meta-prompt by mindrally/skills
npx skills add https://github.com/mindrally/skills --skill meta-prompt一套用于评估和分析 AI 响应及解决方案路径的元提示技术集合。
一个用于评判和反思响应质量的框架,提供评分并指示响应是否已完全解决问题或任务。
Reflections : 对响应的充分性、冗余性和整体质量的评判与反思。
Score : 对候选响应质量的评分,范围为 0-10。
Found_solution : 响应是否已完全解决问题或任务。
评估响应时,请考虑以下几点:
请对这些方面以及任何其他相关因素进行深思熟虑的反思。使用分数来指示整体质量,并且仅当响应完全解决了问题或完成了任务时,才将 found_solution 设置为 true。
reflections: "该响应清晰简洁,有效地解决了主要问题。但是,它本可以提供更多关于边缘情况的背景信息。"
score: 8
found_solution: true
用于分析问答任务解决方案路径的指南。
: 关于当前情况的环境信息,为决策提供背景。
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
Thoughts : 对当前情况的推理,分析已观察到的内容并规划后续步骤。
Actions : 为推进任务解决所采取的步骤。
Search[entity] : 搜索确切的实体,如果该实体存在则返回相关信息。如果不存在,则返回类似实体的建议。
Lookup[keyword] : 返回包含该关键词的下一个相关段落。用于在检索到的内容中查找特定信息。
Finish[answer] : 返回答案并结束任务。当已收集到足够信息以提供明确响应时使用。
分析轨迹时:
引导模型进行逐步推理:
Let's approach this step by step:
1. First, identify the key components
2. Then, analyze each component
3. Finally, synthesize the findings
提供示例以建立模式:
Example 1: [input] -> [output]
Example 2: [input] -> [output]
Now apply this pattern to: [new input]
生成多个推理路径并选择最一致的答案。
鼓励自我评判:
Review your response and identify:
- Any potential errors or oversights
- Areas that could be explained more clearly
- Missing information that would strengthen the answer
每周安装量
88
代码仓库
GitHub 星标数
43
首次出现
2026年1月25日
安全审计
安装于
gemini-cli74
opencode73
cursor70
codex69
github-copilot66
claude-code64
A collection of meta-prompting techniques for evaluating and analyzing AI responses and solution paths.
A framework for critiquing and reflecting on the quality of responses, providing a score and indicating whether the response has fully solved the question or task.
Reflections : The critique and reflections on the sufficiency, superfluency, and general quality of the response.
Score : Score from 0-10 on the quality of the candidate response.
Found_solution : Whether the response has fully solved the question or task.
When evaluating responses, consider the following:
Provide thoughtful reflections on these aspects and any other relevant factors. Use the score to indicate the overall quality, and set found_solution to true only if the response fully addresses the question or completes the task.
reflections: "The response was clear and concise, addressing the main question effectively. However, it could have provided more context on edge cases."
score: 8
found_solution: true
Guidelines for analyzing solution paths to question-answering tasks.
Observations : Environmental information about the current situation that provides context for decision-making.
Thoughts : Reasoning about the current situation, analyzing what has been observed and planning next steps.
Actions : The steps taken to progress toward solving the task.
Search[entity] : Searches for the exact entity and returns relevant information if the entity exists. If not, returns suggestions for similar entities.
Lookup[keyword] : Returns the next relevant passage that contains the keyword. Used for finding specific information within retrieved content.
Finish[answer] : Returns the answer and finishes the task. Used when sufficient information has been gathered to provide a definitive response.
When analyzing a trajectory:
Guide the model through step-by-step reasoning:
Let's approach this step by step:
1. First, identify the key components
2. Then, analyze each component
3. Finally, synthesize the findings
Provide examples to establish the pattern:
Example 1: [input] -> [output]
Example 2: [input] -> [output]
Now apply this pattern to: [new input]
Generate multiple reasoning paths and select the most consistent answer.
Encourage self-critique:
Review your response and identify:
- Any potential errors or oversights
- Areas that could be explained more clearly
- Missing information that would strengthen the answer
Weekly Installs
88
Repository
GitHub Stars
43
First Seen
Jan 25, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
gemini-cli74
opencode73
cursor70
codex69
github-copilot66
claude-code64
AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具
49,800 周安装
Convex组件创建指南:构建可复用后端模块与第三方集成
15,600 周安装
文章插图生成器 - AI智能分析文章内容,自动生成类型风格一致的配图
15,300 周安装
AI封面图片生成器 - 5维定制文章封面,一键生成优雅视觉
15,300 周安装
shadcn/ui 组件库:基于 Radix UI 和 Tailwind CSS 的可访问、可定制 React UI 组件
15,400 周安装
小红书信息图生成器 - AI自动生成多风格小红书图文内容,提升内容创作效率
15,500 周安装
Convex 快速入门指南:5分钟搭建全栈应用,支持React/Next.js/Vue/Svelte
16,200 周安装