Explore skills

Parse and execute commands given in Cantonese. Use when user gives instructions or requests actions in Cantonese. Translates Cantonese commands to executable actions.

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

Conduct natural conversations in Cantonese. Combines understanding, response generation, and cultural awareness for fluid Cantonese dialogue.

Generate responses in Cantonese. Use this skill to reply to users in Cantonese when they communicate in Cantonese or request Cantonese output.

Translate between Cantonese and other languages (Mandarin, English, etc.). Use when user explicitly requests translation or when translation is needed for communication.

Parse and understand Cantonese user input. ALWAYS use this skill first when user writes in Cantonese or uses Cantonese vocabulary. This skill translates Cantonese to standard Chinese/English for LLM comprehension.

Use when a skill exists but blind assessment shows it underperforms, or when iteratively improving a skill through experiment cycles while avoiding overfitting to fixed benchmarks

Generates a dynamic, professional Product Requirements Document (PRD) for any task, feature, product, or project described by the user. Use this skill whenever the user mentions "PRD", "product requirements", "write requirements for", "create a spec", "feature doc", "product doc", "requirement document", or asks to plan/document any feature, app, tool, or system. Also trigger when users say "I wan

World-class AI prompt engineering skill for creating, refining, and enhancing prompts for any LLM task. Use this skill whenever the user wants to: write a new prompt from scratch, improve or refine an existing prompt, enhance a vague instruction into a structured prompt, debug why a prompt isn't working, convert a rough idea into a production-ready prompt, or asks anything related to "prompt engin

Inflate a memory file (CLAUDE.md, AGENTS.md, notes, todo lists) from plain English into ornate Early Modern English prose, while keeping every code block, URL, path, command, identifier, heading, date, and table untouched. A human-readable backup is written to `<file>.original.md`. Trigger: /shakespeare-expand <filepath> or "expand memory file".

Generate an ornate, Elizabethan commit message for the currently staged changes. Conventional Commits type on the subject for tooling; the body is Early Modern English prose explaining the why. Use when the user types /shakespeare-commit or asks for a "bard commit". Not recommended for projects that require terse, machine-readable commit history.

Quick-reference card for shakespeare mode — all intensity levels, commands, and activation phrases. One-shot display, not a persistent mode. Use when the user types /shakespeare-help or asks "what shakespeare commands are there".