dreamor

prompt-optimizer

Optimize and rewrite prompts using 61 frameworks (APE, RACE, CRISPE, Chain-of-Thought, COAST, SMART, etc.). Trigger on "optimize prompt", "improve this prompt", "make this prompt better", "rewrite for AI", "优化提示词", "改写 prompt", "优化指令", "��提示词更好", "帮我把这个写成 prompt" or any vague/short instruction the user wants turned into a high-quality prompt — even if the user only says "make this clearer" or "help me write this". Also trigger whenever the user pastes raw text and asks for a structured AI-ready version, or expresses dissatisfaction with AI output quality without naming a fix. Always use this skill when the user inputs vague instructions, needs prompt optimization, or is dissatisfied with AI output quality.

1 Updated 4 weeks ago

memvault-recall

Search the user's shared MemVault memory store. Use when the user references past conversations ("I told you before...", "as usual...", "remember...") or when personal/project context would change the answer and current context has none.

memvault-review

Work the MemVault review inbox — inspect auto-extracted memory drafts (with their source snippets) and approve, edit, or reject each one. Use when the user asks to review memories, or /memvault-review is invoked.

memvault-save

Write a durable learning (explicit user preference, correction, project decision) into the shared MemVault store so every future session and agent inherits it. Use whenever the user states a lasting preference or corrects course, or asks to remember something.

memvault-sync

Regenerate agent-native rule files (CLAUDE.md, AGENTS.md, .github/copilot-instructions.md) from the MemVault store for hosts without hook injection. Use when the user asks to sync/refresh memory into rule files, or /memvault-sync is invoked.