dbs-content-system

Content

dontbesilent2025/dbskillskills.sh ↗

Installs

15,348

deduplicated, at the last sync

Since we started

+5.3%

40 readings, about 2 hours apart. Not a live curve.

Our category

Content

ours

Last read

Sep 3, 2026

from the directory

Our brief

ours

This skill functions as a comprehensive content structuring system, designed to transform large volumes of disparate local content assets—such as drafts, posts, and case studies—into a reusable, traceable, and continuously growing content engineering framework. It does not merely summarize or polish individual pieces but instead builds an entire operational system for managing structured content.

What it produces
  • Structured content asset repository
  • Content unit draft files (QST, CON, OPI, CAS, SOL)
  • Theme maps and assembled topic drafts
  • Source registry and processing ledger
What it needs
  • Local content directory with sufficient assets
Paid services

not detected

The evidence does not contain any information regarding paid services, APIs, or required credentials.

Registration

not detected

The evidence does not mention any registration requirements for using the skill.

Limits and human review

It cannot perform light organization of small amounts of material or polish single drafts. It also requires sufficient content volume (at least 50 files or 80,000 characters) and clear boundaries to initiate a full engineering process.

Evidenceskills/dbs-content-system/SKILL.md:1-545
skills/dbs-content-system/SKILL.md1–545
---
name: dbs-content-system
description: 把本地文稿、推文、选题、案例和课程稿整理成可持续生长、可重组复用的内容工程。用户要求结构化内容资产、整理旧素材或建立主题地图时使用。
---

# dbs-content-system:内容结构化系统

你是 dontbesilent 的内容结构化系统搭建 AI。你的任务不是整理几篇文案,也不是给用户提几条内容建议。你的任务是:当用户本地已经有足够多的内容资产时,把这些素材搭成一个可持续生长的本地内容工程。

**你交付的不是一份总结,而是一套能继续运转的系统。**

**本 skill 必须自包含。不要假设用户安装后还能读取仓库里的知识包、参考文档或额外支持文件。只要拿到这一个 `SKILL.md`,也必须能完整执行。**

**本 skill 不是轻量 prompt,而是单目录重型 skill。`SKILL.md`、脚手架、模板、脚本、文档都固定留在 `skills/dbs-content-system/` 目录内部,不依赖共享目录。**

---

## 一句话定义

`dbs-content-system` 解决的是:

**如何把本地大量内容资产,从“堆在很多文件夹里的库存”,变成“可复用、可追溯、可重组、可继续生长的内容结构化工程”。**

它处理的是:

- 大量文稿
- 推文与帖子
- 公众号文章
- 选题草稿
- 案例素材
- 课程稿
- 录音转写
- 历史爆款内容

它不处理的是:

- 单篇文案润色
- 标题优化
- 短视频开头优化
- 少量零散素材的轻量整理
- 没有内容积累时的空转搭系统

---

## 核心边界

### 原则 1:先审计,再建工程

不要一上来就新建目录、复制全部素材、开始抽取。

先判断两件事:

1. 用户本地内容量够不够
2. 用户要处理的内容边界清不清楚

如果内容量不够,或者边界没定清,直接指出,不进入重工程。

### 原则 2:默认目标不是“全量处理完”,而是“系统能用了”

大多数用户第一次做这种工程,不需要一口气把所有内容结构化完。

默认目标是把系统推进到可用态:

- 工程骨架完整
- 规则层完整
- 状态层完整
- 原始素材副本已建立
- 首批内容单元已抽取
- 主题地图和装配稿已出现
- 关系与去重索引已跑通

做到这里,系统就已经可以继续长。

### 原则 2.5:结构先于规模

内容结构化工程的第一任务,不是尽快把所有文稿都抽完,而是先验证结构。

如果内容单元边界、关系方向、去重规则、来源登记规则还没稳定,就直接全量推进,只会大规模制造后续返工。

所以这个 skill 必须按模式逐档升级,而不是假装自己一开始就适合全量跑库。

### 原则 3:原始素材不改写,只复制副本

原目录里的原文件不

Read 1 of 1 text files in the skill.

Checked August 2026 · GemmaWritten from the skill's published files. Check the source before relying on access or cost details.

Installfrom the directory

npx skills add https://github.com/dontbesilent2025/dbskill

Installing happens there, not here. We are an index with an opinion, not a mirror.

What is inside itfrom the directory

agents/openai.yaml
docs/acceptance.md
docs/quickstart.md
scaffold/root/AGENTS.md
scaffold/root/CLAUDE.md
scaffold/root/README.md
scaffold/root/SOURCE_OF_TRUTH.md
scaffold/rules/内容单元关系规则.md
scaffold/rules/内容单元去重与版本规则.md
scaffold/rules/内容单元字段规范.md
scaffold/rules/处理流程.md
scaffold/rules/新增文稿进入系统流程.md
scaffold/rules/来源命名规范.md
SKILL.md
templates/主题地图模板.md
templates/方案单元模板.md
templates/案例单元模板.md
templates/概念单元模板.md
templates/观点单元模板.md
templates/选题装配模板.md
templates/问题单元模板.md
tools/assemble-topic-from-units.js
tools/extract-sample-units.js
tools/fill-obsidian-links.js
tools/generate-duplicate-candidates.js
tools/generate-link-map.js
tools/generate-source-registry.js
tools/generate-unit-draft.js
tools/init-content-system.js
tools/rebuild-processing-ledger.js
tools/summarize-system.js

31 files — names only. The directory does not report sizes.

What the auditors foundfrom the directory

A skill is instructions your agent will follow and scripts it may run, so who checked it matters as much as how many people installed it.

Gen Agent Trust HubThe skill is a comprehensive local content management tool designed to structure drafts and assets into a reusable content project. It operates entirely within the local file system using Node.js scripts for file processing, metadata extraction, and indexing, with no network activity or external dependencies detected.Aug 11, 2026 · SAFEpass
SocketNo alertsAug 11, 2026pass
SnykRisk: MEDIUM · 1 issueAug 11, 2026 · MEDIUMwarn

Installs, reading by readingours

14.7k
15.3k
Aug 31, 202640 readings over 4 days, drawn as the last reading of each day.Sep 3, 2026

Axis starts at 14.7k, not zero — the range is 14.7k to 15.3k.

Filed alongside itours