agentleFS
dongnguyenviedongnguyenvie/bashcut-agent-kit/skills/setup/SKILL.md

setup

Skill6 starsChanged 28 days agoMITView on GitHub

Set up BashCut's recommended plugins (captions, Vietnamese voice, silence markers, pre-production, AI Editor), trusted automatically unless the user turned that off (then with one approval in the app), and check they work. Only when the user types /bc:setup. Triggers: "/bc:setup", "cài plugin đề xuất", "setup BashCut".

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not ask them to send it to you.

    line 56
  2. Very specific:

    Prefer the typed command (voice speak, captions generate, beats detect, a plugin skill's own script), then plugins run ACTION.

    line 65

“Common” is measured: kept by at least 6 in 10 of the 170 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Setting up BashCut's recommended plugins

Plain words: the user may not be technical. Never paste raw JSON at them. The user typed /bc:setup, so they want the recommended plugins. Plugins are trusted automatically unless the user turned that off (Settings › Plugins), then they approve in the app. Never turn a plugin on that the user turned off, never change that setting, and never ask for API keys or passwords in the chat.

1. See what is missing

bashcut plugins bundles

The starter bundle (Recommended) lists each plugin (installable, default, reason, sizes). If nothing is installable, say everything is already installed and go to step 4.

2. Tell the user what they get

One short line per installable plugin, from its name: what it does for their videos, not its ID. Say which ones start unchecked (for example Antigravity) and the total download size. If the user already said they do not want some, check only the rest with --only.

3. Install

bashcut plugins install --bundle starter
bashcut plugins install --bundle starter --only bashcut.whisper-captions,bashcut.vieneu-tts

bashcut jobs wait JOB gives approval:

  • approved: the install already runs (default plugins or the --only ones). Say it is installing.
  • pending: the Plugins window shows a checkbox per plugin. Tell the user: "Kiểm tra danh sách rồi bấm Install trong cửa sổ Plugins" (or the same in their language). They can uncheck any plugin.
  • queued with position: another install runs first; this one starts after it. Do not ask again.
  • none: everything is installed.

The install runs as the user's job (plugins.install) and can take minutes (models download). Wait with bashcut jobs status (after pending, or ask the user to say when the Plugins window says it is installed), then go to step 4. Never start another install while one runs.

4. Check they work

bashcut plugins list --health
bashcut capabilities get

For each plugin that is not ready, explain the health detail in one sentence and what comes next:

  • An API key or login: the user enters it in Plugins › the plugin › Options (or signs in where the detail says). Do not ask them to send it to you.
  • A missing tool or a failed setup: run bashcut plugins setup PLUGIN once; approved: wait for the job, then check plugins list --health again; pending: the user approves it in the app (Plugins › the plugin › Set Up…). If it fails again, say what the detail says instead of retrying.

Finish with what they can do now, for example "gõ: làm phụ đề cho video này" or "đọc lồng tiếng đoạn này".

5. Drive a plugin's panel when no command does the job

Prefer the typed command (voice speak, captions generate, beats detect, a plugin skill's own script), then plugins run ACTION. Only a plugin with nothing else needs its view:

  1. bashcut plugins list --views finds it.
  2. bashcut plugins view PLUGIN --view VIEW gives its components as JSON: read it instead of a screenshot.
  3. bashcut plugins view-event PLUGIN --view VIEW --node ID [--type change|submit|select|action --value V] acts and returns the new components: no second view call. A colour picker takes #RRGGBB, a font picker a font name.
  4. --open (or plugins show-view) only when the user should see it. plugins invoke CAPABILITY --params JSON runs a capability raw (a job) when no command wraps it.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.