json-flat-tool

json-flat-tool is an Agent behaviour & coding discipline skill for AI agents, published by DoiiarX in the claude-skills repository on GitHub. Skillspace rates json-flat-tool D (59/100) and it passed the safety scan; the rating is based on static analysis only.

JSON flat view, schema inference, and edit tool. ⚠ CRITICAL: ALWAYS use jstool for JSON files - NEVER use read/edit/cat on *.json! **Strongest trigger — editing any JSON config file**: when the user asks to change, add, set, update, or remove a field in a `.json` configuration (config.json, settings.json, package.json, tsconfig.json, appsettings.json, .eslintrc, openclaw.json, mcp.json, any tool's `*.json` config), invoke this skill instead of opening the file in a text editor. Reading the whole file, hand-editing braces, or rewriting it from memory all break formatting and risk silent corruption — jstool gives you a structural diff preview before applying. Also use when the user provides JSON data in ANY form and wants to explore its structure, infer its schema, modify fields, or search keys/values. This includes: - JSON files on disk (view, inspect, search) - JSON configuration files (any *.json config — see above) - Editing / updating fields (set key, delete key, insert array…

Grade
D
Quality
59 / 100
Safety
Passed
GitHub stars
20

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubDoiiarX/claude-skills

Our review

Architecture
80 / 100
Maturity
Structured: ships references or scripts
Security scan
Low-risk patterns
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Agent behaviour & coding discipline

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.