← all publishers

dimthink

@dimthink source repo

Report this profile Claim this profile

• 3 skills
• 0 followers
• 11 hours ago last updated

1. ▌
   LLM Call · dimthink bundle

   Call external LLM APIs (DeepSeek, Qwen, OpenAI-compatible) from Claude Code without consuming Opus tokens. Use when user says: "use DeepSeek to translate", "summarize with a cheap model", "batch translate files", "use qwen to polish", or any request to call their own model APIs for translation, summarization, polishing, or explanation tasks. Also triggers on first use for interactive setup.
   0
   installs
2. ▌
   Media Gen · dimthink bundle

   AI media generation with 4 atomic capabilities: text-to-image, image-to-image, text-to-video, image-to-video. Supports Gemini (via flow2api) and GPT (via CPA/Codex) image providers, plus Veo 3.1 video models. Auto-selects model by aspect ratio, LLM prompt enhancement, batch generation with concurrency=5. Use when user asks to generate images, create videos, draw, paint, animate, or produce any visual media content.
   0
   installs
3. ▌
   Transit Onboard · dimthink bundle

   核验并录入 PriceAI API 中转站，默认保存为后台待审核草稿，同时完成公开价格与监测来源发现、定价归一化和冲突标记、配置与回归测试、单站采集入库、Huoshan2 collector runtime 同步及生产验收。用于用户提供中转站网址、New API/Sub2API 系统信息、站长资料，要求“补充中转站”“录入后台”“先别展示前台”“等我审核后上架”，或在审核后明确要求启用前台展示与定时采集时。
   0
   installs