Not in the top 1,000 by GitHub stars
orange2ai/podcast-to-article
把多人对谈播客的逐字稿整理成可发布长文的 Agent Skill：换轴成文、人名校准、精简三分之一、去 AI 味自检。An agent skill that turns podcast transcripts into publishable articles.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
efc43919962e → efc43919962e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → efc43919962e
No earlier version was observed for comparison.
Heat
3.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
podcast-to-article
When your agent uses it
把多人对谈或单人访谈的播客逐字稿（字幕 / ASR 转写 / 妙记导出 / 英文播客）整理成能直接发的长文（实录体）。 流程是：清稿 → 要点梳理 → 定主线 → 换轴成文（用原文）→ 人名校准 → 精简 → 自检。 Use when: 用户给出播客逐字稿、字幕、SRT、录音转写，要求整理成文章、实录、公众号长文、 要点稿、长文；或说「播客转文章」「把录音变成文章」「这期整理成一篇」 「Next Token 那种格式」「对谈整理成文」「访谈转文章」。 podcast transcript to article, interview transcript to essay.
What it loads into context
Frontmatter
202 tokensAlways available to the agent
SKILL.md
4,708 tokensWhen the skill is activated
Reference documents
7,045 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 底线：事实优先于文采
- 为什么这件事难
- 交付物
- 流程
- 收尾
- 拍板权
- 参考
Scripts executed separately
scripts/check_style.pyscripts/prep_transcript.py
Files
.gitignoreasset75 bytesLICENSEasset1,074 bytesREADME.en.mddoc3,687 bytesREADME.mddoc5,531 bytesSKILL.mdcore16,908 bytesSKILL.mdcore16,908 bytesSKILL.mdcore16,908 bytesassets/cover.htmlasset7,594 bytesassets/cover.jpgasset531,193 bytesassets/cover.pngasset457,375 bytesreferences/example.mddoc11,110 bytesreferences/style-rules.mddoc4,841 bytesscripts/check_style.pyruns10,429 bytesscripts/prep_transcript.pyruns7,968 bytes
Read SKILL.md
# 播客转文章
逐字稿的轴是**发言人和时间**，文章的轴是**话题和判断**。这份 skill 做的就是换轴。
## 底线：事实优先于文采
改写的前提是事实。逐字稿里有的才写，逐字稿里没有的一个字都不加。三种「编」最常见：
- **添油加醋。** 他真说了那句话，就被写成「他说得很重」「他介绍产品时很坦白」。录音里没有音量标尺，也没有表情，你凭什么知道。
- **归纳成事实。** 把散在三处的说法攒成一句「他做的是四件事：邮件、日历、旅行、交易」，再挂上「他说」。他没这样数过，这就是幻觉。
- **替人表态。** 「他显然很想说下去」「他对此很谨慎」。这是你的判断，不是他的。
核实的动作很简单：写完挑几处关键句，回逐字稿里搜一遍。搜不到就改掉或者删掉。任何一句「这意味着」「这说明」，都要能在逐字稿里找到有人说过。
Skills included
- podcast-to-article
Repository facts
- License
- MIT
- Created
- Oct 7, 2026
- Last pushed
- Oct 8, 2026
- Forks
- 11
- Open issues
- 0
- Project activity
- Active
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 2 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 7 network referencesin 5 files: README.en.md:18 README.md:40 assets/cover.html:82 and 2 more
- No hidden or obfuscated text
- No instruction overrides
- 2 executable scriptsin 2 files: scripts/check_style.py:1 scripts/prep_transcript.py:1
- No access to secrets
- No requests to vote in Hot
Show all 9 signals by file
README.en.md
- Network accessline 18
git clone https://github.com/orange2ai/podcast-to-article.git - Network accessline 49
The language numbers come from [lieflat-less-ai-tone](https://github.com/larashero3-dotcom/lieflat-less-ai-tone) (MIT): 300 model-generated articles plus 329 human-written ones — 629 articles, 95,551 sentences, 45,721 paragraphs. Three of i
README.md
assets/cover.html
- Network accessline 82
<svg class="art" viewBox="0 0 1260 540" xmlns="http://www.w3.org/2000/svg"
references/style-rules.md
- Network accessline 7
出处：[lieflat-less-ai-tone](https://github.com/larashero3-dotcom/lieflat-less-ai-tone)（MIT）。语料是 300 篇五模型生成文本加 329 篇人类写作，95,551 句、45,721 段。人类侧语料没有公开，本机复算不了，所以下面的基准值按它 README 引用。
scripts/check_style.py
scripts/prep_transcript.py
- Executable scriptline 1
#!/usr/bin/env python3
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 8 facts
- Network access in code of documentationREADME.en.md:18Low confidence
- Network access in prose of documentationREADME.en.md:49Low confidence
- Network access in code of documentationREADME.md:40Low confidence
- Network access in prose of documentationREADME.md:81Low confidence
- Network access in prose of documentationreferences/style-rules.md:7Low confidence
- Executable script in code of a file that runsscripts/check_style.py:1High confidence
- Network access in prose of a file that runsscripts/check_style.py:4Low confidence
- Executable script in code of a file that runsscripts/prep_transcript.py:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
