| name | autojlp |
| description | Run and maintain the AutoJLP command-line documentary automation workflow. Use when an AI coding agent needs to inspect source video and SRT materials, validate dependencies, generate source-anchored Chinese narration, synthesize voice, match non-repeating footage, render a finished documentary edit, or troubleshoot AutoJLP. |
AutoJLP
Operate from the AutoJLP repository root. Keep the project command-line only; do not add or start a browser UI or network service.
Workflow
- Inspect the material directory without modifying source video or subtitle files.
- Install dependencies with
python -m pip install -r requirements.txt when needed.
- Run
python autojlp.py check "<material-directory>" before a long task.
- Resolve every reported configuration or dependency problem.
- Run
python autojlp.py script "<material-directory>" for narration only, or python autojlp.py run "<material-directory>" for the complete edit.
- Read the final
AUTOJLP_RESULT=<json> line. Report success only when status is success and output_path exists.
Pass --config <json> for task-specific settings, --target-minutes <5-60> for duration, --trim-head <0-300> and --trim-tail <0-300> for source trimming, and --voice-provider gpt_sovits|qwen|cosyvoice|system to select a voice backend.
Narration rules
- Mention Alan naturally in the first line and in the fixed closing only. Reject
艾伦 in every middle line.
- Reject first-person markers including
我是艾伦, 我, 我们, 咱, 咱们, and 本人.
- Convert interviews, dialogue, recollections, letters, questions, and quotations into indirect third-person narration.
- Reject Chinese or English quotation marks and speech labels such as
问：, 回答：, or 写道：.
- Preserve source anchors when rewriting a violating line. Scan again before voice synthesis or editing.
- Use the fixed closing:
好了，艾伦祝大家心想事成，艾伦该去遛狗了，回见！
Guardrails
- Preserve original videos and SRT files.
- Reuse manifests, synthesized audio, and clips unless regeneration is explicitly requested.
- Never print, copy, or commit
.env, config/secrets.bin, config/.secret.key, API keys, or private voice assets.
- Read
README.md before changing configuration fields, output behavior, Docker usage, or installation instructions.
- Keep every mirrored Skill copy synchronized by running
python scripts/sync_skills.py; verify with python scripts/sync_skills.py --check.
