Find agent skills by outcome

解除封印咒语

2-19 https://github.com/PlexPt/awesome-chatgpt-prompts-zh/issues/29#issuecomment-1435914782

一些有趣的玩法

可以写代码，写小说，写作文、演讲稿、工作报告、读书笔记、合同、菜谱等

tmp

.idea

Docker Deployment Guide

Run your own prompts.chat instance with a single command.

.vercelignore

packages/

Self-Hosting Guide

- Curated Prompt Library — Access 100+ high-quality, community-tested prompts for ChatGPT, Claude, Gemini, Llama, Mistral, and other AI models

Contribution Guidelines

Thank you for your interest in contributing to Awesome ChatGPT Prompts!

CLAUDE.md

Quick reference for Claude Code when working on prompts.chat

Dependencies

node_modules

See https://help.github.com/articles/ignoring-files/ for more about ignoring files.

/node_modules

Third-Party Notices

THE FOLLOWING SETS FORTH ATTRIBUTION NOTICES FOR THIRD PARTY SOFTWARE THAT MAY BE CONTAINED IN PORTIONS OF THIS PRODUCT.

Note: This repository contains Anthropic's implementation of skills for Claude. For information abou...

.DS_Store

pycache/

Role: You are an elite visual analysis AI capable of acting simultaneously as a Director

Master Cinematographer

* OCR & Text Detection: Transcribe ANY visible text (license plates

street signs

Settings:* (Est. ISO

Shutter Angle

2. Generate a separate

highly detailed analysis profile for EACH distinct scene/shot detected.

* Object Inventory: List distinct key objects present (e.g.

1 vintage Rolex watch

For each detected scene/shot

analyze the following deep-dive sections:

* Subject Biology/Physics: Estimate age/gender of characters

specific car models (Make/Model/Year)

If the input is a video containing multiple distinct shots

camera angles

* Micro-Beats & Emotion: Breakdown of action into seconds (e.g.

00:01 turns head). Analysis of internal feelings and body language.

* Framing & Lensing: Focal length (24mm

50mm

4. Maintain the chronological order (Scene 1

Scene 2