cyxj-transcript

cyxj-transcript is a skill for Claude Code, Codex from chenyuxiaojin/xiaochen-skills. It costs 119 tokens per session (1,301 once invoked), scanned A, original, MIT.

A workflow that turns a video or audio transcript into a structured article draft in Obsidian Markdown.

In plain words
What is it for?
It creates headings, rewrites conversational speech, puts data into tables, and prepares a draft for later blog or WeChat formatting.
Why use it?
It removes spoken-language clutter and organizes the material without losing the original transcript for reference.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit It creates headings, rewrites conversational speech, puts data into tables, and prepares a draft for later blog or WeChat formatting.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chenyuxiaojin/xiaochen-skills/cyxj-transcript
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add chenyuxiaojin/xiaochen-skills --skill cyxj-transcript
Clone the repo
git clone --depth 1 https://github.com/chenyuxiaojin/xiaochen-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin cyxj-transcript/plugin install cyxj-transcript after adding the marketplace above.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cyxj-transcript

README.md
[![agentmods](https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-transcript/github.svg)](https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-transcript)
Your own site
<a href="https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-transcript"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-transcript/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cyxj-transcript

Your own site · 80×15
<a href="https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-transcript"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-transcript.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,301 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00119 $0.01301
Opus 5 $0.00060 $0.00651
Sonnet 5 $0.00024 $0.00260
Haiku 4.5 $0.00012 $0.00130

Measured 9d ago against content hash 9c1109f6e70b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cyxj-transcript scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/cyxj-transcript/skills/cyxj-transcript/SKILL.md · 90 lines

What it actually says

cyxj-transcript — 逐字稿转文章

把第一手逐字稿(视频口播、录音转写、直播逐字)整理成能读的文章草稿。 这是上游:产出干净的文章 Markdown,下游再交给排版 skill。

何时用

  • 用户给一段逐字稿/口播稿,说「整理成文章」「转个稿」
  • 素材通常在 $CYXJ_VAULT_BASE/待发布/(未设置 CYXJ_VAULT_BASE 时按 ~/obsidian/灵感库 兜底,并向用户确认),找不到就问用户路径

不适用:已经是成文文章(直接走排版 skill);纯做选题/大纲(走选题 skill)。

转稿规则(硬约束,来自内容创作 CLAUDE.md「转稿规则」;规则已完整内联,无需读原文件)

  1. 逐字稿是第一手素材,优先级高于大纲和录制手册——以实际说出来的内容为准。
  2. 去口语化:删掉视频专属表达——「我们来看一下」「对吧」「这个」「然后呢」「接下来」「那么」等口头禅、语气词、重复啰嗦。
  3. 加结构:用小标题分段;数据/对比/参数用表格整理,不要堆在正文里。
  4. 保留原稿:原始逐字稿原样放到文末「## 原始逐字稿(备查)」段落,不删。
  5. 不抖机灵:按「事实→机制→洞察」三段推进,数字给精度,不做段子手式抒情(用户写作偏好)。
  6. 避开「不是…而是…」对照式句式(用户明确不喜欢)。

改写示例(尺度参考)

Before(口播原文)

我们来看一下这个数据啊,就是说 Claude 它这个月的下载量呢,是涨了差不多三倍,对吧,这个增速其实是很吓人的,然后呢它的付费用户也在涨。

After(成文)

Claude 本月下载量增长约 3 倍,付费用户同步上涨。这个增速很吓人。

去掉「我们来看一下」「就是说」「对吧」「然后呢」等口水,但「这个增速很吓人」这类有态度的金句原样保留。

工作流

  1. 拿到逐字稿:Read 路径,或用 obsidian CLI 在 $CYXJ_VAULT_BASE/待发布/ 搜(CLI 不存在则用 Grep/Glob 直接搜文件)。
  2. 通读定主线:先判断这篇在讲什么、核心论点是什么、有哪些可成段的部分。
  3. 起草
    • 拟一个说人话的标题(讲中心思想,不堆符号)
    • 按主题切小标题,去口语化重写每段
    • 把散落的数字/步骤/对比抽成表格
    • 保留作者原话里有信息量的金句,删无信息量的口水
  4. 附原稿:文末加 ## 原始逐字稿(备查) + 原文。
  5. 存稿:默认写回 $CYXJ_VAULT_BASE/待发布/<标题>.md(Obsidian),动手前确认文件名和落点。
  6. 交接:告诉用户「草稿好了,要发公众号就 /cyxj-wechat-pub,发博客就 /cyxj-blog-pub」。

产出结构(模板)

# <说人话的标题>

<导语:一两句说清这篇讲什么、为什么值得看>

## <小标题 1>
<去口语化的正文>

| <表头> | <表头> |
|--------|--------|
| ...    | ...    |

## <小标题 2>
...

---

## 原始逐字稿(备查)

<原文逐字稿,原样保留>

错误分支

  • 输入是 SRT 文件 → 提示改用 cyxj-subfix 的 --export-md 先转成纯文本再来。
  • 逐字稿超过约 1 万字 → 分段处理再合并,不要一次吞。
  • 目标文件已存在 → 停下向用户确认是否覆盖。

收尾

  • 不臆造逐字稿里没有的事实/数字。原稿没说的不补。
  • 拿不准的事实,提示用户「这条建议发稿前用 fact-checker 核一下」。
  • 只产出草稿,不做排版、不发布——那是下游 skill 的事:发公众号走 cyxj-wechat-pub,发博客走 cyxj-blog-pub。产出草稿后用一句话提示用户这两个去向。
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 90 lines · 119 tokens per session scan A 9c1109f6e70b

Subscribe to this mod's changes

cyxj-transcript is a skill published in the GitHub repository chenyuxiaojin/xiaochen-skills (6 stars, last pushed 5d ago), licensed MIT. It adds 119 tokens to every session and 1,301 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.