prompt-engineering
Skill0 starsChanged 3 months agoMITView on GitHub
编写高质量、可复现的 LLM 提示词。当需要为一句话/复杂任务设计结构化 prompt、明确角色与约束、利用少样本示例、拆分复杂任务、控制输出格式时使用。
85 other projects use a version of this.
Adopted by
Most recently taken up by
- ishandutta2007/Awesome-Claude-Skillstheir own version, first seen Nov 8, 2026
- kazemcodes/skill-treetheir own version, first seen Nov 8, 2026
- MMACABRE/SKILLStheir own version, first seen Nov 8, 2026
- Hoerire/Azurtheir own version, first seen Nov 8, 2026
- Bruno-Cunha-Souza/ValarMindSkillstheir own version, first seen Nov 8, 2026
- LuisSambrano/antigravity-configtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use security-checklist, multi-agent-orchestration and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
atuljha23Skillsecurity-checklist
OWASP-style quick reference — authn/authz, injection, secrets, sessions, crypto, dependencies. Use during code review and before committing security-sensitive changes.
Also in 3 projects that use this
javalenciacaiSkillmulti-agent-orchestration
Design and coordinate multi-agent systems where specialized agents work together to solve complex problems. Covers agent communication, task delegation, workflow orchestration, and result aggregation. Use when building coordinated agent teams, complex workflows, or systems requiring specialized expertise across domains.
Also in 4 projects that use this
GoogleSkillcoding-principles
Enforces engineering, architecture, public API, and code quality standards distilled from human reviewer feedback across A2UI pull requests. Use when authoring new code, refactoring, addressing review feedback, or reviewing PR diffs. Don't use for release publishing or spec blueprint generation without code or PR changes.
Also in 3 projects that use this
pproencaSkillrefactoring
Code refactoring best practices based on Martin Fowler's catalog and Clean Code principles. This skill should be used when refactoring existing code, improving code structure, reducing complexity, eliminating code smells, or reviewing code for maintainability. Triggers on tasks involving extract method, rename, decompose conditional, reduce coupling, or improve readability.
Also in 6 projects that use this
mjunaidcaSkilltool-design
Design tools that agents can use effectively. Use when creating new tools for agents, debugging tool-related failures, or optimizing existing tool sets.
Also in 3 projects that use this
LangChainSkillweb-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research
Also in 4 projects that use this
Other versions85 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 85
- trycompai/comp★ 2.1ksame name
- niki914/zafiro★ 346same name
- CodeAlive-AI/ai-driven-development★ 169same name
- grandamenium/cortextos★ 106same name
- nahid-sparktales/agent-dispatcher★ 59same name
- geekatron/jerry★ 37same name
- Bbar0n234/learnflow-ai★ 35same name
- nimadorostkar/Claude-Skills-collection★ 33same name
- sabahattink/antigravity-fullstack-hq★ 30same name
- VoDaiLocz/kilo-kit-mcp★ 28same name
75 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- data-cleaningSkill
- fine-tuning-prepSkill
- llm-evaluationSkill
- prompt-optimizerSkill
- rag-builderSkill
The file
Files
提示词工程
用系统化方法把任务清晰地表达给 LLM,显著提高输出的准确率、稳定性与可复现性。
使用步骤
1. 明确目标与边界
- 一句话说清"要模型做什么"(任务动词:总结/改写/分类/抽取/生成/推理/写代码…)。
- 定义输出边界:多长、什么格式、针对什么受众、避免什么。
2. 按结构化模板搭建
推荐一个稳定的 prompt 骨架:
## 角色
你是一名<专业角色>。
## 任务
<用一句话清晰描述要做什么>。
## 输入
<给模型的数据/文本/待处理内容,用分隔符包住>
## 约束
- 只输出结果,不解释过程
- 不超过 N 字 / 用中文 / 采用 Markdown 表格 / 遇到不确定要说明
## 示例(Few-shot)
好的例子:
输入:<例A输入> 输出:<例A输出>
## 输出格式
严格按 JSON: {"字段": ...}3. 用分隔符隔离输入与指令
用 """、---、<xml> 等包裹用户内容,防止注入/混淆,也让输入来源清晰。
4. 复杂任务 → 拆解 + 思维链
- 大任务拆成多步:先抽取→再整理→最后成稿。
- 需要推理的任务,明确要求"先逐步想清楚再给结论"(CoT),可配 few-shot 示例。
5. 少样本示例(Few-shot)
- 给 2~5 个代表性示例,覆盖正常与边界情况。
- 示例必须正确,错误的示例会放大错误。
6. 控制输出格式
用 JSON Schema / 枚举 / 表格 明确约束,便于程序解析。
常见误区(自查清单)
- 任务描述含糊、缺少角色与约束。
- 一次塞太多无关知识与任务混在一起。
- 示例太少或示例本身有误。
- 未隔离输入与指令(注入风险)。
- 没规定输出格式,导致解析困难。
验证
- 同一 prompt 跑多几次,观察稳定性(尤其温度设为 0 或较低)。
- 记录不同版本的差异,做 A/B 比较(见 prompt-optimizer 技能)。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

