# Verify Docs

> Validate JSON, file paths, and settings keys across all docs

- **Type:** Skill
- **Install:** `agentstack add skill-paulo-yamagishi-claude-code-setup-verify-docs`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [paulo-yamagishi](https://agentstack.voostack.com/s/paulo-yamagishi)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [paulo-yamagishi](https://github.com/paulo-yamagishi)
- **Source:** https://github.com/paulo-yamagishi/claude-code-setup/tree/main/.claude/skills/verify-docs

## Install

```sh
agentstack add skill-paulo-yamagishi-claude-code-setup-verify-docs
```

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

## About

# Verify Docs

Validate all documentation files in the repo for correctness.

## Steps

1. **Collect files:** Glob all `.md` files in these directories:
   - `core/`
   - `projects/`
   - `templates/`
   - `skill/`
   - `.claude/skills/`
   - `.claude/rules/`

2. **Validate JSON code blocks:** For each file, extract all ` ```json ` fenced code blocks and validate each one:
   - Use `Bash(node -e 'JSON.parse(require("fs").readFileSync("/dev/stdin","utf8"))' < tmpfile)` or inline the JSON string
   - Flag: trailing commas, comments (`//` or `/* */`), single quotes, unquoted keys
   - Record file path and line number of each invalid block

3. **Validate file paths:** Extract all relative file paths referenced in the docs (patterns like `core/`, `.claude/`, `projects/`, `templates/`, `skill/`):
   - Grep for path-like references
   - Verify each referenced file or directory actually exists using Glob
   - Flag broken references with file and line number

4. **Validate settings keys:** Extract settings keys used in JSON examples (e.g., `permissions`, `allow`, `deny`, `hooks`, `mcpServers`):
   - Cross-check against `skill/SKILL.md` Section 4 (Config Reference) as the source of truth
   - Flag any key not present in the reference

5. **Validate hook events:** Extract hook event names (e.g., `PreToolUse`, `PostToolUse`, `Stop`, `SubagentStop`):
   - Cross-check against known valid events in `core/hooks-guide.md`
   - Flag unrecognized events

6. **Report:** Group all issues by file. For each issue, show:
   - File path and line number
   - Issue type: `INVALID_JSON`, `BROKEN_PATH`, `UNKNOWN_KEY`, `UNKNOWN_EVENT`
   - Description of the problem
   - If no issues found, report: "All docs passed verification."

## Source & license

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

- **Author:** [paulo-yamagishi](https://github.com/paulo-yamagishi)
- **Source:** [paulo-yamagishi/claude-code-setup](https://github.com/paulo-yamagishi/claude-code-setup)
- **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:** yes
- **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-paulo-yamagishi-claude-code-setup-verify-docs
- Seller: https://agentstack.voostack.com/s/paulo-yamagishi
- 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%.