seo-schema
An agent skill by AgriciDaniel, from AgriciDaniel/claude-seo. Tags: documents, markup, schema, seo, validation.
What it does
Detect, validate, and generate Schema.org structured data. JSON-LD format preferred. Use when user says "schema", "structured data", "rich results", "JSON-LD", or "markup".
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add AgriciDaniel/claude-seo --skill seo-schema
Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/AgriciDaniel/claude-seo
cp -r claude-seo/skills/seo-schema ~/.claude/skills/seo-schema
Safety box score
Grade B, low risk: 14 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is a bounded SEO schema analyzer/generator that reads a supplied page URL, parses structured data, and writes report files in the workspace. Its main risks are routine outbound fetching of the target page and execution of a referenced helper script; it does not describe secret access, privilege escalation, or external publishing.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 1 (low) | It explicitly runs a helper command: `"${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo" run parse_html.py --url <url> --json`. |
| Network access | 1 (low) | It fetches and analyzes the supplied page URL, and even documents the failure case `URL unreachable`. |
| Filesystem reach | 1 (low) | It writes workspace outputs `SCHEMA-REPORT.md` and `generated-schema.json`. |
| Secrets & credentials | 0 (none) | No step mentions tokens, passwords, dotfiles, keychains, or credential stores. |
| Privilege & persistence | 0 (none) | No sudo, service registration, global install, or shell/OS configuration changes are described. |
| Instruction hijack surface | 0 (none) | The text gives task instructions but does not tell the agent to ignore safeguards, hide actions, or follow remote instructions. |
| Irreversible actions | 0 (none) | It only reports and generates schema; nothing is sent, posted, paid, booked, or deployed. |
| Transparency | 1 (low) | The bundle references `${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo`, `../seo/references/schema-types.md`, and `schema/templates.json`, but those files are not included here. |
Before installing
- Inspect the actual helper at `${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo` and the referenced schema/template files before trusting it.
- Run it once against a public, non-sensitive URL and confirm it only fetches that page.
- Verify the only files it creates are `SCHEMA-REPORT.md` and `generated-schema.json` in the workspace.
Rated 2026-10-19 by an automated review of 3 files from the skill's repository.
Source
- Repository
- AgriciDaniel/claude-seo (all skills from this repository)
- Path
- skills/seo-schema/SKILL.md
- Branch
- main
- Collection
- claude-seo
- Updated
- 2026-09-21
Related skills
- seo-hreflang — Hreflang and international SEO audit, validation, and generation.
- seo-sitemap — Analyze existing XML sitemaps or generate new ones with industry templates. Validates format, URLs, and structure.
- schema — When the user wants to add, fix, or optimize schema markup and structured data on their site.
- seo — Comprehensive SEO analysis for any website or business type.
- seo-content — Content quality and E-E-A-T analysis with AI citation readiness assessment.
- seo-content-brief — Generate competitive SEO content briefs with per-section word counts, competitor scoring, keyword density guidance, and page-type templates.