aurum-batch

Run Aurum bounded resumable multi-file transcription with versioned manifests.

IndexedMIT★ 5

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/joe-broadhead-aurum-batch

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Run Aurum bounded resumable multi-file transcription with versioned manifests. Use for folders of lectures, interviews, or voice notes. For single-file STT/TTS and providers, load skills/aurum-speech.

Use cases: productivity

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/aurum-batch

What's inside

Skill name: aurum-batch
Description: Run Aurum bounded resumable multi-file transcription with versioned manifests. Use for folders of lectures, interviews, or voice notes. For single-file STT/TTS and providers, load skills/aurum-speech.
License: MIT
Metadata: owner: aurum · persona: batch · version: 0.0.23
Instructions: 31 lines in SKILL.md · view on GitHub

Files (2)

SKILL.md
workflow.md · references/

SKILL.md (first lines)

# Aurum batch skill

## Mission

Process **collections** of audio with one model load, deterministic outputs, and honest partial success.

Provider/model selection follows the same rules as single-file STT — see
**`skills/aurum-speech/`** (local default; remote only with explicit provider + key).

## Flow

1. Dry-run first: `aurum batch ./lectures -O ./out --dry-run`
2. Run: `aurum batch ./lectures -O ./out --model tiny-q5_1` (or `--profile speed`)
3. Resume: `aurum batch ./lectures -O ./out --resume`
4. Retry failures: `aurum batch ./lectures -O ./out --resume --retry-failed`
5. Inspect `./out/aurum-batch-manifest.json`

## Rules

- Not a shell `for` loop — use the native command for governor/transaction semantics.
- Do not clobber an existing manifest without `--resume`.
- Report succeeded/failed/pending counts from the summary.
- Keep outputs under `--output-dir`; do not write transcripts into the source tree by default.
- Do not invent flags; see `aurum batch --help`.

## Load order

- `references/workflow.md`
- `../aurum-speech/references/stt.md` when choosing models/providers

From joe-broadhead/aurum, MIT.

Signals

Stars: 5
Forks: 2
Open issues: 4
Last commit (this folder): Aug 3, 2026 (2 months ago)
Last release: Aug 3, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version: 0.0.23
License: MIT
Repository: github.com/joe-broadhead/aurum
Website: joe-broadhead.github.io/aurum/
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from joe-broadhead

Cite this page

aurum-batch skill. Agent Mart. https://agentmart.dev/skills/joe-broadhead-aurum-batch (last updated 2026-10-24)