Explore

Find agent skills by outcome

93,400 skills indexed with the new KISS metadata standard.

Showing 24 of 93,400Categories: Data & Insights, Data, Communication, General, Coding & Debugging

Coding & Debugging

PromptBeginner5 minmarkdown

Your objective is to reverse-engineer why a given product

landing page

Mar 21, 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

- Segments multi-shot video inputs into individual scenes

- Provides machine-precise specifications (HEX codes

- 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

- **Forensic Data**: OCR text

Use checkboxes and stable IDs (e.g.

- **Input Type**: Image

- Any known metadata provided by the requester (production title

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

Use checkboxes and stable IDs (e.g.

- The visual input being analyzed (image

In `TODO_visual-media-analysis.md`

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)

- **Unsupported metadata claims**: Asserting a specific camera model without citing supporting optical evidence (bokeh shape

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

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

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

- Cinematographer's technical analysis with framing

RULE: When using this prompt

- Sound Inference: Ambient

- Cinematic Analysis: Framing

- Forensic Data: OCR text

- Input Type: Image

- Unsupported metadata claims: Asserting a specific camera model without citing supporting optical evidence (bokeh shape

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

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

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