Install By2kb logo

Install By2kb

Community
Charlesmpc
install-by2kb

Install, configure, update, or diagnose the by2kb CLI for this Hermes plugin. Preserve existing configuration and keep Hermes-managed plugin code separate from CLI upgrades.

Overview

PublisherCharlesmpc
Repositoryby2kb
Skill nameinstall-by2kb
Stars
154
Forks
14
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Install By2kb 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/Charlesmpc/by2kb/tree/main/by2kb/integrations/hermes/skills/install-by2kb
  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/Charlesmpc/by2kb.git /tmp/by2kb
mkdir -p .claude/skills
cp -r /tmp/by2kb/by2kb/integrations/hermes/skills/install-by2kb .claude/skills/install-by2kb
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Install By2kb 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 Install By2kb 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 Install By2kb 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.

Set up by2kb for Hermes

This plugin is already installed. Set up its separate CLI on the same machine and under the same user as the Hermes gateway. Do not copy or replace the plugin, clone the repository, or run by2kb agent install hermes from this workflow.

Inspect first

  • Check by2kb version, Python 3.12+, ffmpeg, ffprobe, and the available package manager. This plugin's staged request-file workflow requires by2kb 0.5.3 or newer; do not assume an arbitrary future version is compatible without checking its release notes.
  • Check whether by2kb was installed with pipx list or uv tool list; use that manager for upgrades. Do not create a second installation with another manager.
  • A missing command can be a PATH problem. On Windows use Get-Command and inspect uv tool dir --bin or py -m pipx environment when applicable. The gateway may need a restart to inherit a repaired PATH. BY2KB_COMMAND may name an absolute executable path (not a shell command with arguments).
  • Treat BY2KB_HOME (default ~/.by2kb), its .env, database, models, custom Skills, and the knowledge-base directory as user-owned. Do not display secret values.
  • If configuration already exists, run by2kb doctor --json and repair only the reported problems. Do not run init or change providers just to make checks pass.

First installation

Explain the dependencies and obtain agreement before installing. Prefer an already available package manager; either of these installs an isolated CLI, not into Hermes:

bash
pipx install "by2kb[asr-whisper,youtube]" --python 3.12
# Or, if uv is the chosen manager:
uv tool install --python 3.12 "by2kb[asr-whisper,youtube]"

Install ffmpeg/ffprobe using the platform's trusted package manager if missing. YouTube also needs matching yt-dlp EJS scripts (included by the CLI's default dependencies) and Deno 2.3+ or Node.js 22+. Reuse an existing supported runtime; explain and obtain agreement before installing a missing runtime. doctor --json checks both. An explicit [sources.yt_dlp] js_runtime / js_runtime_path can expose an existing executable outside the gateway PATH without replacing configuration. No browser or account Cookie is required to install JS support. Do not treat JS readiness as proof that YouTube will permit anonymous playback. If a real video requests authentication, use the optional platform sign-in guidance in by2kb:video-to-knowledge: obtain consent for a specific local browser session, do not require a Cookie-export extension, never expose secrets, and preserve all existing configuration. Do not install a browser or PO Token service by default. Confirm the knowledge-base location, then, only for a new configuration:

bash
by2kb init --preset agent-local --library-root "<chosen directory>"

Default to local Whisper and agent-hosted summaries; no separate LLM key or TOS account is needed. Before by2kb models install, inspect by2kb models status, explain the selected model and expected download size from its model information, and obtain agreement. If the size cannot be established, say so rather than inventing it. Then run by2kb doctor --json and explain remaining failures.

Cloud ASR is optional. If the user chooses Doubao, install the asr-doubao,youtube extras using the same package manager and have them run by2kb init in a trusted local terminal to configure TOS and ASR. Do not request secrets in chat. Preserve existing configuration; changing an existing provider is a separate explicit choice. The browser fallback is also optional: do not install Playwright or Chromium unless the user chooses it. Follow the project's browser setup guide for that route.

Finish and upgrade

  • Enable the plugin with hermes plugins enable by2kb if needed. Ask before restarting an active gateway. Verify the gateway sees the CLI, then ask the user to send a test video URL. Do not claim success from installation alone.
  • Upgrade the CLI with its existing manager: pipx upgrade by2kb or uv tool upgrade by2kb. Never run init with --force during an upgrade.
  • For catalog-installed plugin code, use hermes plugins update by2kb. For a Git-pinned plugin, changing the pin requires an explicitly chosen full commit via Hermes install. Never self-update or replace this plugin from PyPI.
  • If the installation is pinned to a Git URL, an upgrade may keep that old revision. Explain it and ask before migrating to PyPI or uninstalling anything.
  • Run doctor again; preserve all user-owned state and stop for unresolved requirements.

After setup, use skill_view("by2kb:video-to-knowledge") for manual ingestion.

Frequently asked questions

What does the Install By2kb AI skill do?

Install, configure, update, or diagnose the by2kb CLI for this Hermes plugin. Preserve existing configuration and keep Hermes-managed plugin code separate from CLI upgrades.

Why use Install By2kb on TypingMind?

Because you install it once and use it with any model. Install By2kb 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 Install By2kb in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Charlesmpc/by2kb/tree/main/by2kb/integrations/hermes/skills/install-by2kb. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Install By2kb?

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 Install By2kb?

As many as you like. As long as a model supports skills, you can use Install By2kb with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Install By2kb AI skill free?

Yes. It is published on GitHub by Charlesmpc 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 👇