fmode-vision
v0.1.1
Published
Claude Code skill: analyze images and videos via Fmode API vision models (api.fmode.cn). Single-pass and multi-pass focused analysis with structured JSON output. Auto-reads token from FMODE_API_TOKEN, ~/.fmode/config.json, project .fmode/config.json, or A
Readme
fmode-vision
Claude Code skill for analyzing images and videos via Fmode API vision models (api.fmode.cn). Supports single-pass analysis, multi-pass focused analysis with intermediate caching, video-frame analysis, batch processing, and a renovation room-measurement (毛坯房量尺) 5-pass prompt pipeline.
Install
Project workspace (writes ./.claude/skills/fmode-vision/):
npx fmode-vision@latest workspaceUser level for all workspaces (writes ~/.claude/skills/fmode-vision/):
npx fmode-vision@latest installRestart the Claude Code session afterwards so it discovers the skill.
Token
The skill auto-detects the Fmode API token in this priority order:
FMODE_API_TOKENenvironment variable~/.fmode/config.json→fmodeApiToken(ornewapiToken)<project>/.fmode/config.json→fmodeApiToken(ornewapiToken)ANTHROPIC_AUTH_TOKENenvironment variable (zero-config inside Claude Code, since it is the same Fmode gateway token)
If none are found, the skill returns a clear message listing these four options.
Usage
In Claude Code, just ask in natural language, e.g.:
帮我分析这张图片里的关键内容,输出结构化信息。The skill calls POST https://api.fmode.cn/v1/chat/completions with the default vision model doubao-seed-2-0-pro-260215. Usage is billed against the Fmode token.
Verify
npm run smoke