A guide for building AI agents and large-language-model applications, including systems that retrieve answers from a document collection. It covers design, tools, memory, prompts, monitoring, and optimization.
A guide for designing and building AI agents and retrieval-augmented generation (RAG) applications. RAG systems search a document collection and use the found material to form answers, often with citations.
A guide for coordinating several AI systems to handle different parts of a task. It describes assigning work to systems such as Claude, Gemini, Codex, and iFlow, then combining and checking their results.
A guide for operating machine-learning systems throughout their lifecycle, from experiments and training to deployment and monitoring. MLOps means the engineering practices that keep machine-learning work reproducible and maintainable.
A toolkit for writing browser-based end-to-end tests with Playwright, a tool that checks complete user journeys in real browsers. It also covers API checks, component checks, screenshot comparisons, and tests across multiple browsers.
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via playwright-cli or the bundled wrapper script.
A guide for building and improving retrieval-augmented generation (RAG) systems. RAG systems find relevant information in a document collection before an AI model writes an answer.
Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (scripts/texttospeech.py) with built-in voices and require OPENAIAPIKEY for live calls. Custom voice creation is out of scope.
Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.
A guide for turning vague requests into clear task briefs for coding agents or groups of agents. Each brief states the goal, context, limits, permissions, stopping rules, evidence, and required handoff format.
A guide for automating Android apps with Auto.js, AutoX.js, or AutoJS Pro using accessibility controls, selectors, screenshots, OCR, and related device features. It is limited to owned devices, authorized testing, and accessibility assistance.
A guide for evaluating large-language-models, AI agents, retrieval systems, prompts, and model changes with datasets, measurements, reviews, and release checks. It focuses on whether AI outputs are accurate, faithful, safe, and useful.
A guide for using MCP servers, tools, and resources safely and correctly. MCP is a standard way for an AI agent to access capabilities or information from other programs.
A security guide for applications that use large language models, covering unsafe inputs, model outputs, personal data, retrieved documents, and tool access.
/cs:ai-act-readiness — EU AI Act 6-question forcing interrogation. Use during AI-system intake, before EU deployment, or during annual compliance refresh as Article 113 obligations phase in (2025-02-02 / 2025-08-02 / 2026-08-02 / 2027-08-02).
/cs:aims-audit — ISO/IEC 42001 AIMS internal-audit 6-question forcing interrogation. Use before certification stage 1, before annual internal audit cycles, or when onboarding a new AI system into an existing AIMS.
Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences…
App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and Google Play Store. Use when the user asks about ASO, app store rankings, app metadata, app titles and descriptions, app store listings, app…
A toolkit for designing and reviewing APIs, databases, command-line tools, software libraries, and data pipelines. It covers contracts such as REST, GraphQL, and OpenAPI, where OpenAPI is a machine-readable description of an API.
A set of Chinese-language rules for designing and reviewing web APIs, which are interfaces that let software exchange requests and responses. It covers routes, authentication, validation, errors, pagination, and safety.