JSON Data Analysis and Output

SkillDev tools

Patterns for analyzing and outputting structured JSON answers from enterprise data queries.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the JSON Data Analysis and Output skill

What this skill tells your AI

The instructions your AI receives, as published by cxcscmu/skilllearnbench in skills/b1-one-shot-claude-opus-4-6/enterprise-information-search/json-data-analysis/SKILL.md and read by ahel’s review.

Output Format

When answering questions from enterprise data, use this standard format:

{
  "q1": {"answer": ["item1", "item2"], "tokens": 123},
  "q2": {"answer": ["item1"], "tokens": 456}
}

Key Rules

  • Every answer is a list, even single items
  • Token counts are numeric values (not strings)
  • Employee IDs are strings like "eid_abc123"
  • URLs are full strings including protocol

Python Verification

import json
with open('answer.json') as f:
    data = json.load(f)
for k, v in data.items():
    assert isinstance(v['answer'], list)
    assert isinstance(v['tokens'], (int, float))

Signals

GitHub stars
83
Forks
5
Last commit
Jul 2026
Advanced
Catalog kind
skill
Gateway key
json-data-analysis
Source
github.com/cxcscmu/skilllearnbench