feat: image-only pipeline with LLM post-filter for category accuracy
#11:Commit
6bc4e1d3b4
pushed by
ivang
docs: remove frame-extraction workflow from SKILL.md, keep video-direct approach only
#10:Commit
e9e1f01728
pushed by
ivang
feat: add detect-video command using direct video upload + API analysis
#9:Commit
db4735e54e
pushed by
ivang
skill: translate user-facing docs to Chinese, add detect-best commands
#8:Commit
91a623751d
pushed by
ivang
feat: use OpenClaw sub-agent for slow detect commands, fix keyword generation
#4:Commit
778a51ad45
pushed by
ivang
refactor: remove VISION_API_KEY/BASE env overrides, all credentials from client config only
#3:Commit
9f381f9bab
pushed by
ivang