agentsclimarketplace
Sign in

AutoJLP

Skill DaBaoAgent/AutoJLP

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.From its SKILL.md

Install
npx -y skills add DaBaoAgent/AutoJLP

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.5 KB, 533 tokens by cl100k_base, as published. Nobody here has run it

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

  1. Inspect the material directory without modifying source video or subtitle files.
  2. Install dependencies with python -m pip install -r requirements.txt when needed.
  3. Run python autojlp.py check "<material-directory>" before a long task.
  4. Resolve every reported configuration or dependency problem.
  5. Run python autojlp.py script "<material-directory>" for narration only, or python autojlp.py run "<material-directory>" for the complete edit.
  6. 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.

What ships with it: 51 files

297973.9 KB alongside SKILL.md, 15 of them executable

assets/

backend/

config/

materials/

references/

11 more files not listed here. See all 51 in the repository.

Gives 0 of the 12 instructions most automation workflows skills give in 533 tokens

Counted across 745 of the 1,008 authors here whose files we hold, read 2026-08-07

  • Write conventional commit messagesin 36 of 745, across 35 files
  • Delete branches after mergein 30 of 745, across 21 files
  • Make atomic commitsin 25 of 745, across 15 files
  • Write minimal code to pass testsin 22 of 745, across 10 files
  • Re-snapshot after navigation or DOM changesin 21 of 745, across 13 files
  • Use try-catch for error handlingin 20 of 745, across 8 files
  • Run tests before committingin 20 of 745, across 12 files
  • Write tests before implementationin 20 of 745, across 8 files
  • Configure branch protection rulesin 19 of 745, across 5 files
  • Explain the why in commit messagesin 19 of 745, across 9 files
  • Refactor code while tests remain greenin 19 of 745, across 6 files
  • Interact with elements using refsin 19 of 745, across 11 files

Said here and by no other author read

  • operate from the repository root
  • keep the project command-line only
  • inspect the material directory without modifying files
  • install dependencies when needed
  • run the check command before a long task
  • resolve every reported problem

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,736. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.