Publish Moviepilot Plugin logo

Publish Moviepilot Plugin

CommunityPopular
jxxghp
publish-moviepilot-plugin

Use this skill when the user asks to publish, upload, sync, pull, push, diff, or maintain a MoviePilot local plugin in a GitHub repository. Covers using the configured MoviePilot GitHub token, PLUGIN_LOCAL_REPO_PATHS local plugin repositories, package.json/package.v2.json metadata, plugins/plugins.v2 layouts, safe file exclusion, diff preview before publishing, incremental GitHub Contents API updates, and syncing local plugin changes back from GitHub. Includes asking whether to use an existing repository or create a new public repository when no target repository is available. Also use for Chinese requests mentioning 插件发布, 插件维护, 推送插件到 GitHub, 从 GitHub 拉取插件, 同步本地插件仓库, 增量发布插件, 插件仓库维护.

Overview

Publisherjxxghp
RepositoryMoviePilot
Skill namepublish-moviepilot-plugin
Stars
11.8K
Forks
1.5K
Bundled files
1
LicenseGPL-3.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jxxghp on GitHub. Read the source before you install it.

Installation

Install the Publish Moviepilot Plugin AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jxxghp/MoviePilot.git /tmp/MoviePilot
mkdir -p .claude/skills
cp -r /tmp/MoviePilot/skills/publish-moviepilot-plugin .claude/skills/publish-moviepilot-plugin
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Publish Moviepilot Plugin in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Publish Moviepilot Plugin on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Publish Moviepilot Plugin is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Publish MoviePilot Plugin

Use this skill to publish and maintain a MoviePilot local plugin repository through GitHub while protecting local secrets and unrelated plugins.

Scope

  • Publish one local plugin under plugins.v2/<plugin_id_lower>/ or plugins/<plugin_id_lower>/ to a GitHub repository.
  • Merge only that plugin's entry into package.v2.json or package.json.
  • Preview local/remote differences before writing.
  • Pull remote plugin files back to the local plugin source.
  • Create the target GitHub repository when the user explicitly chooses automatic creation; repositories are public by default unless the user asks for private.
  • Reuse MoviePilot settings GITHUB_TOKEN, REPO_GITHUB_TOKEN, and PLUGIN_LOCAL_REPO_PATHS when available.

Ground Truth

  • Local plugin development rules: skills/create-moviepilot-plugin/SKILL.md.
  • Local plugin source discovery: app/adapters/external/market.py, PluginHelper.get_local_repo_paths().
  • GitHub token settings: app/runtime/config.py, especially GITHUB_TOKEN and REPO_GITHUB_TOKEN.
  • Plugin package layouts:
    • V2: package.v2.json and plugins.v2/<plugin_id_lower>/
    • Legacy: package.json and plugins/<plugin_id_lower>/

Pre-Flight

  1. Identify the target plugin ID and local source repository.
    • If the user gives a path, use it.
    • Otherwise query PLUGIN_LOCAL_REPO_PATHS; if exactly one configured repository contains the plugin, use it.
    • If several configured repositories contain the plugin, ask which one.
  2. Identify the GitHub repository as owner/repo.
    • Use the user's explicit repository first.
    • If omitted, infer only when the local source has an obvious Git remote.
    • If neither is available, ask whether to use an existing repository or automatically create a new public repository.
    • If the user chooses an existing repository, ask for owner/repo.
    • If the user chooses automatic creation, ask for the target owner/repo and state that the repository will be public by default.
    • Do not create a private repository unless the user explicitly asks for it.
  3. Select the package version layout.
    • Prefer v2 when package.v2.json or plugins.v2/<plugin_id_lower>/ exists.
    • Use legacy only when the local plugin is under plugins/.
  4. Verify token availability.
    • Prefer REPO_GITHUB_TOKEN for the target repo when configured.
    • Fall back to GITHUB_TOKEN.
    • If no token is configured, ask the user to configure one before pushing. Read-only preview may still run without a token for public repositories.

