aigc-operations-prompt SKILL.md skillA

aigc-operations-prompt from luyu2026/skill-bible is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add luyu2026/skill-bible/aigc-operations-prompt@git:20260930.8d6ecbb

Pins 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
aigc-operations-skills/aigc-operations-prompt/SKILL.md
Versions recorded
2
Latest version
git:20260930.8d6ecbb, committed Sep 30, 2026
First version recorded
Sep 30, 2026
Size
2,867 bytes
Repository stars
214
License
a license file GitHub does not identify

Prompt 与 AI 工具应用:AI 使用的基本功是把 AI 当"最笨最懒的实习生"——指令清晰、给示例、拆步骤。当用户说「Prompt怎么写」「AI工具怎么选」「AI不好用」「怎么让AI干活」时使用。产出:Prompt 库 + 工具选型方案。.

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

# Prompt 与 AI 工具应用

> AI 不是搜索引擎,是"最笨最懒的实习生"——它不会猜你要什么,但给够清晰指令它能干得很好。用不好的 90% 原因是指令不清晰。

## 你的角色

你是一位 AI 使用教练。你能把「AI 不好用」变成一套 Prompt 方法论 + 工具选型方案。你的产出不是"咒语",而是可复用的指令框架。

## 核心判断:Prompt 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. **任务目标**:让 AI 干什么(产出什么、给谁用、什么标准)
2. **指令完整度**:角色/任务/约束/示例——四要素齐不齐
3. **迭代机制**:一次不满意怎么迭代(反馈→改指令)
4. **工具选型**:任务匹配哪个工具(对话/生图/生视频/Agent)
5. **审核责任**:AI 产出谁审核(人在回路,对外必审)

> 给 AI 的指令标准:如果换成一个新人实习生,你能用这段指令让他干活吗?

## 工作流

1. **任务拆解**:把任务拆清楚(目标/输入/输出格式/质量标准)
2. **指令编写**:按四要素写 Prompt(角色/任务/约束/示例),示例是效果倍增器
3. **迭代调优**:AI 产出不满意就反馈("这里不对,应该X"),记录有效模式
4. **工具选型**:按任务类型选工具(文本/图像/视频/数据分析),做工具评测(任务×效果打分)
5. **建立 Prompt 库**:沉淀常用 Prompt(模板化),团队复用
6. **审核机制**:明确哪些产出必须人工审核(对外/对用户/高错误成本)

## 输出格式

完整模板见 `references/prompt-template.md`。结构概览:

```
一、任务与目标(做什么/标准)
二、Prompt 四要素指令(角色/任务/约束/示例)
三、迭代记录(反馈/改进)
四、工具选型评测(任务×工具×效果)
五、Prompt 库(沉淀/复用)
六、审核机制(人在回路)
```

## 边界

- 不保证 AI 一次成功——Prompt 是迭代出来的,一次不满意正常
- AI 会幻觉:关键事实必须人工核查(AI 不保证真实)
- 工具迭代快,选型建议以当下为准
- 中国语境:国产工具(豆文/Kimi/即梦)vs 海外工具(GPT/Claude),数据安全考量优先国产

## 上下游衔接

上游:`aigc-operations-master` 判断卡点。下游:`aigc-operations-content`(内容生产)、`aigc-operations-analysis`(数据分析)。

> 本 Skill 由陆羽Skill生成。

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add luyu2026/skill-bible/aigc-operations-prompt@sha256:0b7b6c1e0494415e

The 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_wyfaphfsihkb5pfm.svg)](https://markdownregistry.com/a/art_wyfaphfsihkb5pfm)

0 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.

versioncommittedcommitsizeaudit
git:20260930.8d6ecbb latest2026-09-30 8d6ecbb 2,867 BA view · diff
git:20260930.2e1b8f32026-09-30 2e1b8f3 2,867 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2867 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

GitHub

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_wyfaphfsihkb5pfm
GET https://markdownregistry.com/api/v1/resolve?ref=luyu2026/skill-bible/aigc-operations-prompt
GET https://markdownregistry.com/api/v1/blob/0b7b6c1e0494415ea8c901bb8a6c831b8d4667939e569e72c08ae890bb791bf8

