Draft or update detailed implementation plans for authgear-server specs, design changes, and docs/plans files. Use when Codex needs to turn a spec or outdated plan into a concrete implementation plan with exact files, exact methods, runtime call flow, compatibility requirements, test coverage, and atomic commit steps.
Qianfan Deep Research Agent for complex research tasks. Combines information retrieval, multi-source analysis, content synthesis, and report generation. Use when user needs in-depth research, analysis reports, or comprehensive investigation on complex topics.
Baidu Yijian visual management skill for industrial scenarios. Provides visual recognition capabilities across 20+ industries including retail, energy, mining, ports, chemical, and steel. Use for industrial visual inspection and management.
DiDi ride-hailing service skill. Supports taxi booking, price estimation, route planning (driving/transit/walking/cycling), order management, driver location tracking, and scheduled rides. Use when user expresses any transportation need including ride-hailing, route queries, or commuting.
Mark the plan as completed and generate a summary report. Call when ALL steps are done. Returns execution summary with success/failure statistics.
Create scheduled task or reminder. IMPORTANT - must actually call this tool to create task. Just saying 'OK I will remind you' does NOT create the task. Task types - (1) reminder for simple messages, (2) task for AI operations.
Update the status of a plan step. MUST call after completing each step to track progress. Status values - pending, in_progress, completed, failed, skipped.
AI Video Notes skill for video content analysis and note generation. Extract key information from videos for learning, meetings, and content summarization. Use when user wants to analyze video content or generate notes from videos.
Generate professional Mermaid diagrams with multiple themes, SVG/ASCII output, batch rendering, and a built-in template library for common diagram patterns. Supports flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, C4 architecture, and Gantt charts.
PaddleOCR document parsing skill based on PaddleOCR-VL-1.5. Provides SOTA-level document understanding with ultra-high precision recognition and parsing. Use when user needs to parse, extract, or understand document content.
PaddleOCR text recognition skill using PP-OCRv5 lightweight model. Supports natural scene and complex document text detection and recognition. Use when user needs OCR text extraction from images.
Formats plain text or markdown files with frontmatter, titles, summaries, headings, bold, lists, and code blocks. Use when user asks to "format markdown", "beautify article", "add formatting", or improve article layout. Outputs to {filename}-formatted.md.
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
Summarize content from any source — URLs, local files, YouTube videos, and raw text. Use when the user asks to summarize a webpage, PDF, document, article, video, or any content. Supports multiple output formats (bullet points, executive summary, detailed notes) and configurable length. Can also extract raw content without summarization.
Analyze images using GPT-4 Vision for detailed description, OCR text extraction, object recognition, and visual Q&A. Use when the user needs to understand image content, extract text from screenshots, identify objects in photos, or ask questions about images via OpenAI GPT-4 Vision API.
Baidu FaMou algorithm skills for efficient algorithm self-evolution. Provides experiment management and visualization capabilities to help optimize complex algorithms. Use when user needs algorithm optimization or experiment management.
Suite of tools for creating elaborate, multi-component interactive HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
AI Picture Book generation skill. Transform short text descriptions into coherent picture book stories with visual compositions. Use when user wants to create illustrated stories or picture books from text.
Immediately trigger scheduled task without waiting for scheduled time. When you need to test task execution or run task ahead of schedule.
