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.
npx skills add chenyuxiaojin/xiaochen-skills --skill cyxj-transcriptgit clone --depth 1 https://github.com/chenyuxiaojin/xiaochen-skillsWrote 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.
[](https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-transcript)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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)
- 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。
- 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。
- 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。
- 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。
- 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)。
- 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
- 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)。 - 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。
- 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
- 附原稿:文末加
## 原始逐字稿(备查)+ 原文。 - 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。 - 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。
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.
- 9d ago First seen · 90 lines · 119 tokens per session scan A 9c1109f6e70b
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.
Other skills, from other repositories
import
Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.
document
Generate minimal documentation through parallel agents.
prd-gen
A guide for turning a feature idea into a product requirements document (PRD), a structured plan that explains what to build and how success will be judged.
clarify-requirements
A requirements-clarification workflow used before creating a PRD, a product requirements document that describes what should be built.
full-pm-cycle
A product-management workflow covering the path from market and user research through product strategy, requirements, prototype design, release planning, and post-launch review. It uses defined stages and checkpoints, and can produce HTML prototypes.
market-research
A research skill for understanding markets and users. It can study market trends, market size, competitors, and opportunities, or help design interviews, surveys, and user profiles.