pingdior/text-to-image-prompt-gen3-runway
text-to-image-prompt-gen3-runway/SKILL.md
--- name: text-to-image-prompt-gen3-runway description: Guides Gen-3 Alpha Runway video generation prompts. Use when creating video prompts for Runway, text-to-video, or Gen-3 Alpha. Trigger phrases: "Gen-3 Alpha", "Runway", "文生图", "视频提示词" metadata: author: [email protected] version: 1.0.0 --- # Gen-3 Alpha Prompt Guide - Runway ## Overview Gen-3 Alpha can turn artistic visions into video. Creating powerful prompts that convey scenes is key to generating video that matches your concept.
$ install --global
skillsauthnpx skillsauth add pingdior/usingskills text-to-image-prompt-gen3-runwayInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 6, 2026, 6:35 AM164.2s1 file scanned
SKILL.md
- name:
- text-to-image-prompt-gen3-runway
- description:
- Guides Gen-3 Alpha Runway video generation prompts. Use when creating video prompts for Runway, text-to-video, or Gen-3 Alpha. Trigger phrases: "Gen-3 Alpha", "Runway", "文生图", "视频提示词
- author:
- [email protected]
- version:
- 1.0.0
Gen-3 Alpha Prompt Guide - Runway
Overview
Gen-3 Alpha can turn artistic visions into video. Creating powerful prompts that convey scenes is key to generating video that matches your concept.
Prompt Basics
Direct, Not Conceptual
Describe as if to a new collaborator who will shoot the scene. Avoid conceptual language when simple description works.
❌ 一名男子侵入了主机 → ✅ 一名男子在键盘上用力打字
Descriptive, Not Conversational
Runway models focus on visual details. Dialogue adds no value.
❌ 你能给我制作一段关于两个朋友吃生日蛋糕的视频吗？ → ✅ 两个朋友吃生日蛋糕
Positive Wording
No negative prompts. Model doesn't support "what should NOT happen."
❌ 相机不动。没有动作。 → ✅ 静态相机。相机保持静止。
Structure
[Camera movement]: [Establish scene]. [Additional details].
Example: "Low angle static shot: The camera is angled up at a woman wearing all orange as she stands in a tropical rainforest with colorful flora. The dramatic sky is overcast and gray."
Image + Text
When using input images: use simple, direct text describing movement only. Do NOT describe image contents.
Example: "Subject cheerfully poses, her hands forming a peace sign."
Keywords
- Camera: Low angle, High angle, Overhead, FPV, Hand held, Wide angle, Close up, Macro, Tracking, 50mm lens, SnorriCam
- Lighting: Diffused, Silhouette, Lens flare, Back lit, Side lit, [color] gel lighting
- Movement: 成长, 出现, 爆炸, 上升, 波动, 扭曲, 变换, 涟漪, 破碎, 展开, 涡流
- Style: 穆迪, 电影, 彩虹色, 家庭录像VHS, 故障核
- Text: 大胆的, 涂鸦, 氖, 校队, 刺绣
Bracket Placeholders
Use brackets for reusable presets: 摄像机无缝飞过[拍摄对象位置]
Usage Example
User input: "生成一个冰川峡谷到云海的转场视频" AI action: Applies structure, uses positive wording, outputs prompt with camera + scene + details Expected result: Runway-ready prompt for Gen-3 Alpha
Related Skills
pingdior/xiaohongshu-trending-content-script
documentation
VerifiedTrustedCommunity
--- name: xiaohongshu-trending-content-script description: Generates Xiaohongshu viral copy and 2-minute voiceover scripts through multi-turn dialogue. Use when creating Xiaohongshu content, analyzing viral elements, or writing high-engagement posts. Trigger phrases: "小红书爆款", "爆款文案", "口播脚本", "小红书流量" metadata: author: [email protected] version: 1.0.0 --- # Xiaohongshu Trending Content Script Master ## Overview Expert at generating Xiaohongshu viral copy through guided multi-turn dialogue.
4SKILL.mdUpdated May 6, 2026
pingdior/xiaohongshu-platform-card-output
testing
VerifiedTrustedCommunity
--- name: xiaohongshu-platform-card-output description: Converts long content into Xiaohongshu/Instagram style visual cards. Use when creating social media card series, knowledge cards, or visual content for Xiaohongshu. Trigger phrases: "小红书卡片", "系列卡片", "视觉卡片", "4:5画布" metadata: author: [email protected] version: 1.0.0 --- # Xiaohongshu Style Card Generator ## Overview Professional Xiaohongshu/Instagram content designer. Transforms long content into visual card series. Outputs both Chin
4SKILL.mdUpdated May 6, 2026
pingdior/wechat-video-trending-content-script
testing
VerifiedTrustedCommunity
--- name: wechat-video-trending-content-script description: Generates viral WeChat Video (视频号) scripts with platform-specific optimization. Use when creating short-form video content for WeChat Video, designing hooks, or optimizing for social recommendation. Trigger phrases: "视频号", "爆款脚本", "微信视频", "黄金3秒" metadata: author: [email protected] version: 1.0.0 --- # WeChat Video Trending Content Script Master ## Overview Expert at generating viral WeChat Video scripts. Adapts to platform's "st
4SKILL.mdUpdated May 6, 2026
pingdior/visual-model-card-designer
testing
VerifiedTrustedCommunity
--- name: visual-model-card-designer description: Transforms long content into logic-model or minimal-graphic vertical cards. Use when creating visual summaries, social media cards, or diagram-based content. Trigger phrases: "视觉卡片", "逻辑模型", "竖屏卡片", "图解" metadata: author: [email protected] version: 3.1 --- # Visual Model Card Designer ## Overview Transforms long content into "logic model" or "minimal graphic" style vertical cards. Prioritizes diagrams over pure text. All graphics must use
4SKILL.mdUpdated May 6, 2026