Javdb Cli logo

Javdb Cli

Community
FlanChanXwO
javdb-cli

Operate the installed javdb CLI to search the JavDB App API, inspect movie and entity references, read lists, and perform explicitly authorized account, configuration, mark, or preview-asset actions. Use only for an explicit JavDB or javdb-cli task, a javdb command, or a clear JavDB reference with an operation request. Do not trigger for generic search, adult-content discovery, or downloading. Verify syntax with javdb COMMAND --help.

Overview

PublisherFlanChanXwO
Repositoryjavdb-cli
Skill namejavdb-cli
Stars
76
Forks
15
Bundled files
7
LicenseMIT
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.

  • 7 bundled files

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

  • Open source

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

Installation

Install the Javdb Cli 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.
    https://github.com/FlanChanXwO/javdb-cli/tree/main/skills/javdb-cli
  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/FlanChanXwO/javdb-cli.git /tmp/javdb-cli
mkdir -p .claude/skills
cp -r /tmp/javdb-cli/skills/javdb-cli .claude/skills/javdb-cli
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Javdb Cli 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 Javdb Cli 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 Javdb Cli 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.

JavDB CLI Operator

Drive the installed javdb binary, not a guessed API or a source checkout. Read only the reference needed for the user's operation; no repository-maintenance skill or personal agent configuration is required.

Preflight

  1. Run javdb --version. If missing or not executable, report the blocker. Install only on an explicit installation/repair request using install.md.
  2. Inspect the relevant javdb COMMAND --help before execution. Do not list accounts on every turn; use auth list only for an account decision or explicit request. A stored account is not proof of a valid token.
  3. Use networked javdb auth check --json only when identity validation is needed. Normal discovery does not authorize login, configuration repair, or host changes.

Safety and authorization

  • ~/.javdb-cli/auth.json contains usernames, passwords, and JWTs. Never read, print, upload, quote, or summarize its contents. Supported POSIX systems use private 0600 permissions.
  • For login and credential handling, read auth.md. Do not launch a hidden prompt in an agent terminal the user cannot type into. Never request an undisclosed password in chat as a workaround.
  • Account/config changes, mark/unmark, cache clearing/refresh, updates, and file downloads require the user's explicit current target and action. Prior authorization does not extend to a new target. Reuse an already explicit instruction rather than asking the same question again.
  • Use the App API. Do not substitute browser cookies or scraping after an error. Existing optional-auth anonymous retry for magnets and explicitly enabled auto_relogin are documented product behavior, not permission to add other fallback or retry steps.
  • Image search uploads the image to AVScan or a configured provider. Explain that privacy effect and use only an authorized source. Media assets are previews/thumbnails, not full movies or magnet-target downloads.

Choose the operation

TaskCommands and scope
Read discovery/detailssearch, detail, comments, magnets, entity commands, rankings, tags, browse; see discover.md
Read authenticated liststop250, watched, want, recent, collections, default lists; require the selected local account
Diagnose identityauth list, auth check; only when needed
Change remote/local statemark, unmark, auth login/use/remove, config set/unset; see state.md
Save media assetsassets list then a scoped pipe into assets download; see media.md
Inspect/update installationupdate --check --json is read-only; actual update requires explicit authorization
Manage cachestags --refresh rebuilds tags; cache reverse-search --clear clears only reverse-search cache; use only for the requested cache task

magnets and detail --magnets can run anonymously; a configured account is used when present, and a rejected optional token falls back to anonymous inside the CLI. Do not apply that behavior to authenticated list or write commands.

Output and input contracts

Use the user's requested scope. Supply a positive --limit only when supported and appropriate to that scope; never add an arbitrary limit, page cap, timeout, or retry to save context. --all is command-specific and only for an explicit exhaustive traversal. comments reads one selected page (default page 1, limit 20), not an automatic all-pages loop.

