Add an LLM provider to DeepChat by choosing a suitable API connection method, updating authentication and model configuration, and making focused source changes with tests for the affected behavior.
Review Git changes and draft commit messages using Conventional Commits, a format that labels the type and scope of a change. Produce concise subjects, explanatory bodies, and issue or breaking change references when needed.
Build MCP servers, which let AI agents use external APIs and services through tools. The skill guides tool design, authentication, input validation, implementation, testing, and evaluation using TypeScript or Python.
Create, edit, and analyze spreadsheets with formulas, formatting, and visualizations. Preserve existing workbook conventions, keep calculations responsive to input changes, and use formula recalculation and error checks to verify the resulting files.
Build working web pages, application interfaces, and components with a clear visual direction. Shape typography, color, layout, and animation around the intended audience and purpose, producing coordinated design and code in HTML, CSS, JavaScript, React, or Vue.
Plan substantial DeepChat changes with a written design proposal and a clear implementation path. Record decisions, track progress, review the completed change, and select focused validation for features, complex bugs, or architecture updates.
Create original generative art with p5.js, using code to produce patterns and motion. Receive a written artistic concept and an interactive HTML viewer with adjustable parameters, reproducible random variations, seed navigation, and PNG downloads.
Review code for readability, maintainability, security, and performance. Receive an overview, issues grouped by severity, concrete improvements with code examples, and positive feedback on parts of the implementation that work well.
Change DeepChat preferences through conversation, including theme, interface language, font size, sound effects, and whether copied text includes COT details. Dedicated tools apply supported changes, while other requests open the relevant settings section with guidance.
Create, edit, and analyze Word documents while preserving formatting. Work with tracked changes and comments, extract document text, and convert pages to images for visual review, with workflows tailored to new documents and existing files.
Extract text, tables, and images from PDFs, create documents, combine or split files, and fill forms. It also covers OCR, which reads text from scanned pages, plus watermarks, page rotation, and password protection.
Create, edit, and analyze PowerPoint presentations, including slide content, layouts, comments, and speaker notes. Reuse existing templates or build slides from HTML, then inspect thumbnail previews to identify layout and readability issues.
Prepare and publish DeepChat releases through its project-specific workflow. Update versions and bilingual changelogs, run release checks, manage release branches and tags, and resume unfinished releases before publishing after release PR approval.
Retrieve prior decisions and working context from Nowledge Mem in DeepChat, and save useful lessons for future work. It also supports requested conversation exports and connection troubleshooting while keeping operations within the selected server and Space.
Coauthor proposals, specifications, and other structured documents through context gathering, section-by-section drafting, and revision. Test the finished draft with a fresh Claude conversation to identify unclear assumptions, missing information, and contradictions.
Use DeepChat's bundled command-line interface to compare models, generate media, transcribe audio, and extract text from images. Also inspect runtime status, artifact metadata, public settings, installed Skills, and MCP connections to external tools.
Turn content into AntV Infographic syntax, a text format for describing infographics. The skill organizes titles, items, relationships, and metrics, then selects a suitable template for sequences, lists, comparisons, hierarchies, or charts.
Recall earlier work and organize lasting preferences, project facts, outcomes, and lessons. The skill distinguishes concise memory from original records, reusable procedures that belong in skills, and recurring requests that need scheduled tasks.
Create or update Claude skills that capture specialized knowledge and repeatable workflows. Guides the organization of instructions, scripts, references, and templates, then covers initialization, validation, and packaging into a distributable skill file.
Operate desktop applications through DeepChat's built-in Computer Use tools. Inspect windows, click controls, enter text, use menus, and arrange windows, checking the visible result after each action.
Work with Feishu/Lark documents and spreadsheets through DeepChat's plugin tools. Search, summarize, create, or update content, and inspect or edit structured data using the operations available in the active plugin configuration.
Save explicitly requested facts or approved summaries and recall them across DeepChat conversations through Memcode. The skill checks storage status and supports answers with citations, while keeping saving and recall under the user's control.
Build third-party tools to inspect, extract, migrate, or analyze DeepChat's local settings and conversations. Work through data locations, database encryption, and table relationships while favoring read-only copies and redacted output.
Clean up DeepChat's specification-driven development documents after implementation and validation. Review feature, issue, and architecture files, remove completed or obsolete material when evidence supports deletion, and preserve maintained specifications while checking references.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)