long-audio-transcript-processor

long-audio-transcript-processor is a skill for Claude Code, Codex from cafe3310/public-agent-skills. It costs 32 tokens per session (2,503 once invoked), scanned A, original, Apache-2.0.

A workflow for checking, cleaning up, and splitting very long speech-to-text files into manageable sections. It keeps a glossary, topic notes, and progress records so work can continue later.

In plain words
What is it for?
It helps correct transcripts, separate speakers, organise paragraphs, and process long recordings in sections. It is also for pausing and resuming unfinished transcript work.
Why use it?
Long transcripts may be too large to handle at once, and speech recognition often produces mistakes, repeats, and broken sentences. Saved context helps keep names, terms, and formatting consistent across sessions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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.

agentmods
npx agentmods add skills/cafe3310/public-agent-skills/long-audio-transcript-processor
Any agent
npx skills add cafe3310/public-agent-skills --skill long-audio-transcript-processor
Clone the repo
git clone --depth 1 https://github.com/cafe3310/public-agent-skills

Made for: Claude Code, Codex.

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 long-audio-transcript-processor

README.md
[![agentmods](https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/long-audio-transcript-processor.svg)](https://agentmods.dev/skills/cafe3310/public-agent-skills/long-audio-transcript-processor)
Your own site
<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/long-audio-transcript-processor"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/long-audio-transcript-processor.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,503 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00032 $0.02503
Opus 5 $0.00016 $0.01252
Sonnet 5 $0.00006 $0.00501
Haiku 4.5 $0.00003 $0.00250

Measured 6d ago against content hash b88a08928cab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

long-audio-transcript-processor 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/setup_workspace.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/long-audio-transcript-processor/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

语音转写处理工作流 (Long Audio Transcript Processor)

此技能旨在通过文件系统辅助,安全、有序地处理超长语音转写文本。它通过分段处理、上下文维护(术语表、主题记录)和状态追踪,确保处理过程的可持续性和高质量。 此技能最好使用最高性能的模型(而不是写代码用的快速模型)以确保最佳质量。

使用时机

当用户提供一个或多个长篇语音转写文件,并要求进行:

  1. 校对与修正:修复识别错误、词语重复、中断、错漏等,校对前后行数一致。
  2. 整理与格式化:区分发言人,整理段落。
  3. 长文本处理:文本过长,无法一次性放入 LLM 上下文。
  4. 需要中断与恢复:工作可能跨越多次对话。

工作流

1. 准备阶段 (Initialization)

首先,必须初始化工作区。询问用户是否已准备好源文件。

运行初始化脚本:

python3 .gemini/skills/long-audio-transcript-processor/scripts/setup_workspace.py "path/to/file1.txt" "path/to/file2.txt" ...

(注意:请根据实际技能安装路径调整脚本路径,通常是 .gemini/skills/...)

初始化后,工作区结构如下:

语音转写处理_YYYY-MM-DD-HH-MM/
├── 0-工作日志.md           # 进度追踪与计划
├── 1-原始文件/             # 存放用户提供的原始语音文本
├── 2-要求和信息/           # 存放活动背景、发言人等信息(用户补充)
├── 3-校对和术语表.md       # 动态更新的术语库和错误模式
├── 4-分段主题.md           # 记录已处理分段的主题脉络
└── 5-最终输出/             # 存放校对完成的分段文件

关键操作

  1. 检查生成的目录。
  2. 同步背景知识:确保将用户提供的任何背景文档(如 MRD、PRD、会议背景、相关邮件等)文档复制到 2-要求和信息/ 目录下,也在该目录下创建 Markdown 文档记录用户的说明。这是保证后续处理准确性的基石。

2. 分段处理循环 (Processing Loop)

在进入循环前,总是先读取以下文件以加载上下文(确保跨分段的信息一致性):

  • 0-工作日志.md (检查进度)
  • 2-要求和信息/ 下的所有背景和要求文档
  • 3-校对和术语表.md (加载最新积累的术语和校对规则)
  • 4-分段主题.md (加载已有上下文主题)
  • 5-最终输出/ 下的文件 -- 列出文件名即可

步骤:

  1. 确定任务:从 0-工作日志.md 中找到第一个未完成([ ])的分段。
  2. 提取分段并初始化目标文件
    • 使用 sed 命令从 1-原始文件/ 中提取对应行范围,并重定向写入到 5-最终输出/ 下的对应文件中。
    • 命令示例sed -n '开始行,结束行p' "1-原始文件/文件名.txt" > "5-最终输出/文件名_开始行-结束行.txt"
    • 目的:确保所有原始行都已先进入目标文件,作为后续改写的底稿,防止内容遗漏。
  3. 执行校对与订正
    • 读取:使用 read_file 读取上一步生成的 5-最终输出/ 下的文件内容。
    • 参考:术语表、背景信息、前序分段主题。
    • 改写校对
      • 对读取到的内容进行逐行/逐段校对。
      • 修正错别字、重复、同音错误,减少冗余的语气词。
      • 标记不确定内容为 (...)
      • 保持一致性:必须确保校对后的行数与原始行数完全一致。如果需要合并发言,请在原位保留行占位。
    • 写回:使用 write_file 将校对后的完整文本写回 5-最终输出/ 的对应文件(覆盖掉刚才的底稿)。
  4. 更新辅助文档
    • 更新术语表。如果在本段发现了新的专有名词、特定错误模式或确认了某个模糊术语的正确写法,追加3-校对和术语表.md。仅追加,用行号段落区分不同分段的内容。
    • 更新主题。将本段核心主题 追加4-分段主题.md。仅追加,用行号段落区分不同分段的内容。
  5. 更新状态
    • 更新日志:在 0-工作日志.md 中标记分段为 [x]
  6. 反馈与沉淀
    • 告知用户本段已完成,简述关键修改、新发现的术语或不确定点。
    • 询问是否有新增术语或错误修正。
    • 如有反馈,更新 3-校对和术语表.md 并修正 5-最终输出 中的对应文件。

Read the full file on GitHub · 147 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 147 lines · 32 tokens per session scan A b88a08928cab

Subscribe to this mod's changes

long-audio-transcript-processor is a skill published in the GitHub repository cafe3310/public-agent-skills (253 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 2,503 once invoked, about $0.0002 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 2026-08-30.