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

Self-Hosting Guide

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

CLAUDE.md

Quick reference for Claude Code when working on prompts.chat

Contribution Guidelines

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

Docker Deployment Guide

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

.vercelignore

packages/

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

/node_modules

Dependencies

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/

4. Maintain the chronological order (Scene 1

Scene 2

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

specific car models (Make/Model/Year)

Lens:* (e.g.

Anamorphic

If the input is a video containing multiple distinct shots

camera angles

* Framing & Lensing: Focal length (24mm

50mm

Settings:* (Est. ISO

Shutter Angle

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

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

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

1 vintage Rolex watch

2. Generate a separate

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

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

Master Cinematographer

For each detected scene/shot

analyze the following deep-dive sections:

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

street signs

* Optical Analysis: Estimated Focal length (e.g.

35mm