A thoughtful CLI for Bilibili that's actually designed for AI agents to consume. It defaults to YAML output for token efficiency, has smart fallback patterns for video summarization (subtitles first, then AI summary, then audio extraction), and handles auth via local browser cookies so you're not pasting credentials around. The command surface is sensible: search, trending, user profiles, video metadata, and interactions like triple-click. What's nice is the explicit agent guidance in the docs, like keeping result sets small and preferring specific commands over broad ones. If you're building anything that needs to pull Chinese video platform data into an LLM workflow, this saves you from writing your own Bilibili wrapper.
npx -y skills add jackwener/bilibili-cli --skill bilibili-cli --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sentry/dev
degausai/wonda
github/awesome-copilot
insforge/agent-skills
github/awesome-copilot
breaking-brake/cc-wf-studio