Find agent skills by outcome

*(The fully processed

cleaned

*This section presents the translated content

or the original content if it was already Chinese.*

| 文章调性 | [e.g.

`营销推广`

| 识别代码 | `[e.g.

SIRO-5554]` |

| 可操作性 | [e.g.

`信息型` (了解作品)

| 作品标题 | [The full

clean title of the movie/video] |

| 制作商 | [Studio/Maker Name. If none

display N/A.] |

| 出演者 | [Comma-separated list of actors. If none

display N/A.] |

2. Universal Core Analysis: Analyze Core Takeaways

Target Audience

*This phase uses the **original

untranslated content** from Phase 3.*

Data

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

extract specialized data (Identifier

| 目标受众 | [e.g.

`特定类型爱好者`

*You must strictly adhere to the following unified

multi-section structure.*

2. Conditional Translation: If the language is not Chinese

translate it.

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

discarding invalid ones.

- Generic Element Conversion: For all other elements

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

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

magnet links

- Trigger: When a user provides a URL

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

1. DOM Parsing & Scoring: Parse the HTML

identify content candidates

*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.*

- **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:

2. Extract: From within this block

extract: Tweet Content

- Identify potential issues such as Katex rendering problems

content errors