TTY stdout defaults to human-readable text. Piped stdout normally uses stable text references/URIs; explicit --ndjson selects javdb.pipeline/v1 envelopes. --json retains the command's aggregate/legacy shape where applicable and is mutually exclusive with --ndjson. Inspect exit status before parsing: errors can be plain stderr and empty stdout.

Most data commands accept non-TTY batch input. Explicit positional arguments plus non-empty stdin are ambiguous and fail. Login, password prompts, and config set are outside this generic pipeline path. Batch failures can preserve successful items and still exit nonzero; report both rather than calling them empty results.

Movie/list/entity envelopes carry their actual kind and stable ID; list/entity payloads live in data.list/data.entity. Missing stable IDs fail, while a missing display name can use the ID as ref. A known movie ID bypasses number resolution; never infer one from a title. Assets use a separate TYPE<TAB>URL stream.

text
javdb search "ABC-123" --json
javdb search "QUERY" --type actor --json
javdb detail ABC-123 --json
javdb detail MOVIE_ID --id --json
javdb comments ABC-123 --page 1 --limit 20 --json
javdb lists search "QUERY" --zone all --ndjson
javdb list LIST_ID --json
javdb lists related ABC-123 --ndjson
javdb search ABC --ndjson | javdb detail
javdb rankings movies --type fc2 --period week
javdb update --check --json

Replace placeholders only with verified values. Examples illustrate syntax, not permission to perform extra requests.

Image search and integrated magnet search

javdb search IMAGE_OR_URL [--source NAME] [--no-cache] accepts JPEG/PNG/WEBP up to the existing 8 MiB limit and uploads to the selected provider. Candidates are resolved to JavDB through strict movie-number matching; one failed candidate can leave other output and a nonzero exit. Do not hide the failed candidate.

Reverse-search caching defaults to 30 days, keyed by source and original-image SHA-256. --no-cache bypasses it for one search. javdb cache reverse-search [--source NAME] [--clear] addresses that cache only; do not delete unrelated local state.

javdb search QUERY --magnets N combines movie search, filtering, sorting, and magnet lookup. --cnsub, --hd, and non-negative --min-size filter before sorting; zero is valid and negative fractional sizes fail. N=0 requests all and positive N selects the first N. Text output contains magnet URIs; NDJSON contains kind=magnet. This option does not download the targets and is only for movie search.

Configuration and routing

Precedence is CLI flags, environment, config.toml, then defaults. --proxy URL and --host auto|mirror|main|URL affect one invocation. Supported proxy schemes are HTTP/HTTPS/SOCKS4/SOCKS4A/SOCKS5/SOCKS5H; a host is required and SOCKS needs an explicit port. An explicitly blank proxy is an error, not a direct-connection override.

CLI host=auto verifies and reuses route.json; when invalid, it discovers startup candidates and selects a route. Fixed mirror, main, or absolute URLs bypass discovery. Do not confuse the CLI default with the SDK constructor's mirror default or persist an unreviewed URL.

Actual update resolves its own Release transport, ignoring data host selectors. It detects Homebrew, go install, or Release-archive installation; development builds refuse self-update. Use --prerelease only on request, and not for Homebrew. See install.md for verification boundaries and troubleshooting.md for failures.

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 Javdb Cli AI skill do?

Operate the installed javdb CLI to search the JavDB App API, inspect movie and entity references, read lists, and perform explicitly authorized account, configuration, mark, or preview-asset actions. Use only for an explicit JavDB or javdb-cli task, a javdb command, or a clear JavDB reference with an operation request. Do not trigger for generic search, adult-content discovery, or downloading. Verify syntax with javdb COMMAND --help.

Why use Javdb Cli on TypingMind?

Because you install it once and use it with any model. Javdb Cli 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 Javdb Cli in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/FlanChanXwO/javdb-cli/tree/main/skills/javdb-cli. 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 Javdb Cli?

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 Javdb Cli?

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

Is the Javdb Cli AI skill free?

Yes. It is published on GitHub by FlanChanXwO under the MIT 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 👇