ThinkInAIXYZ/deepchat

Add Provider integrates new DeepChat LLM providers by generating explicit source changes across provider defaults, registry, transports, and tests. Use when a developer asks Codex to add a provider, provider profile, upstream provider config, model catalog mapping, or a special provider adapter.

Algorithmic Art creates generative art using p5.js with seeded randomness and interactive parameter exploration. Use it when users request art made with code, flow fields, or particle systems.

CUA Driver drives native macOS applications by snapshotting their accessibility tree and performing clicks, typing, and scrolling by element index. Use it for GUI tasks in macOS apps, like opening a file in TextEdit or clicking Save in Numbers.

Code Review analyzes code for quality, security, and best practices, providing structured feedback with issues categorized by severity and suggestions with code examples. Use it when reviewing code, requesting a security audit, or wanting implementation feedback.

Computer Use drives native desktop applications through DeepChat's built-in computer use tools for GUI tasks like opening apps, clicking, typing, and verifying screen state. Use it when a user asks to operate, inspect, automate, or perform a task in a real desktop application.

DeepChat CLI controls the running DeepChat desktop application through its bundled command-line interface for model inference, image/video/speech generation, transcription, OCR, artifact inspection, public configuration, Skills, and MCP operations.

DeepChat Data Import helps developers build third-party tools that import, inspect, migrate, or analyze DeepChat local data such as agent.db, encrypted SQLite, and safeStorage passwords. Use it when working with provider configs, sessions, messages, or legacy chat data.

DeepChat Release prepares and publishes DeepChat releases in this repository, handling version bumps, bilingual changelogs, release branches, tags, and fast-forward publishing. Use it when Codex needs to advance a release through this repository's documented workflow.

DeepChat SDD guides spec-driven development for substantial DeepChat code, configuration, test, docs, build, feature, issue, refactor, or architecture changes, creating durable RFC specs and ordered implementation plans. Use it before large changes and skip trivial localized edits.

DeepChat SDD Cleanup scans docs/features, docs/issues, and docs/architecture to remove completed issue docs, stale plans, and obsolete specs when a developer explicitly asks for cleanup or tidying. It uses multi-agent review and validates references before deleting files.

DeepChat Settings changes DeepChat application preferences such as theme, language, and sound via dedicated tools. Use it when a user explicitly asks to modify DeepChat's own settings rather than OS or editor settings.

Doc Co-Authoring guides users through a structured workflow for co-authoring documentation, proposals, technical specs, and decision docs. It helps transfer context, refine content through iteration, and verify the document works for readers before others see it.

Feishu Tools provides MCP tools for reading, creating, updating, and organizing Feishu/Lark documents, spreadsheets, and knowledge content within DeepChat.

Frontend Design creates distinctive, production-grade frontend interfaces and UI components that avoid generic AI aesthetics. Use it when building websites, landing pages, dashboards, React components, or any web UI where high design quality matters.

Git Commit formats git commit messages according to the Conventional Commits standard. Use it after staging changes to produce a clear, structured commit message for a repository.

Infographic Syntax Creator generates AntV Infographic syntax outputs from user content. It selects templates, structures data, and applies themes to produce a single `infographic <template>` code block for sequence, list, compare, hierarchy, or chart layouts.

MCP Builder guides the creation of high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use it when building MCP servers to integrate external APIs, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Memory Management guides an agent to recall prior work, persist durable conclusions, and route reusable procedures or recurring needs into Skills, Scheduled Tasks, or Tape. Use it when a task may produce durable learning or when the user asks to recall, remember, or continue earlier work.

PDF Processing extracts text and tables, creates new PDFs, merges and splits documents, and fills forms. Use it when Claude needs to programmatically process, generate, or analyze PDF documents.

PowerPoint creates, edits, and analyzes .pptx presentation files, including reading text, layouts, comments, and speaker notes, and generating new slides from HTML with design guidance.

Skill Creator guides users through creating or updating skills that extend Claude's capabilities with specialized knowledge, workflows, and tool integrations. Use it when building a new skill or refining an existing one.

Web Artifacts Builder initializes, develops, and bundles multi-component React + Tailwind CSS artifacts for claude.ai. Use it for complex frontend artifacts requiring state management, routing, or shadcn/ui components.

Word Documents creates, edits, and analyzes .docx files, supporting tracked changes, comments, formatting preservation, and text extraction. Use it when you need to generate new Word documents, modify existing ones, or work with tracked changes and comments.

XLSX creates, edits, and analyzes Excel spreadsheets with formulas, formatting, data analysis, and visualization. Use it for financial models, data manipulation, and preserving existing templates while ensuring zero formula errors.