菜单
Orchestrator agent that has comprehensive knowledge and command over all available skills in this toolkit to create complex workflows.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Fetch and store transcripts from YouTube videos for deep content analysis.
Specialized in the MLCommons Croissant metadata specification. Can generate, validate, and serialize dataset metadata into compliant JSON-LD.
Universal Numeric Fingerprint (UNF) generator. For strings, it splits into words and sorts them alphabetically to provide order-invariant fingerprints. Supports dataframes and files too.
Send results and data files to stakeholders via email.
The Visual Systems Architect is an expert in translating complex technical requirements and infrastructure setups into structured, visually intuitive architectural diagrams (Mermaid.js).
Secure GitHub Orchestrator for Croissant Toolkit. Connect any repository, discovery skills, and audit ODRL sovereignty status.
| name | orchestrator_expert |
| description | Orchestrator agent that has comprehensive knowledge and command over all available skills in this toolkit to create complex workflows. |
This skill acts as an orchestrator that leverages the full suite of specialized agents/skills to complete broad user requests. It knows the input/output schemas of every skill and sequences them efficiently.
The Orchestrator Expert knows how to use the following skills seamlessly together:
croissant_expert): Generates MLCommons Croissant metadata.navigator): Performs web searches for information gathering.nlp_expert): Handles text summarization, keyword extraction, and structural text adjustments.tester, skills-testor): Validates that other skills function correctly.transcriber): Converts audio files to text.translator): Translates text across multiple languages.youtuber): Extracts informative metadata and audio from YouTube videos.You can use the Orchestrator Expert to set up a pipeline. For example, to run the create_full_dataset workflow:
Use the Orchestrator Expert to execute the 'create_full_dataset' workflow.
Navigate the topic '[YOUR TOPIC]', extract videos with 'youtuber', transcribe the audio, translate any non-English content, summarize using 'nlp_expert', and package the final result into Croissant metadata.