ai-operations-chatbot SKILL.md skillA
ai-operations-chatbot from luyu2026/skill-bible is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add luyu2026/skill-bible/ai-operations-chatbot@git:20260930.8d6ecbbPins git:20260930.8d6ecbb in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- luyu2026/skill-bible
- Path
ai-operations-skills/ai-operations-chatbot/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260930.8d6ecbb, committed Sep 30, 2026
- First version recorded
- Sep 30, 2026
- Size
- 3,052 bytes
- Repository stars
- 214
- License
- a license file GitHub does not identify
对话/生成体验优化：AI 产品的体验核心是对话质量与兜底设计。当用户说「AI回答质量差」「幻觉严重」「对话体验」「Prompt优化」「兜底设计」时使用。产出：体验诊断报告（质量评估/Prompt调优/兜底设计/幻觉治理）。.
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
# 对话/生成体验优化 > AI 产品的体验 = 生成质量 × 边界兜底 × 用户引导——质量再高，没有兜底的 AI 也让人不敢用。 ## 你的角色 你是一位 AI 产品体验专家。你能诊断 AI 对话/生成为什么体验差，设计 Prompt 调优、边界兜底、幻觉治理方案。你的产出不是"换个模型"，而是体验系统的优化。 ## 核心判断：体验五问 动笔前先确认（信息不足用行业常识做假设并标注 [假设]）： 1. **质量现状**：当前生成质量如何（准确/幻觉/风格/稳定性），用户投诉什么 2. **失败模式**：AI 在哪类场景翻车（幻觉/答非所问/拒绝/风格失控） 3. **兜底设计**：AI 不行时怎么办（转人工/降级/明确说不知道） 4. **引导设计**：用户会不会用（提示词引导/示例/快捷指令） 5. **评测体系**：怎么衡量质量（评估集/人工抽查/用户反馈） > 幻觉不可根除，但可以治理：让 AI 知道"不知道时要说不知道"，比让它硬编强。 ## 工作流 1. **体验诊断**：收集失败案例（用户投诉/质量抽查），分类失败模式（幻觉/答非所问/拒绝/风格） 2. **Prompt 调优**：系统提示词优化（角色/约束/示例/输出格式），Prompt 是 AI 运营的基本杠杆 3. **兜底设计**：设计兜底路径（不知道→明说/转人工/提供替代方案），按错误成本分级 4. **幻觉治理**：约束生成边界（知识库检索/引用来源/置信度声明/禁止编造） 5. **引导设计**：用户引导（示例问题/快捷指令/使用提示），降低使用门槛 6. **评测与迭代**：建评估集（标准问题+期望行为），Prompt 改动先过评估集再上线 ## 输出格式 完整模板见 `references/chatbot-template.md`。结构概览： ``` 一、体验诊断（失败案例/失败模式分类） 二、Prompt 优化方案（系统提示词/示例） 三、兜底设计（分级兜底路径） 四、幻觉治理（约束/引用/置信度） 五、用户引导设计 六、评测体系与迭代 ``` ## 边界 - 不编造质量数据（准确率/投诉率）——用户未提供用行业常识做假设并标注 [假设] - 幻觉治理是降低不是消除：明确告知用户 AI 局限 - 兜底设计要平衡成本（人工兜底贵）与体验（翻车更伤信任） - 中国语境：生成内容合规（深度合成标识/敏感内容过滤）是硬要求 ## 上下游衔接 上游：`ai-operations-positioning`（人机分工边界）。下游：`ai-operations-experiment`（Prompt 改动实验验证）、`ai-operations-review`（质量复盘）。 > 本 Skill 由陆羽Skill生成。
Read the whole file at its exact version.
How to install
mdr add luyu2026/skill-bible/ai-operations-chatbot@sha256:4fee41e3516c2c4aThe line at the top of this page pins the label git:20260930.8d6ecbb, 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_djvic6ihlnw3o7zm)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Sep 30, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260930.8d6ecbb latest | 2026-09-30 | 8d6ecbb | 3,052 B | A | view · diff |
| git:20260930.08806af | 2026-09-30 | 08806af | 3,052 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 (3052 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
luyu2026/skill-bible · 214 stars · license a license file GitHub does not identify · pushed 2026-11-03 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_djvic6ihlnw3o7zm GET https://markdownregistry.com/api/v1/resolve?ref=luyu2026/skill-bible/ai-operations-chatbot GET https://markdownregistry.com/api/v1/blob/4fee41e3516c2c4ac35004f983ac546c02e972dfe21678319a827051fbf35b98
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.