Javdb Cli Develop logo

Javdb Cli Develop

Community
FlanChanXwO
javdb-cli-develop

Implement, diagnose, refactor, and design javdb-cli Go changes across CLI commands, the public SDK, App API adapters, configuration, and state. Use before source changes or engineering design; use the media workflow for image/HLS changes. Does not depend on personal agent configuration.

Overview

PublisherFlanChanXwO
Repositoryjavdb-cli
Skill namejavdb-cli-develop
Stars
76
Forks
15
Bundled files
1
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.

  • 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 FlanChanXwO on GitHub. Read the source before you install it.

Installation

Install the Javdb Cli Develop 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/.agents/skills/javdb-cli-develop
  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/.agents/skills/javdb-cli-develop .claude/skills/javdb-cli-develop
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Javdb Cli Develop 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 Develop 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 Develop 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.

Develop javdb-cli

Establish the change

Read AGENTS.md, the relevant architecture section, exact owner code, and tests. Identify the requested result, compatibility boundary, and acceptance evidence. Reproduce bugs before selecting a fix. Resolve consequential design gaps for large work, but do not turn a clear local change into a multi-document planning exercise.

Inspect branch, base SHA, and git status --short. Reuse a suitable isolated worktree; otherwise use git worktree add -b BRANCH PATH BASE with verified values and an unused agreed path. Preserve unrelated work. Use explicit working directories and safely quoted inputs.

Use available semantic definitions/references/callers for symbol changes; disclose an unavailable LSP and inspect actual imports/callers with targeted search and compiler checks. Read exact edited code and foundational documents yourself.

Go design and language rules

  • Use the go.mod toolchain and gofmt, conventional Go initialisms, consistent receivers, and responsibility-based package names. Document affected exported contracts and state ownership, errors, cancellation, and side effects. Apply javdb-cli-code-commenting to comments and numbered stages; English and Chinese prose are both acceptable, with valid Go doc syntax.
  • Prefer concrete types and consumer-owned narrow interfaces at genuine substitution boundaries. Keep constructors and dependencies explicit. Do not add facade/alias/forwarder layers to imitate another repository or expose internals solely to simplify a test.
  • CLI owners parse input and present output; sdk/ owns the public capability surface; App API owns protocol/decoding. Reuse cli/client, cli/result, cli/entity, and cli/pipeline instead of copying lifecycle, projections, or stream parsing into commands.
  • Treat Client.API() and taxonomy internal return types as frozen compatibility debt, not a precedent for new public leaks. New capabilities use typed SDK operations; preserve existing scripts' flags, output shapes, and status semantics.
  • Pass context through network and media operations. Make goroutine ownership, cancellation, channels, lock scope, and cleanup explicit. Avoid shared process globals for per-invocation options and avoid locks held around uncontrolled I/O.
  • Preserve typed errors with errors.Is/errors.As and useful context. Keep passwords, JWTs, signed/private URLs, and raw upstream payloads out of logs and error wrapping. Distinguish a legitimate empty result from partial failure and a failed operation.
  • Keep schema validation and optional-field semantics at their real boundaries. Do not infer internal movie IDs from display names, select a fuzzy first hit for a write, or widen anonymous retry beyond the existing optional-auth contract.
  • Use standard-library/platform features and installed dependencies before new code. Introduce abstractions, caches, retries, limits, and configuration only for present evidenced needs; preserve established SDK timeout/protocol policies rather than deleting them indiscriminately.

Use the official Go Code Review Comments for additional language guidance; apply it within the repository's existing compatibility and ownership boundaries.

Readability and the smallest design

  • Keep a coherent operation understandable in its owner. Extract a helper or package when it names a real responsibility, hides relevant complexity, or removes stable semantic duplication, not merely to shorten a function. Count the reader's cross-file jumps and parameters, not only lines removed.
  • A useful interface makes its consumer simpler while its implementation owns the difficult details. Reject pass-through layers, option bags, and general frameworks whose callers still manage those details. Use SOLID as a diagnostic for actual coupling, not a requirement for one interface per type or an extension point per branch.
  • Prefer explicit data flow, descriptive names, and a visible normal path over compressed expressions or clever reuse. Keep related validation and transformations near their data; remove nesting when it improves clarity without hiding distinct failures.
  • Tolerate small duplication when the cases have different reasons to change. Share code only when their semantics are stable; avoid boolean modes and configuration added merely to combine unrelated cases.
  • Do not build production abstractions to support oversized mocks. Select a real test boundary and the smallest fixture before changing design for test convenience. Preserve existing caller/security contracts while simplifying.

Execute with evidence

Use javdb-cli-test, including its coverage-gap decision before adding tests. Reuse or extend a relevant test and observe behavioral Red before implementing a feature or fix, make the smallest change Green, then refactor with regression checks. A missing compiler, fixture, or dependency is a blocker, not a valid Red. For pure restructuring, reuse characterization before and after; any behavioral correction still needs failing evidence. Obtain an explicit exception when an applicable Red requirement cannot be run.

For image/HLS or no-replace output, also read javdb-cli-media. Keep input acquisition, decryption, validation, remuxing, and publication with their existing owners. Do not introduce Rust, ffmpeg, an MCP service, or a download-service layer for directory symmetry.

For new dependencies or persistent configuration, apply the root approval policy. For any new defensive constraint, name its evidence, trigger, and normal-path impact in comments and the existing delivery record; test the protected failure and valid path. Prefer fixing the underlying cause to hiding it.

Update changed public contracts through javdb-cli-docs. Run available affected-file semantic diagnostics and the checks selected by the test workflow. Keep additional work tied to the acceptance criteria, not hypothetical future reuse.

Finish

Use javdb-cli-review for a meaningful change. Report exact checks and results, unverified behavior, and remaining risk. A green local check does not authorize a merge, real account operation, or release.

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 Develop AI skill do?

Implement, diagnose, refactor, and design javdb-cli Go changes across CLI commands, the public SDK, App API adapters, configuration, and state. Use before source changes or engineering design; use the media workflow for image/HLS changes. Does not depend on personal agent configuration.

Why use Javdb Cli Develop on TypingMind?

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

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

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 Develop?

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

Is the Javdb Cli Develop 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 👇