Skill Content Postmortem logo

Skill Content Postmortem

OrganizationPopular
ZJU-REAL
skill-content-postmortem

内容复盘与爆款规律提炼。两种模式:(A) 单条复盘 — 分析一条已发布内容为什么爆/扑, 从 Hook、结构、选题、时间、平台适配等维度拆解原因;(B) 规律提炼 — 从多条内容中 提炼爆款共同特征、总结可复制的爆款公式。当用户说"这条为什么火了"、"为什么扑了"、 "复盘"、"分析数据"、"爆款规律"、"总结规律"、"爆款公式"、"内容复盘"、"什么规律"时触发。

Overview

PublisherZJU-REAL
RepositoryEasel
Skill nameskill-content-postmortem
Stars
1.2K
Forks
175
Bundled files
3
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ZJU-REAL on GitHub. Read the source before you install it.

Installation

Install the Skill Content Postmortem AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ZJU-REAL/Easel.git /tmp/Easel
mkdir -p .claude/skills
cp -r /tmp/Easel/skills/openclaw/skill-content-postmortem .claude/skills/skill-content-postmortem
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skill Content Postmortem in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Skill Content Postmortem on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Skill Content Postmortem is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

内容复盘与爆款规律提炼

拆解单条内容的成败原因,或从多条内容中提炼可复制的爆款公式。

输入

模式 A — 单条复盘

字段必填说明
内容原文或链接已发布的帖子全文(标题 + 正文 + 标签)
平台小红书 / 抖音 / 微博 / 知乎 / B站 / 公众号 / X 等
数据指标推荐阅读/播放、点赞、收藏、评论、转发、完播率等
发布时间推荐具体日期和时间
同期对照可选同账号近期其他帖子的平均数据,用于基线比较

模式 B — 规律提炼

字段必填说明
多条内容数据至少 5 条内容的标题、正文摘要、平台、核心指标
时间范围推荐数据覆盖的起止时间
筛选标准可选用户定义的"爆"与"扑"的阈值(如收藏 > 500 为爆)

若用户未提供数据指标,基于内容本身做定性分析,明确标注"无数据支撑,仅为结构性判断"。

输出

模式 A — 单条复盘报告

markdown
# 内容复盘:[标题摘要]

## 结论速览
- 判定:爆款 / 中等 / 扑街(附判定依据)
- 核心成因:一句话总结

## 多维拆解

### 1. Hook 分析
- 开头类型(提问 / 冲突 / 数字 / 故事 / 悬念)
- 前 3 秒 / 前 2 行吸引力评分(1-10)
- 改进建议

### 2. 内容结构
- 结构类型(总分总 / 递进 / 并列 / 故事弧)
- 信息密度与节奏
- 高光点与断裂点

### 3. 选题评估
- 选题热度(趋势型 / 常青型 / 冷门型)
- 受众痛点匹配度
- 差异化角度

### 4. 平台适配
- 是否符合平台内容偏好
- 格式适配(图文 / 视频 / 长度 / 标签策略)
- 分发机制利用程度

### 5. 时间与节奏
- 发布时间是否为活跃时段
- 是否踩中热点窗口
- 互动节奏(评论区运营)

### 6. 视觉 / 封面(如适用)
- 封面吸引力
- 视觉风格与平台调性匹配

## 改进处方
- 3 条具体可执行的优化建议(按优先级排序)

## 数据备注
- 数据来源与置信度说明

维度评分标尺

references/postmortem-dimensions.md 提供 Hook力 / 内容结构 / 信息密度 / 互动引导 / 视觉排版 / 平台适配 六维的 1-10 打分标尺;选题、时间节奏为定性分析维度(不打分)。

分数含义
1-3该维度存在明显问题,是拖累整体表现的短板
4-6及格水平,无明显硬伤但缺乏亮点
7-8优于同类内容平均水平,有可复用的做法
9-10该维度是本条内容的核心竞争力

模式 B — 规律提炼报告

markdown
# 爆款规律提炼:[账号/主题]

## 数据概览
- 分析范围:X 条内容,时间 Y-Z
- 爆款标准:[用户定义或系统推断的阈值]
- 爆款率:X%

## 爆款共同特征
| 维度 | 爆款共性 | 扑街共性 | 差异显著性 |
|------|----------|----------|------------|
| Hook 类型 | | | |
| 选题方向 | | | |
| 内容结构 | | | |
| 发布时间 | | | |
| 内容长度 | | | |
| 标签策略 | | | |
| 视觉风格 | | | |

## 爆款公式
- 公式 1:[选题类型] + [Hook 模式] + [结构] = 高概率爆款
- 公式 2:...
- 反面公式:[避免的组合]

## 可复制行动清单
1. 下一条内容立即可用的 3 个策略
2. 中期优化方向(1-2 周内调整)

## 数据局限
- 样本量、数据完整性、平台算法变化等局限说明

爆款公式模板

[标题公式] 情绪词 + 数字 + 悬念/反差 [结构公式] Hook(前3秒) → 痛点共鸣 → 解决方案 → 行动号召 [选题公式] 热点事件 × 垂直领域 × 反常识角度

