Prompt: Initial Ruleset Generation
Generate initial causal rules \(R_0\) from clustering context.
Explore
23,619 skills indexed with the new KISS metadata standard.
Generate initial causal rules \(R_0\) from clustering context.
На основе текста из истории, создай детальное описание одной сцены на английском, а затем иллюстрацию на основе описания. Используй нейтральные обозначения для людей и животных, не имена, например, "мальчик" вместо "Ваня", "женщина" вместо "Анна", "собака" вместо "Жучка", и т.п. Если в тексте больше
A core intuition and opinion baked into the design of VLM Caption is that multi-turn conversation can help extract superior information by allowing different questions to be asked, then bring them together with a final summary request. Other VLM scripts or apps are likely just trying to "one shot"
====================================================
You are an intelligent agent that completes multi-step tasks.
generic skill
Agent is prompted to [task description] with this skill loaded.
The workflow engine persistence schema is duplicated in RivetKit for inspector transport.
Generic sync.Pool wrappers with automatic reset functionality.
Dux Lite 项目开发规则模板(基于 dux-php-admin 规范去重整理)。
Generic sync.Pool wrappers with automatic reset functionality.
We keep all important docs in .agent folder and keep updating them, structure like below
data prep
excellent for self-hosting
practical starter prompt
best at following extremely long/complex instructions
real-time knowledge via X
some inconsistency |
drafting
consistent data
but goals or data are unclear. AI could assist with insights
well-defined data
not an instant automation request.
Personal Knowledge Base with semantic search. Use to search indexed markdown documents for relevant context, notes, or documentation.