Json extraction
Skill to extract information from the structured JSON data, including Slack messages and document metadata.From its SKILL.md
npx -y skills add cxcscmu/SkillLearnBench --skill json-extractionAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
1.5 KB, 304 tokens by cl100k_base, as published. Nobody here has run it
JSON Extraction Skill
This skill covers how to efficiently navigate and extract information from the enterprise data JSON files.
Data Structure
The product data files (e.g., /root/DATA/products/Product.json) typically have the following structure:
slack: A list of channel messages. Each message has aUser,text, andtimestamp.documents: A list of document metadata, includingauthor,date,type, andcontent.meeting_transcripts: Transcripts of meetings.urls: Shared URLs and their descriptions.
Techniques
Extracting Document Authors and Reviewers
- Search the
documentslist for a specifictype(e.g., "Market Research Report"). - Identify the
authorfield. - Search
slackmessages around the document'sdateto find discussions and feedback. - Users who provide specific suggestions or critiques in the Slack threads are considered reviewers.
Identifying Competitor Insights
- Search
slackmessages andmeeting_transcriptsfor keywords like "competitor", "strengths", "weaknesses", or specific competitor names (e.g., "Salesforce", "HubSpot"). - Map the
userIdfrom those messages to identify the team members.
Finding Shared URLs
- Search the
slackmessages for "http" or "demo". - Cross-reference with the
urlslist in the JSON if available.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.