Krillinai CLI
Apps & Automationkrillinai-cliKrillinai CLI is an Agent Skill for apps & automation published in the krillinai/KrillinAI repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Use when an agent needs to operate KrillinAI through its CLI, choose the right stage command, inspect CLI outputs, or run subtitle, TTS, landscape render, and portrait render tasks from a YouTube/local video input.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/krillinai/KrillinAI/blob/HEAD/skills/krillinai-cli/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/krillinai-cli, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
KrillinAI CLI
Use this as the top-level routing skill for KrillinAI command-line work.
Quick Start
Prefer the repo-local binary:
./build/krillinai-cli <command> [flags]
If it does not exist, build it first:
go build -o build/krillinai-cli ./cmd/cli
For common JSON, manifest, outputs, and error semantics, read:
skills/krillinai-cli/references/cli-contract.md
Choose The Command
| User intent | Command / skill |
|---|---|
| Generate source, target, bilingual, and short vertical subtitles | subtitle; use krillinai-subtitle |
| Generate target-language dubbing from subtitles | tts; use krillinai-tts |
| Create landscape videos | render-horizontal; use krillinai-render-horizontal |
| Create portrait/short-form videos | render-vertical; use krillinai-render-vertical |
pipeline, cover, and status are planned/reserved surfaces in the current CLI. Use their skills for planning or dry-run documentation only unless the implementation has been wired in.
Operating Rules For Agents
- Use a dedicated
--workdir; do not scatter outputs in the repo root. - Prefer
--dry-runwhen validating command shape or planning a run. - Parse stdout JSON and
krillinai_manifest.json; do not parse normal logs. - Reuse manifest outputs for later stages instead of guessing filenames.
- If a command fails, classify by
error.kind:usage,retryable,dependency, orinternal. - Avoid rerunning expensive stages if the manifest already has valid upstream outputs.
Minimal Workflow
./build/krillinai-cli subtitle "https://www.youtube.com/watch?v=VIDEO_ID" \
--origin-lang en \
--target-lang zh_cn \
--workdir tasks/demo \
--caption-source any
./build/krillinai-cli render-vertical \
--workdir tasks/demo \
--video tasks/demo/origin_video.mp4 \
--subtitle tasks/demo/short_origin_mixed_srt.srt