wayne-skills

Configure common development commands and local tool environments with pywayne's toolsetup CLI. Use whenever the user mentions toolsetup, cross-platform shell shortcuts, proxy_on/proxy_off, persistent goto aliases, the Linux gpu helper, nvm/npm bootstrap, Linux Tailscale installation, or MongoDB/PyMongo setup on macOS or Linux—even if they only ask for the right command or a dry-run plan.

Fetch and install C++ tools/libraries from cpp_tools repository. Use when users need to download or clone third-party C++ libraries such as eigen, opencv, pcl, fmt. Use for building tools from source using CMake, installing tools with installation scripts, listing available tools, or managing cpp_tools repository URL. Triggered by requests to fetch, get, download, clone, or install C++ tools or libraries.

Sensor calibration toolkit with magnetometer calibration using close-form method. Use when calibrating IMU sensors (accelerometer, gyroscope, magnetometer) to compute soft-iron matrix and hard-iron offset for magnetometer correction. Requires sensor fusion with VQF for orientation estimation.

Digital signal processing toolkit for filtering, peak detection, detrending, and curve similarity. Use when working with sensor data, signal preprocessing, feature extraction, noise suppression, or time-series analysis. Includes Butterworth filter, One-Euro filter, signal detrending, DTW curve similarity, Welford standard deviation, and sliding window extrema detection.

SE(3) rigid body transformation library for 3D rotation and translation operations. Use when working with robot poses, camera transformations, SLAM systems, or any 3D rigid body motion tasks. Supports SE(3) matrix operations, Lie group/algebra mappings (log/Log, exp/Exp), representation conversions (quaternion, axis-angle, Euler angles), and batch processing of trajectories.

VIO (Visual Inertial Odometry) data processing utilities for SE(3) pose conversion and 3D visualization. Use when working with SE(3) matrices and need pose representation conversion (tx,ty,tz,qw,qx,qy,qz), 3D visualization of pose trajectories with orientation arrows, or Visual Inertial Odometry data transformation and analysis

Analyze and visualize Git commit time distribution. Use when users need to analyze Git repository commit patterns, generate commit statistics, visualize commit activity by time, hour, or weekday. Triggered by requests to analyze commits, show commit distribution, visualize Git activity, or generate commit time statistics.

Use this skill whenever the user asks to record, save, organize, update, or maintain project documentation, including plan documents, todo documents, temporary ideas, project risks, next actions, experiment notes, know-how, roadmap items, decision records, summaries, story-telling documentation polish, technical book chapters, thesis-style derivations, or common command registries. Also use it when the user asks to save a generated shell command, append to 常用命令, or create a reusable AI/human project documentation interface. Defaults to <project-root>/docs unless the user specifies another documentation path.

AprilTag corner detection for camera calibration and pose estimation. Use when working with pywayne.cv.apriltag_detector module to detect AprilTag fiducial markers in images, extract tag IDs and four corner coordinates, choose tag families such as tag16h5 or tag36h11, apply optional preprocessing, and rely on automatic apriltag_detection installation via gettool.

Feishu/Lark Bot API wrapper for full-featured Feishu bot interactions. Use when users need to send messages (text, image, audio, file, rich_text, card, share), especially Markdown delivery via send_markdown_message_to_chat with card_v2/post routing, table fallback, and auto chunking; build or update schema 2.0 cards; send in-place streaming reply cards with reply_streaming_card, update_streaming_card, recolor_streaming_card, stream_reply_card, or astream_reply_card; manage files (upload/download); query user/group info; reply to messages; forward/recall/update messages; edit previously sent text/rich_text/card messages via edit_text_message, edit_post_message, edit_card_message; add reactions; pin messages; manage chats (create, delete, update, members, admins); get message history; batch send; handle read receipts and urgent notifications.

Material-based AI weekly report system. Use when the user mentions 周报, week report, weekly report, 本周总结, 工作总结, 写周报, 生成周报, 帮我写周报, 本周工作, 上周周报, 查看周报, 周报系统, 记录工作, 纳入周报素材, 周报素材, plan, experiment, 方案文档, 复盘文档, or asks to summarize recent repo activity into weekly report materials. This skill captures work materials, syncs them to Git, and generates weekly reports from structured materials.

Comprehensive ALAPI skill covering the full bundled ALAPI OpenAPI catalog. Use when the user mentions ALAPI, alapi, ALAPI_TOKEN, openapi.json, or an ALAPI path like /api/..., or asks to find which ALAPI API matches a business need, choose between similar ALAPI endpoints, explain request fields, prepare or execute a request, or troubleshoot an ALAPI response. Covers inspirational content, articles, news and hotlists, AI chat/translation/NLP, OCR and document recognition, weather and calendar data, IP/phone/ID/domain/ICP/enterprise lookup and verification, finance/exchange/gold/oil/crypto market data, music/media/video/TTS, URL/QR tools, and related utility APIs.

