LilBot-agent

Help with Claude/LLM API usage, models, and integration patterns.

Scaffold or plan LilBot-style local plugins.

Break a large request into a tracked batch of smaller tasks.

Coordinate browser-assisted work when a Chrome/browser connector is available.

Investigate a bug or failing behavior and isolate the likely cause.

Use subagents to split exploration, implementation, review, and verification work.

Create, inspect, edit, or convert document-style deliverables.

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and API setup.

Explain or design keyboard shortcut bindings.

Set up a recurring check or repeated agent workflow.

Generate placeholder copy with controllable tone and length.

Design, build, configure, or debug Model Context Protocol servers.

Read, extract, split, merge, rotate, watermark, fill, OCR, or create PDF files.

Create, edit, inspect, or convert slide decks and PPTX-style presentations.

Decide whether user information should become durable memory.

Generate a complete skill package from a short request.

Schedule a future task, reminder, or remote-style agent action.

Simplify code, prose, or a plan without changing its intent.

Create or improve LilBot skills and decide when a skill is the right abstraction.

Install, update, trust, or inspect local/community skill folders.

Turn a repeated workflow into a reusable LilBot SKILL.md.

Create, inspect, clean, analyze, or convert spreadsheet and tabular files.

Recover when progress stalls or the agent may be looping.

Help inspect and update LilBot project or user configuration.

Use for DeepSeek V4-style multi-step or plan-driven tasks.

Verify that implementation work is correct before reporting done.