Backend skills

This skill helps you query, create, update, and delete CloudBase documents in WeChat MiniProgram apps with efficient, scalable database operations.

This skill guides structured software development from requirements to task execution using EARS syntax and UI-design references to ensure quality.

This skill helps you develop CloudBase Run backends with long connections and AI agents, supporting multi-language runtimes and secure, scalable deployments.

This skill helps you develop, deploy, and manage CloudBase cloud functions by guiding runtime selection, deployment, logging, and HTTP access configuration.

This skill guides calling AI models with CloudBase across web, Node, and WeChat Mini Program, enabling text, streaming, and image workflows.

This skill dumps basic system and environment information to out/env.txt to aid debugging and auditing.

This skill writes a hello file to the workspace output directory, enabling quick validation of file I/O in Go workflows.

This skill extracts text from images using OCR with Tesseract, supporting many languages and optional preprocessing for improved accuracy.

This skill transcribes audio to text using OpenAI Whisper, supporting multiple languages, models, and optional timestamps for versatile transcripts.

This skill helps you use the Upstash Redis SDK for serverless caching, sessions, rate limiting, and data structures with automatic serialization.

This skill runs multiple isolated dev-server sandboxes by provisioning temporary MUX_ROOTs and free ports to speed parallel development.

This skill enables browser automation via HTTP API to navigate pages, interact with elements, extract data, and run batch actions for faster tasks.

This skill helps you generate and validate mermaid diagrams for flowcharts, sequences, and mind maps to document processes and architectures.

This skill streamlines OmicVerse data loading by replacing scanpy with ov.io readers for h5ad, 10x, Visium, Nanostring, and CSV formats.

This skill exports bioinformatics results and tables to formatted Excel files using openpyxl, running locally for compatibility with all LLM providers.

This skill guides migrating error handling to a typed Result-based approach, converting try/catch to Result.try and applying railway-oriented patterns.

This skill ensures TTS worker errors are reported to the main process to trigger user-friendly toasts and prevent silent failures.

This skill pushes local commits to an existing PR source branch without creating new branches, ensuring compliant and gap-free updates.

This skill helps you integrate Gemini OpenAI compatible API, configure thinking, and normalize responses for seamless AI-assisted workflows.

This skill extracts a price series from raw data to generate a Pytestable test module and Parquet data for vault price testing.

This skill analyzes YouTube subtitles to generate precise 2-5 minute chapters and outputs clip-ready, bilingual subtitles for quick editing.