prompt-enhancer SKILL.md skillA
prompt-enhancer from renky1025/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add renky1025/agent-skills/prompt-enhancer@git:20260925.32ce6c0Pins git:20260925.32ce6c0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- renky1025/agent-skills
- Path
prompt-enhancer/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260925.32ce6c0, committed Sep 25, 2026
- First version recorded
- Sep 9, 2026
- Size
- 8,745 bytes
- Repository stars
- 11
- License
- MIT
将用户给出的"弱提示词 / 草稿指令"按《开发强指令》方法论增强为生产级强指令。方法论核心为八段式结构（角色+目标 -> 上下文 -> 复述对齐 -> 先思考 -> 执行要求 -> 明确不要 -> 自我批评 -> 输出与验收），配套八条指导思想（角色目标 / 复述对齐 / 先思考 / 明确不要 / 自我批评 / 不同方向 / 给例子 / 充分上下文）。当用户说"增强提示词"、"强化提示词"、"优化一下这段 prompt"、"把这句需求改写成强指令"、"按开发强指令方法论改写"、"enhance/strengthen this prompt"、或给出一段任务描述草稿并要求"让它更稳更准 / 更少返工"时触发。输入：原始提示词（必须）+ 可选领域背景 / 参考例子。输出：可粘贴的强指令全文 + 增强对照表（原稿薄弱点 -> 增强处理）+ 用法说明（占位符与可裁剪闸门）。不用于直接执行提示词描述的任务本身。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 增强提示词（prompt-enhancer）
## Purpose
把"一句话草稿"变成"八段式生产级强指令"，减少 AI 拿到任务就开干、做错方向、交出平庸结果的行为。
产出物是三件：可直接粘贴的强指令全文、增强对照表、用法说明。
## When to Use
- 用户给出一段任务描述草稿，要求"增强 / 强化 / 优化"它。
- 用户要求把口语化需求改写成结构化强指令。
- 用户说"让它更稳更准 / 更少返工 / 少走弯路"，意图是改指令而不是执行指令。
- 触发词：增强提示词、强化提示词、优化一下这段 prompt、把这句需求改写成强指令、按开发强指令
方法论改写、enhance this prompt、strengthen this prompt。
- 用法：`增强提示词：<原始提示词>`；可追加说明 `受众 / 领域 / 我满意的例子 / 输出语言`。
## When NOT to Use
- **本 Skill 不执行提示词里描述的任务。** 用户要的是"把指令写好"，不是"照着指令干活"；若用户想
的是后者，直接执行任务，不要先产出增强版指令。
- 用户要的是某个具体领域的成品（方案、代码、文档）而非改进指令 -> 按该任务本身处理或路由到对应
Skill。
- 用户只想要翻译、润色或去 AI 味 -> 交给 `de-ai-writing` 等专项 Skill，不要套用八段式结构。
## Workflow
1. **解析原稿**。提取意图（要 AI 完成什么）、产出物、目标受众、隐含约束、领域。留意原稿里的
口语化/错字表达，按真实意图归一化（如"我向导的是"->"我想要的是"），不把错字带进增强版。
2. **诊断缺口**（对照下方骨架逐项检查）。重点查这些常见病：
- 无角色 / 无目标，或目标不可验证。
- 口头结构要求没有固化为步骤（例："要有主业务路径、业务能力、产品能力"只是描述，没变成执行
步骤 + 自检）。
- "不清楚就问 / 有问题随时问"太含糊，没定义问什么、什么时候问。
- 无"明确不要"，AI 易跑偏或虚构（编造仓库不存在的证据等）。
- 无验收标准 / 交付清单。
- 无防平庸机制（自我批评、不同方向）。
3. **选模板**。按任务领域从 `references/method-quickref.md` 的模板库选取最贴近的骨架；跨领域任务
合并多个模板的要素。
4. **增强填充**（核心技巧）：
1. **角色落地**：给专业身份 + 判断准则（例：售前解决方案架构师，擅长把技术翻译成高层业务语言）。
2. **目标可验证**：把"生成一张图"升级为带验收口径的目标（例：让不懂技术的客户高层 3 分钟看懂）。
…Read the whole file at its exact version.
How to install
mdr add renky1025/agent-skills/prompt-enhancer@sha256:2e81a2a948418411The line at the top of this page pins the label git:20260925.32ce6c0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_4gr3f3tneecqwrmb)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Sep 9, 2026 and Sep 25, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260925.32ce6c0 latest | 2026-09-25 | 32ce6c0 | 8,745 B | A | view · diff |
| git:20260910.97b7c0d | 2026-09-10 | 97b7c0d | 10,464 B | A | view · diff |
| git:20260909.0f98fca | 2026-09-09 | 0f98fca | 10,476 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8745 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
renky1025/agent-skills · 11 stars · license MIT · pushed 2026-10-10 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_4gr3f3tneecqwrmb GET https://markdownregistry.com/api/v1/resolve?ref=renky1025/agent-skills/prompt-enhancer GET https://markdownregistry.com/api/v1/blob/2e81a2a9484184112c2eb399eb6840f94d716571c5cafea8c0069d30e6beed21
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from renky1025/agent-skills
Every file in renky1025/agent-skills