Back to list
ivanvza

json-tools

by ivanvza

A DSPy integration for the Agent Skills specification, enabling ReAct agents to dynamically discover and use modular, sandboxed skills

6🍴 0📅 Jan 24, 2026

SKILL.md


name: json-tools description: JSON processing toolkit for validating, formatting, querying, and comparing JSON data. Use when working with JSON files, API responses, configuration files, or any structured JSON data that needs parsing, validation, transformation, or comparison. license: MIT metadata: author: dspy-skills version: "1.0"

JSON Tools

A toolkit for working with JSON data using Python standard library only.

When to Use This Skill

Activate this skill when the user needs to:

  • Validate JSON syntax
  • Format/pretty-print JSON
  • Query JSON with path expressions
  • Compare two JSON files
  • Transform JSON data

Available Scripts

Always run scripts with --help first to see all available options.

ScriptPurpose
validate_json.pyCheck if JSON is valid
format_json.pyPretty-print or minify JSON
query_json.pyExtract data using path expressions
diff_json.pyCompare two JSON files

Decision Tree

Task → What do you need?
    │
    ├─ Check if JSON is valid?
    │   └─ Use: validate_json.py <file>
    │
    ├─ Format/beautify JSON?
    │   └─ Use: format_json.py <file>
    │
    ├─ Extract specific data?
    │   └─ Use: query_json.py <file> <path>
    │
    └─ Compare two JSON files?
        └─ Use: diff_json.py <file1> <file2>

Quick Examples

Validate JSON:

python scripts/validate_json.py data.json
echo '{"key": "value"}' | python scripts/validate_json.py -

Format JSON:

python scripts/format_json.py data.json
python scripts/format_json.py data.json --indent 4
python scripts/format_json.py data.json --minify

Query JSON:

python scripts/query_json.py data.json "users"
python scripts/query_json.py data.json "users.0.name"
python scripts/query_json.py data.json "config.database.host"

Compare JSON:

python scripts/diff_json.py old.json new.json
python scripts/diff_json.py config1.json config2.json --keys-only

Path Expression Syntax

The query_json.py script uses dot-notation paths:

PathDescription
keyAccess object key
0, 1, 2Access array index
key.subkeyNested access
items.0.nameMixed access
. or emptyRoot element

Examples

Given JSON:

{
  "users": [
    {"name": "Alice", "age": 30},
    {"name": "Bob", "age": 25}
  ],
  "config": {
    "debug": true
  }
}
PathResult
usersThe users array
users.0First user object
users.0.name"Alice"
users.1.age25
config.debugtrue

Input Sources

All scripts accept input from:

  • File: script.py data.json
  • Stdin: echo '{}' | script.py -
  • String: script.py --string '{"key": "value"}'

Common Use Cases

  1. Validate API response: validate_json.py response.json
  2. Pretty-print minified JSON: format_json.py api_response.json
  3. Extract config value: query_json.py config.json "database.host"
  4. Find config differences: diff_json.py prod.json staging.json

Notes

  • All scripts use Python standard library only (no external dependencies)
  • Unicode is fully supported
  • Large files are handled efficiently
  • Exit codes: 0 = success, 1 = error/invalid, 2 = differences found (diff)

Score

Total Score

60/100

Based on repository quality metrics

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

0/10
説明文

100文字以上の説明がある

+10
人気

GitHub Stars 100以上

0/15
最近の活動

3ヶ月以内に更新がある

0/10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

0/5

Reviews

💬

Reviews coming soon