跳到主内容
智客 ZICQ

技能库 智客分类:设计创意 prompt-engineer

Prompt Engineer

为 LLMs 编写、重构和评价提示——生成最优化的即时模板、结构化输出计划、评价标题和测试套件。 在设计新的 LLM 应用程序的提示时使用,为更好的准确性或象征性效率重构现有的提示,执行思维链式或几发的学习,创建带有人和护栏的系统提示,建立JSON/函数调用计划,或制定即时评价框架来衡量和改善模型性能.

5056 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

编写、重构和评价LLMS的提示——生成优化的即时模板、结构化的输出计划、评价标题和测试套件

何时用

这个技能

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Prompt Engineer、When to Use This Skill、Core Workflow、Reference Guide、Prompt Examples、Zero-shot vs. Few-shot。 其中含规范建议的小节:分步指令、输入输出示例。

文件分析

文件分析:除 SKILL.md 外,正文引用了 references/prompt-patterns.md、references/prompt-optimization.md、references/evaluation-frameworks.md、references/structured-outputs.md、references/system-prompts.md、references/context-management.md,属于带资源的技能包,这些文件按需再读。

官方 description(原文)

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.

Prompt EngineerWhen to Use This SkillCore WorkflowReference GuidePrompt ExamplesZero-shot vs. Few-shotBefore/After OptimizationConstraintsMUST DOMUST NOT DOOutput TemplatesCoverage Note

· 许可:MIT

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
prompt-engineer
description
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance.
许可
MIT
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。
指令中引用的文件 · 6
  • references/prompt-patterns.md
  • references/prompt-optimization.md
  • references/evaluation-frameworks.md
  • references/structured-outputs.md
  • references/system-prompts.md
  • references/context-management.md

以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「prompt-engineer」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-d20eb9e99e3a86c1-%E5%BF%AB%E9%80%9F%E5%B7%A5%E7%A8%8B%E5%B8%88.html
请存为 .cursor/skills/prompt-engineer/SKILL.md 或 .claude/skills/prompt-engineer/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/jeffallan/claude-skills 取完整目录,不要只建一个 SKILL.md。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/jeffallan/claude-skills' --list

npx skills add 'https://github.com/jeffallan/claude-skills' --skill 'prompt-engineer'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

name: prompt-engineer description: Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot learning, creating system prompts with personas and guardrails, building JSON/function-calling schemas, or developing prompt evaluation frameworks to measure and improve model performance. license: MIT metadata: author: https://github.com/Jeffallan version: "1.2.0" domain: data-ml triggers: prompt engineering, prompt optimization, chain-of-thought, few-shot learning, prompt testing, LLM prompts, prompt evaluation, system prompts, structured outputs, prompt design, context management, lost-in-the-middle, context degradation, token optimization, attention budget role: expert scope: design output-format: document related-skills: test-master, rag-architect, debugging-wizard

Prompt Engineer

Expert prompt engineer specializing in designing, optimizing, and evaluating prompts that maximize LLM performance across diverse use cases.

When to Use This Skill

  • Designing prompts for new LLM applications
  • Optimizing existing prompts for better accuracy or efficiency
  • Implementing chain-of-thought or few-shot learning
  • Creating system prompts with personas and guardrails
  • Building structured output schemas (JSON mode, function calling)
  • Developing prompt evaluation and testing frameworks
  • Debugging inconsistent or poor-quality LLM outputs
  • Migrating prompts between different models or providers

Core Workflow

  1. Understand requirements — Define task, success criteria, constraints, and edge cases
  2. Design initial prompt — Choose pattern (zero-shot, few-shot, CoT), write clear instructions
  3. Test and evaluate — Run diverse test cases, measure quality metrics
    • Validation checkpoint: If accuracy < 80% on the test set, identify failure patterns before iterating (e.g., ambiguous instructions, missing examples, edge case gaps)
  4. Iterate and optimize — Make one change at a time; refine based on failures, reduce tokens, improve reliability
  5. Document and deploy — Version prompts, document behavior, monitor production

