# Json Data Config

> Validate, format, and manipulate JSON (configs, payloads, n8n workflows, AI responses).

- **Type:** Skill
- **Install:** `agentstack add skill-agent-kit-startup-agent-kit-json-data-config`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [agent-kit-startup](https://agentstack.voostack.com/s/agent-kit-startup)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [agent-kit-startup](https://github.com/agent-kit-startup)
- **Source:** https://github.com/agent-kit-startup/agent-kit/tree/main/registry/skills/community/json-data-config

## Install

```sh
agentstack add skill-agent-kit-startup-agent-kit-json-data-config
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# JSON - Config and payloads

**Routing:** small, in-scope JSON change: apply this skill in the main window. Large or isolated batch (or when it needs its own context): hand to the `json-guardian` Task subagent (demoted, dogfood-only). Docs work routes to the `docs-repo` agent; security review of payloads to `security-reviewer`.

## Valid JSON

- Double quotes on keys and strings; commas between items; no trailing comma; correct escaping (`\"`, `\n`).
- JSON does not support comments; use `_comment` key if you need notes in the object.

## Recommended patterns

- **AI response parsing:** remove markdown blocks (`` ```json ``), extract first `{ ... }`, handle `\n`/`\"`; return object with error handling (try/catch, clear message).
- **Configs:** unit structures, mappings; maintain consistent names (e.g., mapping-*.json).
- **n8n workflows:** JSON with `nodes`, `connections`, `settings`; keep readable (indented) when editing manually.

## Best practices

- Validate before saving (syntax); when available, follow schema (config or API).
- In parsing code: always try/catch; error message with relevant excerpt (e.g., first 100-200 chars of raw).
- Minification only for deploy/assets; in repo prefer readable JSON for diff and review.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [agent-kit-startup](https://github.com/agent-kit-startup)
- **Source:** [agent-kit-startup/agent-kit](https://github.com/agent-kit-startup/agent-kit)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-agent-kit-startup-agent-kit-json-data-config
- Seller: https://agentstack.voostack.com/s/agent-kit-startup
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.