long-audio-to-obsidian

long-audio-to-obsidian is a skill for Claude Code, Codex from cafe3310/public-agent-skills. It costs 35 tokens per session (1,493 once invoked), scanned A, original, Apache-2.0.

A workflow for combining scattered voice-transcription project files into organized Markdown documents for Obsidian, a note-taking and knowledge-management app. It sorts transcript sections by the numbers in their filenames and groups related project material.

In plain words
What is it for?
Use it to scan a transcription project, identify source transcripts and final segments, order them correctly, include metadata and derived notes, and create an Obsidian archive.
Why use it?
Long recordings often produce many transcript parts, logs, glossaries, and question files that are difficult to archive manually. The workflow separates these file types and uses a script to assemble the planned documents consistently.

Skill for Claude CodeCodex

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

Good fit Use it to scan a transcription project, identify source transcripts and final segments, order them correctly, include metadata and derived notes, and create an Obsidian archive.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cafe3310/public-agent-skills/long-audio-to-obsidian
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 cafe3310/public-agent-skills --skill long-audio-to-obsidian
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-to-obsidian

README.md
[![agentmods](https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/long-audio-to-obsidian/github.svg)](https://agentmods.dev/skills/cafe3310/public-agent-skills/long-audio-to-obsidian)
Your own site
<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/long-audio-to-obsidian"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/long-audio-to-obsidian/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 long-audio-to-obsidian

Your own site · 80×15
<a href="https://agentmods.dev/skills/cafe3310/public-agent-skills/long-audio-to-obsidian"><img src="https://agentmods.dev/badge/skills/cafe3310/public-agent-skills/long-audio-to-obsidian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,493 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00035 $0.01493
Opus 5 $0.00017 $0.00746
Sonnet 5 $0.00007 $0.00299
Haiku 4.5 $0.00003 $0.00149

Measured 13d ago against content hash 234a5b7f4bd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

long-audio-to-obsidian 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 13d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/doc_merger.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-to-obsidian/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Long Audio to Obsidian Archiver

此技能将散乱的语音转写项目文件整理成结构清晰的 Markdown 文档,便于在 Obsidian 等知识库中归档。

它采用 "Agent 规划 + 脚本执行" 的模式:

  1. Agent (你):负责理解目录结构、识别文件类型、对分段文件进行逻辑排序(例如按行号 1-200, 201-400),并生成合并计划。
  2. Script:负责根据你的计划,机械地读取文件并生成 Markdown。

使用场景

当用户要求将一个包含多个原始音频、数十个转写分段、以及各种说明文档的目录“整理归档”时使用。

工作流 (Workflow)

1. 调查与分析 (Survey & Analyze)

首先,使用 list_directory (必要时配合 glob) 扫描目标项目目录。 你需要回答以下问题:

  • 哪些是原始录音文本?(通常在 1-原始文件 或类似目录)
  • 哪些是最终输出的分段脚本?(通常在 5-最终输出,文件名包含行号如 _1-200
    • 关键任务:你需要根据文件名中的数字对它们进行正确排序。
  • 哪些是项目元数据?(日志、术语表、背景要求等)
  • 哪些是衍生知识/问答?(5-最终输出 中非分段的 Markdown 文件)

2. 生成合并配置 (Generate Configuration)

基于你的分析,构建一个 JSON 配置文件。不要直接输出给用户,而是准备写入临时文件。

JSON 结构定义

{
  "output_dir": "目标项目路径/obsidian_archive",
  "tasks": [
    {
      "filename": "1-原始录音汇总.md",
      "title": "原始录音汇总",
      "sections": [
        {
          "title": "文件1.txt",
          "path": "绝对路径或相对路径/文件1.txt",
          "syntax": "text"
        }
      ]
    },
    {
      "filename": "2-最终输出脚本汇总.md",
      "title": "最终输出脚本汇总",
      "sections": [
        {
          "title": "Part 1 (1-200)",
          "path": "路径/output_1-200.txt",
          "syntax": "text"
        },
        {
          "title": "Part 2 (201-400)",
          "path": "路径/output_201-400.txt",
          "syntax": "text"
        }
        // Agent 必须确保这里的顺序是正确的!
      ]
    }
    // ... 继续为“整理要求汇总”和“知识整理汇总”创建任务
  ]
}

3. 执行合并 (Execute)

  1. 使用 write_file 将 JSON 配置保存为临时文件,例如 merge_plan.json

  2. 调用脚本执行合并:

    python3 .gemini/skills/long-audio-to-obsidian/scripts/doc_merger.py merge_plan.json
    

    (注意:请根据实际安装位置调整脚本路径)

  3. 检查脚本输出,确认生成成功。

  4. 删除临时文件 merge_plan.json

4. 优化命名与生成索引 (Rename & Index)

脚本生成的只是标准文件名的中间产物。为了方便 Obsidian 使用,你需要进行最后一步的人工智能优化:

  1. 确定项目标题:根据原始目录名或核心文件名,提取一个清晰的项目标题(例如 2024-01-01 会议转写 - 项目 A)。
  2. 重命名文件:使用 run_shell_commandmv 命令,将 obsidian_archive 中的标准文件重命名为带前缀的格式。
    • 1-原始录音汇总.md -> {标题} 1 原始录音汇总.md
    • 2-最终输出脚本汇总.md -> {标题} 2 最终输出脚本汇总.md
    • ...以此类推。
  3. 生成索引页
    • 创建一个名为 {标题}.md 的新文件。
    • 内容应包含指向上述所有文件的 Obsidian WikiLinks ([[文件名]])。
    • 如果有关联的外部产品文档(未合并进来的),也可以在此处添加链接。

Read the full file on GitHub · 134 lines

Files

What ships with it

1 file 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. 13d ago First seen · 134 lines · 35 tokens per session scan A 234a5b7f4bd3

Subscribe to this mod's changes

long-audio-to-obsidian is a skill published in the GitHub repository cafe3310/public-agent-skills (253 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,493 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.