Reference Guide

Load detailed guidance based on context:

| Topic | Reference | Load When | |-------|-----------|-----------| | Prompt Patterns | references/prompt-patterns.md | Zero-shot, few-shot, chain-of-thought, ReAct | | Optimization | references/prompt-optimization.md | Iterative refinement, A/B testing, token reduction | | Evaluation | references/evaluation-frameworks.md | Metrics, test suites, automated evaluation | | Structured Outputs | references/structured-outputs.md | JSON mode, function calling, schema design | | System Prompts | references/system-prompts.md | Persona design, guardrails, injection defense | | Context Management | references/context-management.md | Attention budget, degradation patterns, context optimization |

Prompt Examples

Zero-shot vs. Few-shot

Zero-shot (baseline):

Classify the sentiment of the following review as Positive, Negative, or Neutral.

Review: {{review}}
Sentiment:

Few-shot (improved reliability):

Classify the sentiment of the following review as Positive, Negative, or Neutral.

Review: "The battery life is incredible, lasts all day."
Sentiment: Positive

Review: "Stopped working after two weeks. Very disappointed."
Sentiment: Negative

Review: "It arrived on time and matches the description."
Sentiment: Neutral

Review: {{review}}
Sentiment:

Before/After Optimization

Before (vague, inconsistent outputs):

Summarize this document.

{{document}}

After (structured, token-efficient):

Summarize the document below in exactly 3 bullet points. Each bullet must be one sentence and start with an action verb. Do not include opinions or information not present in the document.

Document:
{{document}}

Summary:

Constraints

MUST DO

  • Test prompts with diverse, realistic inputs including edge cases
  • Measure performance with quantitative metrics (accuracy, consistency)
  • Version prompts and track changes systematically
  • Document expected behavior and known limitations
  • Use few-shot examples that match target distribution
  • Validate structured outputs against schemas
  • Consider token costs and latency in design
  • Test across model versions before production deployment

MUST NOT DO

  • Deploy prompts without systematic evaluation on test cases
  • Use few-shot examples that contradict instructions
  • Ignore model-specific capabilities and limitations
  • Skip edge case testing (empty inputs, unusual formats)
  • Make multiple changes simultaneously when debugging
  • Hardcode sensitive data in prompts or examples
  • Assume prompts transfer perfectly between models
  • Neglect monitoring for prompt degradation in production

Output Templates

When delivering prompt work, provide:

  1. Final prompt with clear sections (role, task, constraints, format)
  2. Test cases and evaluation results
  3. Usage instructions (temperature, max tokens, model version)
  4. Performance metrics and comparison with baselines
  5. Known limitations and edge cases

Coverage Note

Reference files cover major prompting techniques (zero-shot, few-shot, CoT, ReAct, tree-of-thoughts), structured output patterns (JSON mode, function calling), context management (attention budgets, degradation mitigation, optimization), and model-specific guidance for GPT-4, Claude, and Gemini families. Consult the relevant reference before designing for a specific model or pattern.

Documentation

相关技能

设计创意

Automation Workflows

设计和实施自动化工作流程,以节省时间和规模化操作作为独家. 用于识别重复任务实现自动化,构建跨工具的工作流程,设置触发器和行动,或优化现有自动化. 包括自动化机会识别,工作流程设计,工具选择(Zapier,Make,n8n),测试,和维护. 触发"自动","自动","工作流程自动…

设计创意

Ui Ux Pro Max

UI/UX设计智能及建筑抛光接口实施指导. 当用户要求UI设计,UX流量,信息架构,视觉风格方向,设计系统/托盘,组件规格,副本/显微镜,可访问性,或生成/critique/refine前端UI(HTML/CSS/JS,React,Next.js,Vue,Svelte,Tailw…

设计创意

Frontend Design

创建美丽现代UI的专家前端设计指南. 在构建起落架页面,仪表板,或任何用户界面时使用.

设计创意

N8n Workflow Automation

设计和输出 n8n 工作流程 JSON 有强力触发器, idempotency, 错误处理, 记录, 重试, 以及 人入"一站"审查队列. 当您需要可审计的自动化时使用.