site-crawlability
v1.2.1When the user wants to improve crawlability, fix orphan pages, or optimize site structure for search engines. Also use when the user mentions "crawlability,"...
⭐ 0· 91·0 current·0 all-time
byKostja Zhang@kostja94
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description match the content: the SKILL.md contains detailed, focused technical-SEO guidance (robots, redirects, sitemaps, pagination, internal links, SSR) and references related SEO sub-skills. There are no unrelated requirements (no env vars, no binaries).
Instruction Scope
Runtime instructions are prose guidance and checklists. They ask the agent to read project context files if present (.claude/project-context.md or .cursor/project-context.md) and to audit site assets like robots.txt, sitemap, and URLs — all reasonable and relevant to crawlability. The SKILL.md does not instruct the agent to access unrelated system files, request secrets, or transmit data to unknown endpoints.
Install Mechanism
No install spec and no code files — the skill is instruction-only, so nothing is written to disk or downloaded. This is the lowest-risk install profile.
Credentials
The skill declares no required environment variables, credentials, or config paths. The guidance references public web resources and site files only; no secret access is requested or implied.
Persistence & Privilege
always is false and default autonomous invocation is allowed (platform default). The skill does not request persistent system modification or cross-skill configuration changes.
Assessment
This skill appears internally coherent and low-risk: it is a text-only SEO playbook that asks the agent to inspect site files and project-context docs and requires no credentials or installs. Before enabling: (1) confirm the project-context files (.claude/project-context.md, .cursor/project-context.md) contain no sensitive data you wouldn't want an agent to read; (2) note the skill's source is unknown/has no homepage — if provenance matters, prefer skills from known publishers; (3) consider invoking it first on a non-sensitive/test project; (4) if you are uncomfortable with autonomous runs, disable autonomous invocation for this skill in your agent settings.Like a lobster shell, security has layers — review code before you run it.
latestvk97egd9sjc0w02jwph4my8qbms84b364
License
MIT-0
Free to use, modify, and redistribute. No attribution required.