential execution, and no destructive operations without confirmation.

Use this skill when delegating to sub-agents that require more flexibility than the Task tool provides - when launching multiple agents in parallel, managing persistent sessions across calls, or coordinating complex multi-agent workflows with custom orchestration patterns.

Archive completed projects by moving outputs to archive directory. Use when a project is complete and ready for archival.

Analyze and optimize prompts using 6-dimension quality assessment (Clarity, Efficiency, Structure, Completeness, Actionability, Specificity). Use when you need to improve a prompt before implementation.

Transform PRD documents into actionable task breakdowns with dependencies. Use after creating a PRD to generate implementation tasks.

Create comprehensive Product Requirements Documents through strategic questioning. Use when planning a new feature or project that needs clear requirements.

Iterate on existing PRDs or improved prompts to enhance quality. Use when you have a draft that needs further refinement.

Review code changes with criteria-driven analysis (Security, Architecture, Standards, Performance). Use when reviewing PRs or code changes.

Verify implementation against PRD requirements with systematic checking. Use after implementation to validate completeness.

Use ClawHub CLI to search, install, update, and publish agent skills from clawhub.ai with advanced caching and compression. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with optimized performance.

AI-powered betting advisory for gaming platforms. Provides intelligent bet recommendations, risk analysis, bankroll management, and strategy optimization for crash games, dice, and casino games. Use when building automated betting bots or need AI gambling strategy guidance.

Contribute to and reference Clawpedia, the collaborative knowledge base for AI agents

The classifieds marketplace for AI agents. Buy, sell, hire, automate.

Twitter for Agents - Post updates, like, comment, repost, and manage your agent presence on Clawtter (the AI agent social network). Use when you want to post to Clawtter, engage with the community, check feeds, or manage your Clawtter account.

This skill provides comprehensive checking of ABAP code against Clean ABAP principles, based on the Clean ABAP style guide which adapts Robert C. Martin's Clean Code for ABAP.

Verifies code follows Clean Architecture principles in Polibase. Activates when creating or modifying src/domain, src/application, src/infrastructure, or src/interfaces files. Checks dependency rules, entity independence, repository patterns, DTO usage, and type safety.

Clean Architecture patterns for Next.js 16 frontend applications. Enforces strict layer separation (Domain, Application, Infrastructure, Delivery) with the Dependency Rule, ensuring business logic independence from frameworks. Use when designing scalable architecture, implementing use cases, separating concerns, or migrating to maintainable patterns.

Enforces Clean Architecture dependency rules (Domain → Application → Infrastructure → API/Blazor). Blocks violations to maintain architectural integrity.

Assist developers in writing clean, maintainable code following software engineering best practices. Use when conducting code reviews, refactoring code, enforcing coding standards, seeking guidance on clean code principles, or integrating automated quality checks into development workflows.

**CLEAN CODE MASTERY**: '코드 작성', '함수 만들어', '구현해', '개발해', '리팩토링', '개선해', '설계해', '클린코드', '코드품질' 요청 시 자동 발동. *.ts/*.py/*.go/*.java 등 모든 코드 파일 작업 시 자동 적용. SOLID/DRY/KISS + OWASP 보안 패턴. 언어별 선택적 로드.

Remove unnecessary, redundant, or obvious code comments while preserving valuable explanations. Use when cleaning up comments, removing verbose documentation, simplifying inline comments, or preparing code for review.

Use when committing code - ensures atomic, descriptive commits that leave the codebase in a merge-ready state at every point

>

Organize files on my desktop into tidy folders (approval required for moves)

TypeScript type best practices - proper typing patterns, avoiding type complexity, meaningful type annotations

Systematic data quality remediation - detect duplicates/outliers/inconsistencies, design cleaning strategy, execute transformations, verify results (component skill for DataPeeker analysis sessions)

- When the user explicitly asks to "clean up unused files" or "delete dead code".

Safely remove intermediate files from completed research sessions while preserving important data

WSL2 stores all data in `ext4.vhdx` files that:

Project organization expert - analyzes folder state, detects redundancy, moves files to proper locations, consolidates duplicate content, appends to accumulator files, removes obsolete content, and generates detailed operation reports. Maintains project structure integrity.

Review and clean up code, removing unwanted patterns and improving test structure.

Combine CLEAR (Concise, Logical, Explicit, Adaptive, Reflective) and CoVe (Chain of Verification) to write and lint agent task files that will be executed by worker agents. Use when orchestration or planning agents are producing task plans, task prompts, or TASK.md style instructions that must be unambiguous, verifiable, and resistant to hallucination.

(Optional) Remove demo content for a clean context folder

William Strunk Jr.'s _The Elements of Style_ (1918) teaches you to write clearly and cut ruthlessly.

Clerk authentication patterns and integration with Convex. Use when implementing sign-in/sign-out, protected routes, user profile sync, or role-based access control.

Expert patterns for Clerk auth implementation, middleware, organizations, webhooks, and user sync Use when: adding authentication, clerk auth, user authentication, sign in, sign up.

Expert in Clerk authentication for React Native/Expo apps. Handles user authentication, session management, protected routes, and integration with backend services.

clerk-auth

Comprehensive guide for implementing and testing Clerk authentication, with special focus on Astro SSR integration and Playwright E2E testing.

Use Clerk auth in Hono apps via @hono/clerk-auth. Use when adding or changing Clerk authentication, protecting routes, or reading userId/orgId in Hono.

Implements authentication with Clerk including user management, protected routes, middleware, and React components. Use when adding authentication, managing users, protecting routes, or implementing sign-in/sign-up flows.

Automates Clerk JWT token generation, validation, and export for FastAPI integration tests. Use when an agent must refresh tokens, verify JWT templates, or unblock authentication workflows without breaking environment state.

>

Auto-activates when user mentions Clerk, authentication, user management, or auth flows. Expert in Clerk authentication including Next.js integration, user management, and session handling.

Use this skill when you need to invoke another Claude Code session via the cli-agent-runner.sh script to perform specialized, potentially long-running tasks in a simplified way. This wrapper handles session management, result extraction, and can be run in background with polling support.