Skip to content
Get packs

KrillinAI CLI Routing

Lets an agent build and run the KrillinAI CLI for subtitles, dubbing, renders, covers and speech

Source Download skill
Repository
krillinai/OpenCreator
Stars
14,089
Licence
Apache-2.0
Files
2 files

What it does

This skill teaches an AI agent how to build the KrillinAI command-line tool from a source checkout, pick the right command for a task, and read its JSON output. Once installed, the agent can route requests such as generating translated subtitles, dubbing, landscape or vertical video renders, cover images, speech, and voice lists to the matching CLI command. It also gives safety habits such as using a dedicated work folder, validating with a dry run first, and reusing outputs recorded in a manifest file.

Great for

  • Developers who already work in the KrillinAI repository and want an agent to drive its CLI
  • Video creators who need translated subtitles, dubbing, or short-form renders produced through KrillinAI
  • Teams building automated video localisation pipelines who want consistent JSON handling

Skip it if

  • People without the KrillinAI repository or a built binary, since the skill only routes commands and cannot run the tool by itself
  • Uses requiring the pipeline command to actually execute multi-stage work, because non-dry-run pipeline calls return unsupported_command
  • Use with untrusted video URLs or unknown configuration files, since the CLI runs locally and makes external provider calls

Try asking

  • “Generate English to Chinese subtitles for this YouTube video and then make a vertical short from it”
  • “Build the KrillinAI CLI from this checkout and check that the binary exists”
  • “List the available OpenAI voice codes for dubbing”
  • “Create a landscape render from the existing subtitle outputs in my task folder”
Step-by-step guide: how to use KrillinAI CLI RoutingInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the Apache-2.0 licence and an attribution note.

    krillinai-cli.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip krillinai-cli.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip krillinai-cli.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Always run with --dry-run first to confirm the command shape before spending money on external calls
  • Point --workdir at a dedicated folder such as tasks/demo so outputs do not clutter the repo root
  • Let the agent read krillinai_manifest.json for filenames instead of guessing, and keep config.toml secret

What's inside

  • references/cli-contract.md
  • SKILL.md

Redistributed unmodified from krillinai/OpenCreator under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.