ClawHub

meta-description

v1.4.0

When the user wants to optimize the meta description or meta tag description. Also use when the user mentions "meta description," "meta desc," "page descript...

⭐ 0· 59·0 current·0 all-time
by@kostja94
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 and description match the SKILL.md content. All guidance (length-by-language, CTA, uniqueness, GSC-driven optimization) is appropriate for a meta description optimization helper; no unrelated credentials, binaries, or installs are requested.
✓
Instruction Scope
Runtime instructions are limited to SEO guidance and producing recommended meta descriptions. The only file reads it suggests (.claude/project-context.md or .cursor/project-context.md) are reasonable for obtaining brand voice/keywords and are coherent with the stated purpose. It does not instruct the agent to collect unrelated system data or transmit data to unexpected endpoints.
✓
Install Mechanism
No install spec and no code files — instruction-only. This minimizes disk writes and execution of third-party code.
✓
Credentials
No environment variables, credentials, or config paths are requested. References to external tools (Google Search Console, pixel checkers) are advisory and do not require implicit credentials in the skill itself.
✓
Persistence & Privilege
always is false and the skill does not request elevated or permanent presence. Model invocation is enabled (the platform default) which is expected for user-invocable skills; nothing in the skill attempts to modify other skills or system-wide settings.
Assessment
This skill appears coherent and low-risk: it merely contains guidance for writing meta descriptions and asks the agent to consult local project-context files if present. Before installing, consider: (1) ensure .claude/project-context.md or .cursor/project-context.md do not contain sensitive secrets you wouldn't want the agent to read, (2) avoid supplying search-console or analytics credentials to the skill unless you intend the agent to perform live clicks/CTR analysis, and (3) if you prefer tighter control, keep the skill user-invocable only (don’t enable autonomous invocation) so it runs only when you explicitly call it.

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

latestvk979bpn5fya8ahwqmkvg1sxad18496kn

License

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

Comments