AgentClaw

Generate, edit, and iterate raster images from text prompts or reference images with GPT Image, Nano Banana, or Seedream. Use for visual asset creation, concept art, product/mockup imagery, style exploration, thumbnails, illustrations, and image transformation workflows across image provider APIs.

Create or modify AgentClaw workflows and agents from natural-language requirements. Use when changing workflow architecture, nodes, prompts, persona, routing, tool/skill configuration, runtime behavior, validation gates, registration, or project wiring.

Run existing workflows via local /_internal/* relay; relay handles internal authentication. Use AgentClaw platform APIs for workflow/agent execution, scheduler automation, traces/logs, knowledge bases, channels, conversations, files, prompts, models, and hot registration.

Use the ClawHub CLI to search, install, update, list, authenticate, and publish reusable AgentClaw/OpenClaw skill packages. Use when you need to fetch skills on the fly, acquire skill dependencies, sync installed skills to latest or a specific version, or publish new/updated skill folders.

Inspect, edit, test, refactor, and validate project code inside the configured project directory. Use when the task involves source search, code reading, bug fixes, implementation changes, syntax checks, automated tests, file moves, or refactors.

Create or modify AgentClaw skill packages. Use when changing skill scope, trigger descriptions, bundled references, scripts, assets, metadata, packaging, documentation, validation, or distribution.