|
|
2 mēneši atpakaļ | |
|---|---|---|
| .. | ||
| .claude-plugin | 2 mēneši atpakaļ | |
| bin | 2 mēneši atpakaļ | |
| scripts | 2 mēneši atpakaļ | |
| skills | 2 mēneši atpakaļ | |
| README.md | 2 mēneši atpakaļ | |
| package.json | 2 mēneši atpakaļ | |
| skill-package-manifest.json | 2 mēneši atpakaļ | |
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.
Project workspace (writes ./.claude/skills/fmode-vision/):
npx fmode-vision@latest workspace
User level for all workspaces (writes ~/.claude/skills/fmode-vision/):
npx fmode-vision@latest install
Restart the Claude Code session afterwards so it discovers the skill.
The skill auto-detects the Fmode API token in this priority order:
FMODE_API_TOKEN environment variable~/.fmode/config.json → fmodeApiToken (or newapiToken)<project>/.fmode/config.json → fmodeApiToken (or newapiToken)ANTHROPIC_AUTH_TOKEN environment 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.
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.
npm run smoke