agentleFS
Sign inStart free
WALKERKILLERWALKERKILLER/Look-Tongji-Notes/skills/ralphtrans/SKILL.md

ralphtrans

Skill53 starsChanged 5 months agoMITView on GitHub

Batch transcribe ALL playable lectures for a course in a persistent loop. Uses a JSON state file for checkpoint/resume. Runs until every lecture is transcribed or marked failed.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run /note for each transcribed lecture to generate study notes.

    line 54
  2. Very specific:

    Run /wiki to rebuild and serve the course site.

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ralph Batch Transcribe

Batch transcribe all playable lectures for a course with checkpoint/resume.

When to Use

  • User says /ralphtrans or "batch transcribe this course".
  • User wants to transcribe an entire course in one go.

Workflow

  1. Start batch transcription:
python "<SKILL_DIR>/../../scripts/look_tongji.py" batch-transcribe --course-id "<ID>"
  1. The CLI:
    • Loads all playable lectures for the course.
    • Creates/reads batch_state.json in the workspace to track progress.
    • Transcribes lectures one by one, updating state after each.
    • Retries failed lectures up to --max-retries times.
    • Prints a summary when all lectures are done or failed.
  2. Interrupt & Resume:
    • Press Ctrl+C to safely stop. State is saved.
    • Re-run the same command to resume from pending lectures.

State File

batch_state.json structure:

{
  "course_id": "xxx",
  "started_at": "ISO8601",
  "updated_at": "ISO8601",
  "lectures": [
    {"sub_id": "xxx", "sub_title": "xxx", "status": "pending|done|failed", "attempts": 0, "error": null}
  ]
}

After Completion

  • Run /note for each transcribed lecture to generate study notes.
  • Run /wiki to rebuild and serve the course site.

Where <SKILL_DIR> Points

<SKILL_DIR> is the directory containing this SKILL.md. Shared scripts (look_tongji.py, timeline_tools.py, tongji_backend/) and references live two levels up in the repository root (<SKILL_DIR>/../../scripts/ and <SKILL_DIR>/../../references/).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free