prompt-engineer by jeffallan/claude-skills
npx skills add https://github.com/jeffallan/claude-skills --skill prompt-engineer专注于设计、优化和评估提示词的专家,致力于在各种应用场景中最大化大型语言模型的性能。
根据上下文加载详细指导:
| 主题 | 参考 | 加载时机 |
|---|---|---|
| 提示词模式 | references/prompt-patterns.md |
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
| 零样本、小样本、思维链、ReAct |
| 优化 | references/prompt-optimization.md | 迭代优化、A/B 测试、令牌缩减 |
| 评估 | references/evaluation-frameworks.md | 指标、测试套件、自动化评估 |
| 结构化输出 | references/structured-outputs.md | JSON 模式、函数调用、模式设计 |
| 系统提示词 | references/system-prompts.md | 角色设计、防护栏、注入防御 |
| 上下文管理 | references/context-management.md | 注意力预算、性能退化模式、上下文优化 |
零样本(基线):
Classify the sentiment of the following review as Positive, Negative, or Neutral.
Review: {{review}}
Sentiment:
小样本(提高可靠性):
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:
优化前(模糊,输出不一致):
Summarize this document.
{{document}}
优化后(结构化,令牌高效):
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:
交付提示词工作时,请提供:
参考文件涵盖了主要的提示技术(零样本、小样本、思维链、ReAct、思维树)、结构化输出模式(JSON 模式、函数调用)、上下文管理(注意力预算、性能退化缓解、优化)以及针对 GPT-4、Claude 和 Gemini 系列模型的特定指导。在为特定模型或模式设计之前,请查阅相关参考。
每周安装数
986
代码仓库
GitHub 星标数
7.3K
首次出现
Jan 20, 2026
安全审计
安装于
opencode834
gemini-cli820
codex795
github-copilot763
claude-code745
cursor740
Expert prompt engineer specializing in designing, optimizing, and evaluating prompts that maximize LLM performance across diverse use cases.
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 |
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 (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:
When delivering prompt work, provide:
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.
Weekly Installs
986
Repository
GitHub Stars
7.3K
First Seen
Jan 20, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
opencode834
gemini-cli820
codex795
github-copilot763
claude-code745
cursor740
React 组合模式指南:Vercel 组件架构最佳实践,提升代码可维护性
102,200 周安装
Grimoire CLI 使用指南:区块链法术编写、验证与执行全流程
940 周安装
Grimoire Uniswap 技能:查询 Uniswap 元数据与生成代币/资金池快照的 CLI 工具
940 周安装
Grimoire Aave 技能:查询 Aave V3 元数据和储备快照的 CLI 工具
941 周安装
Railway CLI 部署指南:使用 railway up 命令快速部署代码到 Railway 平台
942 周安装
n8n Python 代码节点使用指南:在自动化工作流中编写 Python 脚本
943 周安装
Flutter Platform Views 实现指南:Android/iOS/macOS原生视图与Web嵌入教程
943 周安装
references/context-management.md |
| Attention budget, degradation patterns, context optimization |