Lark's Official CLI, in Three Command Tiers

Added 2026-08-06

Plus-prefixed shortcuts serve humans and agents alike, with smart defaults and dry-run; 100-plus API commands map one-to-one onto platform endpoints; below that, lark-cli api reaches 2,500-plus endpoints raw.

Product & ProjectContent & KnowledgeEngineering

View on GitHub ↗

Lark's Official CLI, in Three Command Tiers preview

One counter-intuitive convention: a successful JSON envelope has no code or msg field, so success reads from ok or the exit code, not the raw API's code == 0. The README carries a Read Before Use section that is blunter than most: hallucination, unpredictable execution and prompt injection are inherent risks; once authorised the agent acts as you within the granted scope and can leak sensitive data. It advises leaving the default security settings alone and keeping the bot out of group chats.

Related skills

Devil's Advocate: Only Challenge, No ComfortThe whole repository is three files, and the core is a rule set that inverts the model's default agreeableness. The claim is blunt: the danger is not that AI errs, but that it ships a bad idea with equal enthusiasm.Content & Knowledge · Product & Project +128 stars 28 Mental Models, Zero Proven to HelpThe entry point is a routing meta-skill, with another for combining models. The theory is credited by name to Munger, Meadows, Kahneman, Goldratt, TRIZ and OODA.Engineering · Content & Knowledge +1933 stars Six Skills Khazix Uses HimselfSix skills, one job each: break down a goal, clean up disk space, write research reports, track what is trending, tidy files, and write. From Khazix, founder of Xushi Media.Content & Knowledge · Product & Project19.3K stars Small, Hackable Skills for Real EngineeringThe skills Matt Pocock uses daily: get grilled until nothing is ambiguous, turn talk into a spec and linked tickets, build red-green-refactor, run hard bugs through a fixed loop. Small and hackable, not process-owning.Engineering · Product & Project205.2K stars