Creates, analyzes, updates, and improves Claude Code agent skills including YAML frontmatter, allowed-tools field, progressive disclosure, and skill authoring workflows. Use when user asks how skills work, what agent skills are, explaining skill concepts, understanding SKILL.md structure, describing .md files organization, skill authoring process, asked to create a new skill, evaluate existing skills for improvements, optimize skills for AI/Claude effectiveness, suggest converting current logic into a skill, update outdated skill information, or when user mentions skill validation, best practices, supporting files, skill security, API integration, or technical architecture.
Structured code review criteria for pre-implementation plan review (Critic) and post-implementation security/quality review. Covers security, performance, maintainability, and correctness with severity ratings.
Use for Conestoga game development, validation/fallback handling, UI headless toggle, and test workflow in this repo. Covers make/uv commands, Gemini fallback patterns, and Pygame headless settings.
Implement monitoring, logging, and observability for Clerk authentication. Use when setting up monitoring, debugging auth issues in production, or implementing audit logging. Trigger with phrases like "clerk monitoring", "clerk logging", "clerk observability", "clerk metrics", "clerk audit log".
Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation. Use when user asks to "post to X", "tweet", "publish to Twitter", or "share on X".
Systematic validation methodology for ResearchPacks and Implementation Plans. Provides scoring rubrics and quality gates to ensure outputs meet standards before proceeding to next phase. Prevents garbage-in-garbage-out scenarios.
This skill should be used when the user asks to "pentest WordPress sites", "scan WordPress for vulnerabilities", "enumerate WordPress users, themes, or plugins", "exploit WordPress vulnerabilities", or "use WPScan". It provides comprehensive WordPress security assessment methodologies.
Integrate Databricks Genie rooms as tools in agent workflows. Use when integrating Genie spaces with AI agents, querying Genie rooms programmatically via SDK or MCP, managing Genie conversations and polling, handling Genie API responses and errors, or building tool-calling agents that use Genie as a data source. Covers SDK patterns, MCP tool integration, conversation management, error handling, and performance optimization for Genie-based agent tools.
Retrieval-Augmented Generation for project knowledge management using ChromaDB
<figure><img src="../../.gitbook/assets/image (6) (1) (1) (1).png" alt=""><figcaption></figcaption></figure>
The chat will provide safety guides, equipment suggestions, reviews, and techniques, with context-driven summary and multimedia tools to enhance understanding.
Use when the user says /bye, "wrap up", "end session", or similar. Reconstructs full session history including compacted context, creates a sessionlog (if project has a sessionlog directory), commits changes, and summarizes next steps.
Use when writing or reviewing any TypeScript code. Covers discriminated unions, branded types, Zod at boundaries, const arrays over enums, and safe access patterns.
**Activation**: `/rollback` or `/rollback <phase>`
Query real-time parking availability in Taipei City. Shows available parking spaces, capacity, status (green/available, orange/moderate, red/full), address, phone, and payment info. Supports underground/multi-level parking and street parking for cars, motorcycles, and buses. Use when user asks about parking availability, finding parking near a location, or checking parking occupancy in Taipei.
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration
Plugin Marketplace構造を対話的に生成し、marketplace.json、plugin.json、ディレクトリ構造を自動作成するスキル。Use when users mention "plugin marketplace", "marketplace作成", "プラグインカタログ", "複数のプラグインを管理", "チーム向けプラグイン配布", or need to create marketplace.json/plugin.json files. Also use when users want to organize multiple Claude Code plugins for distribution.
Orchestrates on-demand generation of crate-specific skills based on project dependencies.
Enhanced docs unified with AI-powered features. Enhanced with Context7 MCP for up-to-date documentation.
Generate a project-specific AGENTS.md from a user goal, then confirm before overwriting.