ClawHub

Schema Markup

v1.0.0

When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured da...

⭐ 0· 93·0 current·0 all-time
byMario Karras@mariokarras
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name, description, and content align: the skill provides guidance, templates, examples, and testing advice for schema/structured data. It does not request unrelated credentials, binaries, or install actions that would be inconsistent with its purpose.
✓
Instruction Scope
Runtime instructions stay on-topic (choose schema types, produce JSON-LD, validate with public tools). The only file access it mentions is checking for a local product-marketing-context file (.agents/product-marketing-context.md or .claude/product-marketing-context.md) to reuse existing context — this is relevant to producing accurate markup. It does not instruct the agent to read arbitrary system paths, secrets, or send data to unexpected endpoints.
✓
Install Mechanism
No install spec or code files that would write executables to disk; instruction-only reduces install risk.
✓
Credentials
The skill declares no environment variables, credentials, or config paths. Its guidance references public validation tools (Google, Schema.org) which is appropriate for the task.
✓
Persistence & Privilege
Skill is not force-enabled (always: false) and is user-invocable. disable-model-invocation is default (allows autonomous invocation) — this is platform-normal and not by itself a red flag, but see user guidance.
Assessment
This is an instruction-only, coherent schema/JSON-LD helper that does not request keys or install code. It does instruct the agent to look for a local product-marketing-context file (if present) to reuse project context — consider whether that file may contain sensitive information before allowing the skill to access your workspace. Also note the skill can be invoked autonomously by the agent (platform default); if you prefer tighter control, disable autonomous skill invocation in your agent settings before installing.

Like a lobster shell, security has layers — review code before you run it.

latestvk97fhg1zzckwvzbf28hy8h09jd837dj0

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments