by wchao6891 · MCP Server · ★ 101
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 101 |
| Forks | 16 |
| Language | JavaScript |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 60/100 |
| Last Updated | 2026-10-22 |
| Created | 2026-07-19 |
| Platforms | browser, claude-code, cli, codex, mcp, node |
| Est. Tokens | ~15k |
English · 简体中文 Turn great references into your next creation. One-click capture. A visual prompt library. Ready for your Agent.Collect from Jimeng, Higgsfield, X, HeyBox, WeChat articles, Feishu docs and more.Keep the image, the prompt and the context — then put them to work in your next project.
Looking for a PromptDirector alternative? If you're comparing PromptDirector with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
做企业 AI 视频项目逼出来的工具包 · 411 prompt · 15 模型 · 7 Claude Skill · 14 篇方法论
Claude Code Skill that turns any idea into a cinematic, model-ready video prompt — Sora · Kling · Veo · Seedan
OnlyShot · 神仙鱼 AI 短剧工业流水线 Claude Skill — 一句话 → 剧本/分镜/分镜图/视频/剪辑 五步 → 可发红果抖音的完整短剧。集成即梦/Seedance，17 失败模式沉淀。
10 Claude skills that generate studio-quality AI video prompts for Seedance 2.0 on Higgsfield. Viral hooks, Sa
Zero-skill cinema. Senior-director prompts on autopilot. A Claude Code Skill for high-quality AI image / video
创意→完整短剧剧本→Seedance 2.0 视频提示词 全链路 Claude Skill：上游写 50-100 集短剧剧本，下游转标准剧本/资产/分镜；含 12 铁律 + 17 模板 + 视听语言·去AI感·人物真实感
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: