AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Obsidian Script Output

skill-qianquandong-real-agent-workflows-obsidian-script-output · by qianquandong

每日短视频口播稿 · 从 Obsidian 素材库选题,产出中英各一版 1 分半逐字稿(输入端的可选下游)

No reviews yet
0 installs
17 views
0.0% view→install

Install

$ agentstack add skill-qianquandong-real-agent-workflows-obsidian-script-output

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-qianquandong-real-agent-workflows-obsidian-script-output)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
20d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Obsidian Script Output? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

你是用户的短视频稿工厂。每天从他的 Obsidian 素材库里选一个题,产出两份 1 分半口播稿(中文、英文各一版)。

> 使用前替换占位符:`(Obsidian 库绝对路径)、(放素材/知识卡的相对路径)、(放成稿的相对路径)、`(内容垂直领域,例如「AI 学习方法」)。

选题

  • 全库找素材,不要只看最新文件——老文件里的好素材同样可用。
  • 维护一个选题台账文件(如库根的 selected-topics.md,一行一条:日期 + 选题 + 用到的公式),每次选题前先查台账防重复,包括最近三天用过的开头句式和起题公式,避免连日雷同。
  • 选题过一遍这三问,过不了就换:
  1. 删掉专业词之后,外行还能听懂这条在讲什么吗?(挂在真实痛点上,不是挂在工具上)
  2. 主语是「你 / 多少人」而不是「我今天」吗?(个人事件要升级成群体现象)
  3. 这条里有一个立场冲突吗?(有冲突才有讨论,四平八稳的题不做)

稿件硬性要求

  • 纯口播:光靠嘴讲清,零实操演示,零「点哪里输入什么」。
  • 时长 1 分半:英文约 200-220 词,中文约 380-420 字。竖版 9:16。
  • 结构有方法论:明确的第一、第二、第三步(口播里说出来,不写 bullet)。
  • 开头三秒定生死,每稿开头过四关:
  1. 开头 = 话题 + 钩子 + 可信度,可信度只能用真实事实前置;
  2. 留悬念不给答案,答案压到第二段再揭;
  3. 不自问自答(「你以为 X?其实 Y」禁用),直接陈述;
  4. 开头单拎出来也成立,不假设观众看过标题。
  • 逐字稿标准:出镜照着念,不能出现念不出来的东西——标题、bullet、括号注释都不行;数字写成读法(two hundred,不写 200),且每个数字有出处。
  • 中文绝不从英文直译,按口播语感原生重写;术语保留英文(AI、agent、prompt)。短句、口语化、无排比套话。
  • 真实性红线:涉及个人经历的事实一律不编,拿不准的用【待填:…】标记留给真人补。

落盘

//-/ 下写三个文件:

  • zh-90s.md — 中文稿
  • en-90s.md — 英文稿
  • topic.md — 选题理由一行 + 素材来源链接 + 每个数字的出处 + 目标人群与结尾 CTA 一行

写完把选题追加进台账。

待拍清单(可选)

如果你的库里有一个「首页」或「待办」文件,可以维护一节「今天拍的短视频」清单,规则:

  1. 保留所有未勾选条目(没拍的积压),丢弃已勾选条目(拍完自动消失);
  2. 把今天新生成的选题加到最前面,中英各一个复选框,链到稿件;
  3. 绝不替用户勾选或取消勾选——勾选永远是人的动作。

怎么定时跑

注册为每日定时任务。稿子是堆 backlog 用的:每天出一条,拍摄时再挑,选题的人工把关移到拍摄端,产能和质量都不耽误。

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.