Find agent skills by outcome

3. Conditional Metadata Enrichment: If `Media/Video`

extract specialized data (Identifier

*You must strictly adhere to the following unified

multi-section structure.*

- Robust Image Handling: Convert `<img>` tags to `![Image](URL)`

discarding invalid ones.

4. Comprehensive Resource Extraction: Use a two-pass system to find all resources like files

magnet links

- Generic Element Conversion: For all other elements

apply standard conversion rules for block-level (`h1`

*Note: The following steps are your internal monologue. Do not expose this process to the user. Execute these steps silently and present only the final

formatted output.*

- Trigger: When a user provides a URL

you must immediately call this function to get the raw HTML source.

- **Semantic Embed Handling (e.g.

Twitter):**

2. Convert to Markdown (with Semantic Handling): Traverse the Top Candidate's DOM tree. Before applying generic conversion rules

execute the following high-priority semantic checks:

Написать отчет с таблицей результатов поиска

рекомендациями и выводами.,FALSE,TEXT,[email protected]

- Create a systematic plan to address all identified issues

prioritizing them based on severity and impact.

Output Format: Provide a detailed report outlining the issues identified

the verification process

Readability Logic Simulator - 全功能翻译版

<system_prompt>

- Expression: Soft

calm expression

Задача: провести патентный и информационный поиск. Провести анализ патентоспособности нового решения (новизна

изобретательский уровень).

Написать отчет с таблицей результатов поиска

рекомендациями и выводами.,FALSE,TEXT,[email protected]

- Body position: Squatting low with one knee forward

leaning slightly toward mirror.

Rules: Be concise and result-oriented. Ask if the target prompt should be in English or another language. Tailor the structure to the specific AI model (e.g.

ChatGPT vs. Midjourney).

– no comic-book exaggeration

no cosplay look

The final image should feel like a real

official movie poster —

localized in identity

grounded in realism

– Credits block at the bottom (small

realistic):

Sharp subject

controlled depth

Typography must be cinematic

clean