Menu

Not in the top 1,000 by GitHub stars

LeoLin990405/oral-interview-transcription-skill

A methodology-grounded pipeline that de-oralizes verbatim oral-history and podcast interview transcripts into faithful, reviewable Pass 1 drafts. · 方法论驱动的口述史 / 播客访谈逐字稿去口语化流水线，产出忠实、可复核的 Pass 1 整理稿。

Research

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

oral-history-master/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

92a9ac205f63 → 92a9ac205f63

Compare on GitHub

oral-history-quality-guard/SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

92a9ac205f63 → 92a9ac205f63

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 92a9ac205f63a7f90a692b6cba26c111d3f95b8a

19GitHub stars
2stars in 7 days
2skills in this repository
2commits in 30 days

Heat

3.3
  • 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

Oct 25, 2026Nov 4, 202619

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

oral-history-master

When your agent uses it

口述史 / 播客 / 通用访谈「整理稿」生成系统（Pass 1 去口语化）。将录音转写稿通过 「方针师→整理者→质量门」多角色协作，按存真优先原则转换为忠实、可读的整理稿， 并配套逐段字级审阅包（对照稿 / HTML / Word 修订）。专为长文设计：分块 + 术语锚定 + 跨块一致性。搭配 companion skill `oral-history-quality-guard` 做交付前忠实度审计。 触发词：口述史整理、播客转文字、转写稿去口语化、整理访谈记录、口述文本处理、 oral history、podcast transcript、整理稿、"按口述史要求处理录音转文字"。 书面化（Pass 2）见 workflows/pass2-bookify.md。

What it loads into context

Frontmatter

223 tokens

Always available to the agent

SKILL.md

3,118 tokens

When the skill is activated

Reference documents

21,055 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. 主流水线脚本
  2. 参考与模板索引
  3. 独立工作流
  4. 流程
  5. 角色切换协议
  6. Notes

Scripts executed separately

  • scripts/chunker.py
  • scripts/config.py
  • scripts/consistency_checker.py
  • scripts/diff_reporter.py
  • scripts/fidelity_checker.py
  • scripts/filler_scan.py
  • scripts/glossary_extractor.py
  • scripts/package_review.py
  • scripts/project_manager.py
  • scripts/report.py
  • scripts/review_diff.py
  • scripts/run_pipeline.py
  • scripts/transcript_ingest.py
  • tests/test_pipeline.py

