File contents content-factory
内容工厂——从热点池批量筛选评分选题,生成内容选题卡片并推送
使用场景
每日内容选题自动筛选(从 10+ 平台热点池中 AI 评分 Top 10)
选题卡片格式化推送到 Telegram
内容管线核心组件,衔接 content-source-aggregator(上游采集)和内容创作(下游)
使用方法
# 评分今天的热点池(默认 Top 10)
python ~/clawd/skills/content-factory/scripts/topic_scorer.py
# 指定日期 / 数量
python topic_scorer.py --date 2026-03-22 --top 5
# 不推送,只输出
python topic_scorer.py --no-send
# Dry run(不调 LLM,用随机分测试)
python topic_scorer.py --dry-run
# 只评分前 N 条热点
python topic_scorer.py --limit 20
# 推送已评分的选题到 Telegram
python ~/clawd/skills/content-factory/scripts/topic_presenter.py --date 2026-03-22 --top 5
python topic_presenter.py --dry-run
评分维度(权重可配)
维度
权重
说明
heat
0.35
热度和讨论量
timeliness
0.25
话题新鲜度
creativity
0.40
创作空间(纯新闻搬运低分)
配置要求
Python 3.10+, httpx
LLM API(DeepSeek 或 ZAI,通过 pass show api/deepseek 配置)
~/clawd/scripts/newsbot_send.py(推送依赖)
热点池目录:~/clawd/workspace/content-pipeline/hotpool/
选题输出目录:~/clawd/workspace/content-pipeline/topics/
相关文件
scripts/topic_scorer.py — 核心评分脚本
scripts/topic_presenter.py — 选题格式化与推送
scripts/aggregator/ — 内容聚合子模块
data/topics/ — 历史评分数据
data/hotpool/ — 历史热点池快照
1 --- 2 name: content-factory 3 description: content-factory 4 --- 5 # content-factory 6 > 内容工厂——从热点池批量筛选评分选题,生成内容选题卡片并推送 7 8 ## 使用场景 9 - 每日内容选题自动筛选(从 10+ 平台热点池中 AI 评分 Top 10) 10 - 选题卡片格式化推送到 Telegram 11 - 内容管线核心组件,衔接 content-source-aggregator(上游采集)和内容创作(下游) 12 13 ## 使用方法 14 ```bash 15 # 评分今天的热点池(默认 Top 10) 16 python ~/clawd/skills/content-factory/scripts/topic_scorer.py 17 18 # 指定日期 / 数量 19 python topic_scorer.py --date 2026-03-22 --top 5 20 21 # 不推送,只输出 22 python topic_scorer.py --no-send 23 24 # Dry run(不调 LLM,用随机分测试) 25 python topic_scorer.py --dry-run 26 27 # 只评分前 N 条热点 28 python topic_scorer.py --limit 20 29 30 # 推送已评分的选题到 Telegram 31 python ~/clawd/skills/content-factory/scripts/topic_presenter.py --date 2026-03-22 --top 5 32 python topic_presenter.py --dry-run 33 ``` 34 35 ## 评分维度(权重可配) 36 | 维度 | 权重 | 说明 | 37 |------|------|------| 38 | heat | 0.35 | 热度和讨论量 | 39 | timeliness | 0.25 | 话题新鲜度 | 40 | creativity | 0.40 | 创作空间(纯新闻搬运低分) | 41 42 ## 配置要求 43 - Python 3.10+, httpx 44 - LLM API(DeepSeek 或 ZAI,通过 `pass show api/deepseek` 配置) 45 - `~/clawd/scripts/newsbot_send.py`(推送依赖) 46 - 热点池目录:`~/clawd/workspace/content-pipeline/hotpool/` 47 - 选题输出目录:`~/clawd/workspace/content-pipeline/topics/` 48 49 ## 相关文件 50 - `scripts/topic_scorer.py` — 核心评分脚本 51 - `scripts/topic_presenter.py` — 选题格式化与推送 52 - `scripts/aggregator/` — 内容聚合子模块 53 - `data/topics/` — 历史评分数据 54 - `data/hotpool/` — 历史热点池快照
aAAaqwq/AGI-Super-Skills/tree/main/skills/content-factory commit b7b0791de0
Frequently asked questions How do I install the Content Factory skill? Run npx skillmds@latest add aaaaqwq/content-factory in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
What does the Content Factory skill do? content-factory It is listed under Coding & Dev Tools on SkillMD.
Is Content Factory safe to use? This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
Which AI agents work with Content Factory? This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Is Content Factory free to use? Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
Who published Content Factory? aAAaqwq (@aaaaqwq) published this skill. Their other Agent Skills are listed on their SkillMD profile.