Script

Use scripts/publish_plugin.py for deterministic GitHub operations.

bash
python skills/publish-moviepilot-plugin/scripts/publish_plugin.py preview \
  --repo owner/repo \
  --plugin-id MyPlugin \
  --local-repo /path/to/MoviePilot-Plugins \
  --package-version v2

python skills/publish-moviepilot-plugin/scripts/publish_plugin.py push \
  --repo owner/repo \
  --plugin-id MyPlugin \
  --local-repo /path/to/MoviePilot-Plugins \
  --package-version v2 \
  --message "Publish MyPlugin v1.0.0"

python skills/publish-moviepilot-plugin/scripts/publish_plugin.py pull \
  --repo owner/repo \
  --plugin-id MyPlugin \
  --local-repo /path/to/MoviePilot-Plugins \
  --package-version v2

python skills/publish-moviepilot-plugin/scripts/publish_plugin.py create-repo \
  --repo owner/repo

Options:

  • create-repo: create the target GitHub repository. Default visibility is public; use --private only when the user explicitly asked for private.
  • preview: compare local filtered files with remote files and print JSON.
  • push: upload changed files and merge the plugin package entry.
  • pull: write remote plugin files and package entry into local source.
  • --create-repo-if-missing: on push, create the target public repository when GitHub reports that it does not exist.
  • --delete-remote: on push, delete remote plugin files that no longer exist locally after exclusions.
  • --force: on pull, allow overwriting local files that differ from remote.
  • --include PATTERN: add files otherwise excluded by default.
  • --exclude PATTERN: add an extra ignore pattern.
  • --dry-run: print planned changes without writing.
  • --proxy URL: use an explicit HTTP/HTTPS proxy for GitHub API requests.

Safety Rules

  • Always run preview before push unless the user explicitly asks for a direct push and already reviewed the diff.
  • When no repository is known, ask the user to choose: 使用已有 GitHub 仓库 or 自动创建 GitHub 仓库(默认 public).
  • Only run create-repo or push --create-repo-if-missing after the user has explicitly chosen automatic creation.
  • Never upload these files unless explicitly included: .env, .env.*, config/, data/, cache/, logs/, tmp/, __pycache__/, .pytest_cache/, .mypy_cache/, .ruff_cache/, .DS_Store, *.pyc, *.pyo, *.db, *.sqlite, *.sqlite3, *.log, *.bak, *.tmp, *.secret, *.key, *.pem, *.crt, *.p12, *.pfx, node_modules/.
  • For Vue federation plugins, publish built runtime assets under dist/assets/ when they are present; do not exclude them as generated files.
  • Do not overwrite or remove package entries for other plugins.
  • Do not log or print GitHub token values.
  • For push operations, report created, updated, deleted, skipped, and rejected files separately.
  • For pull operations, preserve local-only ignored files and refuse to overwrite differing local files unless --force is used.

Examples

User asks: 把本地 MyPlugin 发布到我的 GitHub 插件仓库

  1. Find MyPlugin under configured PLUGIN_LOCAL_REPO_PATHS.
  2. Ask whether to use an existing repository or create a new public repository if owner/repo cannot be inferred.
  3. Run preview and summarize the diff.
  4. Run push only after the user confirms or requested immediate publish.

User asks: 发布插件,没有 GitHub 仓库

  1. Ask for the target owner/repo and confirm automatic creation.
  2. Run create-repo or use push --create-repo-if-missing.
  3. Continue with preview and push after repository creation succeeds.

User asks: 同步 GitHub 上 MyPlugin 的最新代码到本地

  1. Run pull without --force.
  2. If local conflicts are reported, show the conflicting paths and ask whether to force overwrite or resolve manually.

Final Checklist

  • The plugin ID matches the package object key.
  • The package file and plugin directory layout match the selected version.
  • Sensitive and runtime-local files were rejected or skipped.
  • The preview was shown before push, unless explicitly bypassed.
  • The final response mentions whether local agent restart is needed only when this built-in skill itself changed.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Publish Moviepilot Plugin AI skill do?

Use this skill when the user asks to publish, upload, sync, pull, push, diff, or maintain a MoviePilot local plugin in a GitHub repository. Covers using the configured MoviePilot GitHub token, PLUGIN_LOCAL_REPO_PATHS local plugin repositories, package.json/package.v2.json metadata, plugins/plugins.v2 layouts, safe file exclusion, diff preview before publishing, incremental GitHub Contents API updates, and syncing local plugin changes back from GitHub. Includes asking whether to use an existing repository or create a new public repository when no target repository is available. Also use for...

Why use Publish Moviepilot Plugin on TypingMind?

Because you install it once and use it with any model. Publish Moviepilot Plugin is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Publish Moviepilot Plugin in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jxxghp/MoviePilot/tree/v3/skills/publish-moviepilot-plugin. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Publish Moviepilot Plugin?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Publish Moviepilot Plugin?

As many as you like. As long as a model supports skills, you can use Publish Moviepilot Plugin with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Publish Moviepilot Plugin AI skill free?

Yes. It is published on GitHub by jxxghp under the GPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