Files

  • SKILL.mdcore10,064 bytes
  • SKILL.mdcore10,064 bytes
  • SKILL.mdcore10,064 bytes
  • SKILL.mdcore10,064 bytes
  • SKILL.mdcore10,064 bytes
  • SKILL.mdcore10,064 bytes
  • SKILL.mdcore10,064 bytes
  • SKILL.mdcore10,064 bytes
  • SKILL.mdcore10,064 bytes
  • SKILL.mdcore10,064 bytes
  • SKILL.mdcore10,064 bytes
  • projects/demo/edit_spec.mddoc1,764 bytes
  • projects/demo/output/整理稿.mddoc1,153 bytes
  • projects/demo/review/一致性报告.mddoc282 bytes
  • projects/demo/review/审阅稿.docxasset3,660 bytes
  • projects/demo/review/审阅稿.htmlasset12,267 bytes
  • projects/demo/review/对照稿.mddoc6,148 bytes
  • projects/demo/review/待核对清单.mddoc385 bytes
  • projects/demo/review/忠实度报告.mddoc550 bytes
  • projects/demo/review/语气词残留.mddoc406 bytes
  • projects/demo/review/质检总览.mddoc964 bytes
  • projects/demo/sources/ingested.mddoc1,528 bytes
  • projects/demo/sources/raw.txtdoc1,328 bytes
  • projects/demo/term_lock.mddoc1,623 bytes
  • projects/demo/work/chunks/chunk_001.mddoc470 bytes
  • projects/demo/work/chunks/chunk_002.mddoc852 bytes
  • projects/demo/work/chunks/chunk_003.mddoc729 bytes
  • projects/demo/work/edited/chunk_001.edited.mddoc319 bytes
  • projects/demo/work/edited/chunk_002.edited.mddoc618 bytes
  • projects/demo/work/edited/chunk_003.edited.mddoc396 bytes
  • projects/demo/work/glossary_candidates.jsonasset565 bytes
  • projects/demo/work/manifest.jsonasset471 bytes
  • projects/demo/work/term_table_draft.mddoc388 bytes
  • references/editor.mddoc4,040 bytes
  • references/examples.mddoc10,886 bytes
  • references/methodology.mddoc8,621 bytes
  • references/shared-standards.mddoc3,867 bytes
  • references/surveyor.mddoc3,636 bytes
  • requirements.txtdoc435 bytes
  • scripts/README.mddoc4,279 bytes
  • scripts/chunker.pyruns4,666 bytes
  • scripts/config.pyruns10,868 bytes
  • scripts/consistency_checker.pyruns3,800 bytes
  • scripts/diff_reporter.pyruns1,159 bytes
  • scripts/fidelity_checker.pyruns5,927 bytes
  • scripts/filler_scan.pyruns5,009 bytes
  • scripts/glossary_extractor.pyruns5,277 bytes
  • scripts/package_review.pyruns4,328 bytes
  • scripts/project_manager.pyruns6,532 bytes
  • scripts/report.pyruns4,396 bytes
  • scripts/review_diff.pyruns24,285 bytes
  • scripts/run_pipeline.pyruns2,557 bytes
  • scripts/transcript_ingest.pyruns7,356 bytes
  • templates/edit_spec_reference.mddoc3,105 bytes
  • templates/term_lock_reference.mddoc2,345 bytes
  • tests/test_pipeline.pyruns11,792 bytes
  • workflows/pass2-bookify.mddoc6,219 bytes
  • workflows/resume-execute.mddoc2,064 bytes
Read SKILL.md

# Oral History Master

> 录音转写稿 → 忠实整理稿（Pass 1）。多角色串行流水线 + 确定性脚本 + 机读执行契约。
> **存真 > 可读。** 口述史里录音才是史料；播客同样禁止添写与抹平矛盾。整理稿是最小干预转写。

**核心流水线**：`转写稿 → 归一(Ingest) → 建项目+专名预扫 → ⛔方针师(Surveyor) → 分块 → 整理者(Editor) → 一致性/忠实度门 → 复核包 → 质量门(QA) → 交付(签字)`

> [!CAUTION]
> ## 🚨 全局执行纪律（强制 · 最高优先级）
>
> **本流程是严格串行流水线。违反以下任一条即视为执行失败：**
>
> 1. **串行执行** — 步骤必须按序进行，上一步产物是下一步输入。非 BLOCKING 的相邻步骤在前置满足后可连续推进，无需用户说"继续"。
> 2. **BLOCKING = 硬停** — 标 ⛔ 的步骤必须完全停下，等用户明确回应才继续，**不得替用户做决定**。唯一 BLOCKING 点是 Step 2 方针师的"整理方针确认"。
View the complete source on GitHub

Skills included

  • oral-history-master
  • oral-history-quality-guard

Repository facts

License
MIT
Created
Jun 13, 2026
Last pushed
Nov 4, 2026
Forks
0
Open issues
0
Project activity
Active

Before you install

Local scripts

Automated 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 13 notes
  • oral-history-master/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • oral-history-master/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • oral-history-master/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • oral-history-master/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • oral-history-master/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • oral-history-master/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • oral-history-master/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • oral-history-master/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • oral-history-master/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • oral-history-master/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • oral-history-master/projects/demo/review/审阅稿.html:103 Analysis incomplete: physical or joined line exceeds character limit
  • oral-history-master/projects/demo/review/审阅稿.html:101 Analysis incomplete: physical or joined line exceeds character limit
  • oral-history-master/projects/demo/review/审阅稿.html:102 Analysis incomplete: physical or joined line exceeds character limit
Show all 35 signals by file