Feishu/Lark message listener for real-time event processing via WebSocket. Use when users need to listen for incoming Feishu messages (text, image, file, audio, media, sticker, post, interactive) and events (recall, read, reaction, bot added/removed, member changes, chat updates) with automatic deduplication, async handling, resource auto-download, and convenient decorators. Provides high-level handlers (text_handler, image_handler, file_handler, audio_handler, media_handler, sticker_handler, mention_handler) with automatic download/cleanup and optional file回传, plus event handlers (recall_handler, message_read_handler, reaction_handler, bot_added/removed_handler, member_changed_handler, chat_updated/disbanded_handler), card action callback support, and listener-level streaming card helpers such as reply_streaming_card, update_streaming_card, recolor_streaming_card, stream_reply_card, and astream_reply_card.

Utility toolkit for pywayne.tools. Use when tasks need colored console output and tables (wayne_print, wayne_print_table), timing/profiling (@func_timer, @func_timer_batch), YAML config I/O (read_yaml_config, write_yaml_config), logging (wayne_logger), tracing (@trace_calls), retries (@retry), disk caching (@disk_cache), parallel execution (parallel_map), progress bars (@with_progress, progress_iter), file listing/line counting, FileWatcher callbacks, singleton/compose helpers, matplotlib helpers (@maximize_figure, binding_press_release), numpy/pandas display control, or TTS/speech helpers (say, leader_speech). Prefer these built-ins over adding new dependencies or using raw print/logging/config code.

Feishu/Lark Custom Bot API wrapper for sending messages via webhook. Use when users need to send text messages, images, rich text posts, interactive cards, or share chat content to Feishu/Lark channels. Supports image upload from files or OpenCV/numpy images, signature verification for security, and @mention functionality. Ideal for one-way notifications, alerts, scheduled tasks, and simple push scenarios without message listening or two-way interaction requirements.

一对一辅导老师技能，用于解答数学题，生成HTML讲解文档和带配音的Manim动画视频。 核心工作流：数学分析 → HTML可视化 → 分镜脚本 → TTS音频 → 验证更新 → 脚手架 → Manim代码 → 渲染验证 触发条件：学生粘贴数学题图片、需要教学视频、需要HTML讲解资料 【重要】生成的视频必须带 TTS 配音，这是强制要求，不可跳过

通用的知识教学视频制作技能，生成带配音的 Motion Canvas 动画视频。 核心工作流：内容分析 → 分镜脚本 → TTS音频 → 验证更新 → Motion Canvas代码 → 渲染验证 触发条件：需要制作任何主题的教学视频、科普讲解、技术原理演示

让 AI 助手从「等待任务」变成「主动预见」的架构设计。包含 WAL 协议、Working Buffer、自动定时任务等经过实战验证的模式。

Configure cross-platform terminal shortcut commands on a new machine, including proxy_on/proxy_off (env vars + git global proxy), goto (persistent path jump shortcuts), gpu (nvidia-smi helper), and optional Conda auto-activation. Use when setting up Windows PowerShell Profile / CMD AutoRun, or adding functions to macOS/Linux shell rc files.

Android device logcat reader for real-time log monitoring. Use when working with pywayne.adb.logcat_reader module to read Android device logs via adb logcat command, supporting both C++ backend (faster) and Python backend (subprocess) with generator-style output for streaming logs.

AHRS quaternion decomposition and roll/pitch compensation utilities. Use when working with pywayne.ahrs.tools module for quaternion to Euler angle decomposition, or compensating orientation to zero pitch and roll using roll-pitch compensation method.

Camera model wrapper for camera_models C++ library via pybind11. Use when working with pywayne.cv.camera_model module to load camera models from YAML configuration files, access camera properties (model type, image size, parameters), perform projection operations (lift_projective, space_to_plane), and export camera parameters as dictionaries.

Geometric hull calculator for 2D point sets supporting convex hull, concave hull (concave-hull, alphashape), and minimum bounding rectangle. Use when working with pywayne.cv.geometric_hull_calculator module to compute geometric hulls, visualize results with OpenCV or matplotlib, and generate random test point sets.

Stereo vision AprilTag matching for dual-camera systems. Use when working with pywayne.cv.stereo_tag_matcher module to match AprilTags from left/right camera views, find common tags between images, stitch stereo images together, and visualize results with color-coded annotations (all tags green, common tags yellow, red connection lines).

