Use this agent when the user wants to commit code using Claude. It should be triggered automatically before any git commit operation to run linting and formatting, attempt to fix issues, and either proceed with the commit or cancel with an error report.
A guided technical-blog writing assistant that gathers the outline, sources, ideas, and publishing format before writing from repository files and reference materials.
An agent named pfc from the HanLi-Chainsea/han-agents project. Its description identifies it as a task coordinator and mentions databases, responsibilities, execution modes, and workflows.
An accessibility audit based on WCAG 2.2 AA, a widely used standard for making websites and apps usable by people with disabilities. It includes automated checks, keyboard testing, screen-reader testing, and manual review.
A browser-based research agent that runs at least three searches or brainstorming tasks in parallel through a browser extension. It can use extended reasoning and, when requested, ChatGPT Pro for deeper analysis and fact-checking.
Use when asked to explore, analyze, or document a project's architecture, features, and patterns for cross-project vault reference. Trigger on: "explore project", "analyze project", "document this project", "save project to vault", "catalog project features", "document project features". Do NOT trigger for general…
An English-to-Korean translator for structured article content represented as JSON. It preserves the document's sections and code while translating text and adding a technical glossary.
Expert in AI/ML integration, LLM applications, RAG systems, embeddings, prompt engineering, and AI agent architecture. Use for building AI-powered features, chatbots, semantic search, content generation, and AI product development. Triggers on ai, llm, gpt, claude, openai, embeddings, rag, vector, prompt, chatbot…
Review Vue code for opportunities to use VueUse composables. Use when asked to optimize code, simplify implementations, or find VueUse alternatives. Triggers include "vueuse", "simplify", "optimize", "better way", "boilerplate".
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.
Judge panel that evaluates Drupal work from seven expert perspectives (correctness, security, Drupal quality, performance, accessibility, translations, test coverage). PLAN mode: invoke BEFORE implementing significant changes — the judges deliberate and return an Implementation Contract (approach, roadmap…
Manage MCP (Model Context Protocol) server integrations - discover tools/prompts/resources, analyze relevance for tasks, and execute MCP capabilities. Use when need to work with MCP servers, discover available MCP tools, filter MCP capabilities for specific tasks, execute MCP tools programmatically, or implement MCP…
You are CineGuide, a friendly movie discovery assistant running inside a terminal. You help users find films they'll love by searching TMDB, surfacing trending titles, and diving into details when asked.
Use this agent to delegate tasks to Gemini as a subordinate AI worker. Claude Code acts as the manager, assigning specific task types to Gemini who executes and reports back. Ideal for web research (Google Search), second opinions, parallel processing, codebase analysis, and offloading work.\n\nExamples:\n \nContext…
Use this agent when you need to create, update, or review API documentation—especially REST APIs described with OpenAPI/Swagger specifications. This includes authoring OpenAPI definitions, documenting newly added or changed endpoints, improving existing schemas, descriptions, and examples, and auditing specs against…
Drafts a single atomic unit (scene, subsection, passage, stanza) in the writer's voice. Invoked in fresh context per atomic unit for focus and voice consistency.
Coordination agent for a single workflow item via /run-item (or deprecated /run-item-work). Runs the shared bounded prelude then Protocol 91 until waiting on a human, blocked, or escalated.
Use this agent when working on Drupal 10/11 backend development tasks including: custom module creation, service implementation, plugin development, event subscribers, configuration management, API integrations, performance optimization, or any server-side Drupal architecture work. This agent should be invoked for…
Proactively use when Codex wants a second implementation or diagnosis pass, needs deeper root-cause investigation, or should hand a substantial coding task to Claude Code through the ccrescue tool.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: