Explore

Find agent skills by outcome

117,329 skills indexed with the new KISS metadata standard.

Showing 24 of 117,329Categories: Cursor-rules, General, Writing & Content, Coding & Debugging

Coding & Debugging

PromptBeginner5 minmarkdown

Your objective is to reverse-engineer why a given product

landing page

Apr 2, 2026

Coding & Debugging

PromptBeginner5 minmarkdown

RULE: When using this prompt

you must create a file named `TODO_visual-media-analysis.md`. This file must contain the findings resulting from this research as checkable checkboxes that can be coded and tracked by an LLM.,TRUE,TEX...

Find agent skills by outcome

Your objective is to reverse-engineer why a given product

**RULE:** When using this prompt

- Provides machine-precise specifications (HEX codes

- Segments multi-shot video inputs into individual scenes

- Treats every frame as a forensic evidence surface

- [ ] Object inventory includes specific counts

Before finalizing

- [ ] All six analysis perspectives (forensic

- **Sound Inference**: Ambient

- **Cinematic Analysis**: Framing

- **Editorial Inference**: Rhythm

Use checkboxes and stable IDs (e.g.

- **Input Type**: Image

Use checkboxes and stable IDs (e.g.

- The scope of analysis requested (full multi-perspective analysis

- The visual input being analyzed (image

Write all proposed analysis findings and any structured data to `TODO_visual-media-analysis.md` only. Do not create any other files. If specific output files should be created (such as JSON exports)

In `TODO_visual-media-analysis.md`

- **Ignoring text in frame**: Failing to OCR visible text on screens

- **Generic lighting descriptions**: Stating the scene is well lit instead of mapping key

- **Missing HEX color values**: Providing color descriptions without specific HEX codes (e.g.

- Editor's pacing analysis with rhythm classification

- Cinematographer's technical analysis with framing

- Director's narrative deconstruction with dramatic structure

RULE: When using this prompt

- Sound Inference: Ambient

- Cinematic Analysis: Framing

- Editorial Inference: Rhythm

- Input Type: Image

- Ignoring text in frame: Failing to OCR visible text on screens

- Generic lighting descriptions: Stating the scene is well lit instead of mapping key

- Missing HEX color values: Providing color descriptions without specific HEX codes (e.g.