OpenCV YAML file read/write utilities. Use when working with pywayne.cv.tools module to read OpenCV FileStorage YAML files with support for nested structures, numpy arrays, basic types, and lists. Handles cv2.FileNode parsing including Map, Seq, and matrix nodes.

LLM chat interface using OpenAI-compatible APIs with streaming support and session management. Use when working with pywayne.llm.chat_bot module for creating LLM chat instances with custom configuration, managing multi-turn conversations with history, handling streaming responses, or managing multiple chat sessions with ChatManager

Gradio-based chat interface for Ollama with multi-session management. Use when working with pywayne.llm.chat_ollama_gradio module to create a web-based chat UI that connects to Ollama models, supports multiple chat sessions, model selection, and streaming responses. Integrates with ChatManager for session management.

PyQt5-based GUI chat window for LLM conversations with streaming responses and stop functionality. Use when working with pywayne.llm.chat_window module to create desktop chat applications with customizable window configuration, system message management, and real-time streaming display.

SO(3) rotation matrix utilities including Lie group/ Lie algebra operations, rotation representation conversions, skew-symmetric matrix operations, and rotation averaging. Use when working with 3D rotations, robot kinematics, computer vision, SLAM, or any task requiring SO(3) matrix validation and manipulation, quaternion/ axis-angle/ Euler angle conversions, Lie algebra Log/Exp mapping, skew-symmetric matrix operations, or rotation matrix averaging

Static 3D visualization utilities wrapping Rerun SDK for adding point clouds, trajectories, cameras, planes, and chessboards. Use when visualizing 3D data in Rerun, including SLAM trajectories, robot poses, camera calibration targets, and debug visualizations. All methods are static and do not require viewer instance management. For SE(3)/SO(3) matrix operations, use pywayne-vio-se3 or pywayne-vio-so3 skills.

3D visualization toolkit wrapping Pangolin viewer for real-time display of point clouds, trajectories, cameras, planes, chessboards, and images. Use when visualizing sensor data (IMU, SLAM, tracking), robot states, or any 3D data with camera poses and trajectories. Supports dual-image display, step mode for debugging, and main camera following.

WebSocket-based cross-language communication service with support for multiple message types (text, JSON, dict, bytes, images, files, folders) and client management. Use when building real-time communication applications between Python and other languages, needing multi-device messaging, or requiring file transfer via Aliyun OSS. Supports both server and client roles with heartbeat, client list management, and message filtering by type or sender.

Aliyun OSS (Object Storage Service) file management toolkit for Python. Use when working with Aliyun OSS to upload files, download files, list objects, delete files, manage directories, read file contents, check file existence, get file metadata, copy and move objects. Supports both authenticated (with API key/secret for write operations) and anonymous access (read-only).

Encryption and decryption toolkit for string and byte data. Supports Fernet (AES-128) symmetric encryption, fallback XOR encryption, custom password protection, code obfuscation, and batch processing. Use when users need to encrypt/decrypt sensitive data, protect algorithms, or obfuscate Python code.

Data structure toolkit for logical condition trees, union-find operations, and XML file I/O. Use when working with tree-based data structures, set operations, union-find algorithms, or XML parsing and serialization.

Windows GUI automation toolkit for global hotkeys and window management. Use when users need to register global hotkeys, find/control windows, automate GUI operations, or perform Windows desktop automation. Requires Windows OS with pywin32, pyuserinput, and pyautogui dependencies.

Project configuration management helper for YAML config files. Use when projects need cross-process/cross-file parameter sharing via a centralized config file. Supports automatic project root detection, nested config key management, and waiting mechanism for values set by other processes.

Mathematical utility functions for factorization, digit counting, and large integer multiplication using Karatsuba algorithm. Use when solving number theory problems, computing factors, counting digit occurrences, or performing optimized large integer multiplication.

Comprehensive statistical testing library with 37+ methods for normality tests, location tests, correlation tests, time series tests, and model diagnostics. Use when performing hypothesis testing, A/B testing, data quality checks, time series analysis, or regression model validation. All methods return unified TestResult objects with consistent interface including p-value, statistic, confidence interval, and effect size.

Enhanced spectrogram visualization tools for time-frequency analysis. Use when creating spectrograms, spectral analysis, or time-frequency plots for signals including IMU data (accelerometer, gyroscope), physiological signals (PPG, ECG, respiration), vibration analysis, and audio processing. Supports frequency unit conversion (Hz/bpm/kHz), multiple normalization modes (global/local/none), and MATLAB-style parula colormap.