oral-history-master/scripts/chunker.py

  • Executable scriptline 1
    #!/usr/bin/env python3

oral-history-master/scripts/config.py

  • Executable scriptline 1
    Executable file

oral-history-master/scripts/consistency_checker.py

  • Executable scriptline 1
    #!/usr/bin/env python3

oral-history-master/scripts/diff_reporter.py

  • Executable scriptline 1
    #!/usr/bin/env python3

oral-history-master/scripts/fidelity_checker.py

  • Executable scriptline 1
    #!/usr/bin/env python3

oral-history-master/scripts/filler_scan.py

  • Executable scriptline 1
    #!/usr/bin/env python3

oral-history-master/scripts/glossary_extractor.py

  • Executable scriptline 1
    #!/usr/bin/env python3

oral-history-master/scripts/package_review.py

  • Executable scriptline 1
    #!/usr/bin/env python3

oral-history-master/scripts/project_manager.py

  • Executable scriptline 1
    #!/usr/bin/env python3

oral-history-master/scripts/report.py

  • Executable scriptline 1
    #!/usr/bin/env python3

oral-history-master/scripts/review_diff.py

  • Executable scriptline 1
    Executable file
  • Network accessline 494
    document = (         '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'         '<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'
  • Network accessline 495
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'         '<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'         f'<w:body>{"".join(paras)}<w:sectPr/></w:body></w:document>'
  • Network accessline 496
    '<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'
  • Network accessline 499
    styles = (         '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'         '<w:styles xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'
  • Network accessline 500
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'         '<w:styles xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'         '<w:style w:type="paragraph" w:default="1" w:styleId="Normal">'
  • Network accessline 501
    '<w:styles xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'
  • Network accessline 515
    settings = (         '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'         '<w:settings xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'
  • Network accessline 516
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'         '<w:settings xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'         '<w:trackRevisions w:val="true"/>'
  • Network accessline 517
    '<w:settings xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">'
  • Network accessline 521
    content_types = (         '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'         '<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">'
  • Network accessline 522
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'         '<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">'         '<Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relation
  • Network accessline 523
    '<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">'
  • Network accessline 534
    rels = (         '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'         '<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">'
  • Network accessline 535
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'         '<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">'         '<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument
  • Network accessline 536
    '<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">'
  • Network accessline 537
    '<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/>'
  • Network accessline 540
    doc_rels = (         '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'         '<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">'
  • Network accessline 541
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>'         '<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">'         '<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument
  • Network accessline 542
    '<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">'
  • Network accessline 543
    '<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles" Target="styles.xml"/>'
  • Network accessline 544
    '<Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/settings" Target="settings.xml"/>'

oral-history-master/scripts/run_pipeline.py

  • Executable scriptline 1
    #!/usr/bin/env python3

oral-history-master/scripts/transcript_ingest.py

  • Executable scriptline 1
    #!/usr/bin/env python3

oral-history-master/tests/test_pipeline.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.

Declared and executed: 1 fact
Signal confidence: 35 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md oral-history-master/SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md oral-history-master/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md oral-history-master/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md oral-history-master/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md oral-history-master/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md oral-history-master/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.

You might also use

heyuxuan0209/watch-anything

看不完的视频，让 AI 替你看懂：X/YouTube/B站视频 → 中文卡片解读（read-anything 的姊妹）

26GitHub stars

heyuxuan0209/read-anything

任意链接（网页/播客/视频/X）→ 中文结构化解读 → NotebookLM 式对话。自包含 skill，任何能跑 shell 的 AI agent 都能用。

31GitHub stars

fnjialun/cnipa-patent-writer

中国发明专利(CNIPA)撰写 Claude Code 技能：只借模板版式、内容据你的材料自生成；npx 一键安装

10GitHub stars

op7418/guizang-social-card-skill

Generate Guizang-style social card image sets, Live Photo motion cards, material-first Live Photo puzzle layouts, triple Live Photo collages, long-video-to-Live-Photo treatments, …

8kGitHub stars

feitangyuan/onetake

Make short product / skill motion videos (10–30 s, narrated feature demos up to ~60 s) the way high-end launch clips are made — kinetic type, real UI as the material, a hand that …

3.9kGitHub stars

yanliudesign/mono-color-skill

Generate original one-ink or controlled two-ink editorial images from any theme, sentence, article idea, object, or reference photo. Always use this skill when the user asks for …

3.6kGitHub stars