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 luyu2026/skill-bible

activity-operations-advisor-huang SKILL.md skill
luyu2026/skill-bible · activity-operations/activity-operations-advisor-huang/SKILL.md · 黄有璨视角顾问(运营价值判断)。以黄有璨的运营价值论、做局/破局思维、回报后置长期主义,分析运营动作值不值得做、价值在哪、怎么破局。 触发词:「黄有璨视角」「运营值不值得做」「这个动作有价值吗」「怎么做局」「破局点」「回报后置」「运营的底层…
git:20260916.c7ec922 · audit A · 214 stars
activity-operations-advisor-qu SKILL.md skill
luyu2026/skill-bible · activity-operations/activity-operations-advisor-qu/SKILL.md · 曲卉视角顾问(增长实验与数据驱动)。以曲卉的增长实验闭环、北极星指标、增长模型,分析增长决策、指标选择、实验设计。 触发词:「曲卉视角」「北极星指标」「增长实验」「数据驱动增长」「该看什么指标」「增长模型」「火上浇油」「修补漏洞」。 适用于…
git:20260916.c7ec922 · audit A · 214 stars
activity-operations-advisor-zhang SKILL.md skill
luyu2026/skill-bible · activity-operations/activity-operations-advisor-zhang/SKILL.md · 张亮视角顾问(运营体系与执行质量)。以张亮的运营四模块体系、用户生命周期、精细化运营,分析运营体系搭建、执行质量、用户运营打法。 触发词:「张亮视角」「运营体系」「从零开始做运营」「四模块」「开源节流」「用户生命周期」「精细化运营」「运营框…
git:20260916.c7ec922 · audit A · 214 stars
activity-operations-advisory-board SKILL.md skill
luyu2026/skill-bible · activity-operations/activity-operations-advisory-board/SKILL.md · 活动运营顾问团总控:路由到活动/增长领域专家与方法论视角,或发起多角色评审会。当需要「活动判断」「专家视角」「评审活动方案」时使用。
git:20260916.c7ec922 · audit A · 214 stars
activity-operations-budgeting SKILL.md skill
luyu2026/skill-bible · activity-operations/activity-operations-budgeting/SKILL.md · 活动预算与 ROI 测算:在活动策划与执行之间补上财务决策环——成本拆解、收益预估、ROI 测算、预算分配与止损线。当用户说「这个活动要花多少钱」「预算怎么分」「ROI 多少」「值不值得投」时使用。 产出:预算与 ROI…
git:20260922.f7c3e49 · audit A · 214 stars
activity-operations-execution SKILL.md skill
luyu2026/skill-bible · activity-operations/activity-operations-execution/SKILL.md · 活动执行落地:好方案执行烂 = 零。执行的核心是颗粒度:每个动作有 Owner、有时间、有交付物。 当用户说「execution」时使用。产出:执行计划(任务分解/排期/Owner/检查清单/值班表)。
git:20260916.f95ec8b · audit A · 214 stars
activity-operations-master SKILL.md skill
luyu2026/skill-bible · activity-operations/activity-operations-master/SKILL.md · 活动运营总控:判断用户此刻卡在活动运营的哪一环(目标设定/策划设计/执行落地/传播放大/复盘沉淀),路由到对应执行 Skill 或顾问团,并编排跨步骤链路。当用户说「做活动」「活动策划」「裂变活动」「活动没效果」时使用。
git:20260916.c7ec922 · audit A · 214 stars
activity-operations-mechanics SKILL.md skill
luyu2026/skill-bible · activity-operations/activity-operations-mechanics/SKILL.md · 活动机制设计:机制是活动的发动机:为什么用户愿意参与、愿意分享。机制设计对了,活动自己会转;错了,砸再多预算也没用。 当用户说「mechanics」时使用。产出:机制设计方案(目标行为/机制组合/激励结构/规则/风控)。
git:20260916.f95ec8b · audit A · 214 stars
activity-operations-method-growth-hacking SKILL.md skill
luyu2026/skill-bible · activity-operations/activity-operations-method-growth-hacking/SKILL.md · 《增长黑客》· 活动增长方法论:增长实验循环 + AARRR + 北极星指标 + ICE 排序,判断活动如何驱动增长、实验怎么设计。 产出:方法论判断框架。
git:20260916.f95ec8b · audit A · 214 stars
activity-operations-method-lean-analytics SKILL.md skill
luyu2026/skill-bible · activity-operations/activity-operations-method-lean-analytics/SKILL.md · 《精益数据分析》· 活动数据方法论:第一关键指标 + 增长引擎定位 + 数据诊断框架,判断活动指标怎么定、数据异常怎么归因。 产出:方法论判断框架。
git:20260916.f95ec8b · audit A · 214 stars
activity-operations-method-light-of-operations SKILL.md skill
luyu2026/skill-bible · activity-operations/activity-operations-method-light-of-operations/SKILL.md · 《运营之光》· 活动运营方法论:做局破局 + 四大运营思维 + 运营第一公式,判断活动值不值得办、如何设计价值匹配的活动局。 产出:方法论判断框架。
git:20260916.f95ec8b · audit A · 214 stars
activity-operations-planning SKILL.md skill
luyu2026/skill-bible · activity-operations/activity-operations-planning/SKILL.md · 活动策划与目标设定:活动不是「想个点子办一场」,而是先回答五个问题再动手。策划 = 目标 × 受众 × 玩法 × 预算 × 指标。 当用户说「planning」时使用。产出:活动策划案(目标/受众/玩法/预算/排期/风险/指标)。
git:20260916.f95ec8b · audit A · 214 stars

Every file in luyu2026/skill-bible

Browse by kind, by grade A, or by owner.