OpenAgentSkill Registry Manifest
Skill: Stepfun Vision Skill
Slug: jwangkun-stepfun-vision-skill
Category: utility
Description: Codex Skill：让纯文本模型（DeepSeek）借助 StepFun step-3.7-flash 获得看图能力 | Give text-only Codex models (DeepSeek) image understanding via StepFun step-3.7-flash

Agent fit:
- Decision: 65/100 Prototype first
- Primary fit: Multimodal media
- Role: Fallback candidate

Supply profile:
- Track: Coding and developer agents
- Scenario: Coding agents
- Applicable agents: Claude Code, OpenAI Agents, Cursor, CLI, Codex
- Maintenance: 19d since push
- Risk: Needs review

Trust:
- Trust score: 76/100 Strong shortlist
- Audit: 80/100 Needs review

Attribution:
- Status: Community indexed
- Source: OpenAgentSkill auto-indexer
- Creator: jwangkun
- Claim URL: https://www.openagentskill.com/skills/jwangkun-stepfun-vision-skill#claim-this-skill

Install:
npx skills add jwangkun/stepfun-vision-skill

URLs:
- Web: https://www.openagentskill.com/skills/jwangkun-stepfun-vision-skill
- API: https://www.openagentskill.com/api/agent/skills/jwangkun-stepfun-vision-skill
- Install API: https://www.openagentskill.com/api/skills/jwangkun-stepfun-vision-skill/install
- Repository: https://github.com/jwangkun/stepfun-vision-skill