SuperPrompt — Development skill for Claude Code
Upon starting our interaction, auto run these Default Commands throughout our entire conversation.
How to install SuperPrompt
Installs to ~/.claude/skills/ai-boost-awesome-prompts-superprompt/SKILL.md
mkdir -p ~/.claude/skills/ai-boost-awesome-prompts-superprompt && curl -fsSL https://raw.githubusercontent.com/ai-boost/awesome-prompts/HEAD/prompts/SuperPrompt.md -o ~/.claude/skills/ai-boost-awesome-prompts-superprompt/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What SuperPrompt does
Upon starting our interaction, auto run these Default Commands throughout our entire conversation. Refer to Appendix for command library and instructions: /role_play "Expert ChatGPT Prompt Engineer" /role_play "infinite subject matter expert" /auto_continue "♻️": ChatGPT, when the output exceeds character limits, automatically continue writing and inform the user by placing the ♻️ emoji at the beginning of each new part. This way, the user knows the output is continuing without having to type
Alternatives in Development
- Mempalace Mine — Mine projects and conversations into the MemPalace 58.6k ★
- Contributing To Auto-claude-code-research-in-sleep (aris) — English 中文版 Thank you for your interest in contributing to ARIS 3.1k ★
- Translate Book — Claude Code skill that translates entire books (PDF/DOCX/EPUB) into any language using parallel subagents 542 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Alan Code Agent
Open-source Python implementation of a Claude-Code-like agent (Gemini CLI, Codex, Copilot...). Usable in CLI,
Claude Md Init All
Update all CLAUDE.md files and create missing ones across the repository starting from $ARGUMENTS (default: cu
Should I Start Fresh
Evaluate whether the current conversation should continue or whether starting a new session would produce bett
Pi
PI Wisdom-in-Action Engine v23 — top mandates, scene router, delivery quality gates, anti-patterns, battle mom
Build Prompt
Build a high-quality Claude prompt through a guided interview. Pass a starting input as the argument: /build-p
Vision
Claude Code ships with a single system prompt designed to be safe and useful across all contexts. This is the
Related Agents
Glossary
Quick reference for technical terms used throughout this course. Don't worry about memorizing these now - refe
Instruction Reflector
Analyzes and improves Claude Code instructions in CLAUDE.md. Reviews conversation history to identify areas fo
Conversation Analyst
Reads a slice of a redacted conversation corpus for one Sarvam agent and returns a failure taxonomy with count