每个拆解输出:

  • 公式名称(≤8字,便于复用)
  • 公式结构(用 → 连接各环节)
  • 可迁移条件(什么类型的内容可以套用)
  • 套用示例(用创作者自己的领域举一个例子)

执行步骤

模式 A — 单条复盘

  1. 确认模式:根据用户输入判断是单条复盘还是规律提炼。若用户只提供一条内容,进入模式 A。
  2. 采集上下文:确认平台、发布时间、数据指标。缺失数据主动询问一次,用户不补充则继续。
  3. 基线建立:若有同期对照数据,计算偏离度;若无,使用平台通用基线(参考 references/ 中的平台特征数据)。
  4. 多维拆解:可打分维度(Hook力/内容结构/信息密度/互动引导/视觉排版/平台适配)用 references/postmortem-dimensions.md 的 1-10 标尺;选题、时间节奏做定性判断。每个维度给出判断和证据。
  5. 归因排序:识别最关键的 1-2 个成败因素,区分"内容因素"和"运气因素"(如平台推荐、热点窗口)。
  6. 生成处方:输出 3 条具体、可执行、有优先级的改进建议。
  7. 输出报告:按输出模板生成完整报告,保存到 outputs/

模式 B — 规律提炼

聚合统计交给脚本,LLM 只做规律提炼。 阈值划分 top20%、爆款组 vs 普通组分组对比、多维交叉、标签共现全部由 scripts/aggregate.py 完成(复用 ../../shared/scripts/social_stats.pyengagement_score/engagement_rate/cooccurrence/pct_change/sample_warning)。

  1. 数据摄入:接收多条内容数据,标准化为统一 JSON 数组(每条含标题、平台、数值指标 likes/collects/comments/shares/views,及维度字段 hook_type/topic/structure/length_bucket/time_bucket/tags 等),写入临时文件。
  2. 调用脚本聚合
    bash
    python3 skills/openclaw/skill-content-postmortem/scripts/aggregate.py --input contents.json
    python3 skills/openclaw/skill-content-postmortem/scripts/aggregate.py --input contents.json \
      --metric collects --threshold 500 --cross "hook_type,topic"  # 指定排名字段/绝对阈值/两维交叉
    脚本自动完成:阈值划分(--threshold 优先,否则 --top-pct 百分位)、爆款组/普通组分组对比(每维度 count/top_count/top_rate_pct/avg_score/lift_vs_global)、两维交叉、标签共现、样本量警告。
  3. 模式识别 + 公式生成(LLM 解读):从 by_dimension/cross 读出爆款组高频、高 lift 的取值组合,总结为可复制的"爆款公式"(选题 + Hook + 结构)。
  4. 反面总结 + 行动清单(LLM 解读):从低 top_rate / 负 lift 取值总结"避坑清单",输出分层建议(立即可用 / 中期调整),转达脚本样本量 warning
  5. 输出报告:按模板生成,保存到 outputs/

Profile 感知

有 Profile 时:

  • 读取 identity.md(账号定位、内容风格、赛道信息)
  • 读取 audience.md(目标受众画像、痛点偏好)
  • 读取 platforms.md(各平台运营策略与历史表现)
  • 复盘时结合账号定位判断选题适配度("这个选题对你的受众来说太泛了")
  • 规律提炼时按账号阶段给出针对性建议(冷启动期 vs 增长期 vs 变现期)
  • 对照 Profile 中的"表现好的内容"做历史比较

无 Profile 时:

  • 退到通用模式,基于平台通用规律分析
  • 不做账号定位相关的适配度判断
  • 提示用户补充 Profile(identity.md / audience.md / platforms.md)可获得更精准复盘

自研溯源与参考项目见同目录 EASEL-META.md

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Skill Content Postmortem AI skill do?

内容复盘与爆款规律提炼。两种模式:(A) 单条复盘 — 分析一条已发布内容为什么爆/扑, 从 Hook、结构、选题、时间、平台适配等维度拆解原因;(B) 规律提炼 — 从多条内容中 提炼爆款共同特征、总结可复制的爆款公式。当用户说"这条为什么火了"、"为什么扑了"、 "复盘"、"分析数据"、"爆款规律"、"总结规律"、"爆款公式"、"内容复盘"、"什么规律"时触发。

Why use Skill Content Postmortem on TypingMind?

Because you install it once and use it with any model. Skill Content Postmortem is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Skill Content Postmortem in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/skill-content-postmortem. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Skill Content Postmortem?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Skill Content Postmortem?

As many as you like. As long as a model supports skills, you can use Skill Content Postmortem with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Skill Content Postmortem AI skill free?

Yes. It is published on GitHub by ZJU-REAL under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