Aeo Keyword Selector
v0.1.0select a single aeo blog keyword in question format from a business topic, with architecture-first sitemap-plus-page-intent checks to avoid cannibalization,...
⭐ 0· 32·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name, description, SKILL.md, and auxiliary references all align: the skill is about keyword selection with architecture-first sitemap checks. The included parse_sitemap.py and company profile references directly support the described workflow. There are no unrelated binaries, credentials, or installs requested.
Instruction Scope
Runtime instructions stay within keyword selection and cannibalization checks: parse a sitemap, shortlist URLs, fetch pages to infer page intent, consult Semrush and SERPs as validation, then output a single decision block. The SKILL.md does instruct the agent to fetch external pages and use browser SERP inspection (which is expected for this purpose) but does not ask for unrelated system files or secrets.
Install Mechanism
This is instruction-only with no install spec. The only bundled code is a small, standard Python script (parse_sitemap.py) that reads sitemaps over HTTPS or local files using the Python standard library. No downloads from arbitrary URLs or extracted archives are present.
Credentials
The skill does not declare any required environment variables or credentials. However, the SKILL.md repeatedly references Semrush as the primary validation layer and permits browser SERP inspection. If the agent is expected to use the Semrush API or an authenticated account, credentials would be required but are not declared. This is a modest inconsistency (may be intentional if Semrush is used via public pages or the host agent already provides access).
Persistence & Privilege
No elevated persistence requested: always is false, the skill is user-invocable and allows autonomous invocation (the platform default). The skill does not modify other skills or request system-wide config changes.
Assessment
This skill appears to do what it says: it flattens sitemaps, inspects existing pages, and returns one non-cannibalizing question-format keyword decision. Two practical considerations before installing or using it: (1) Semrush is referenced as the primary validation layer but no Semrush credentials or API keys are declared — decide how the agent will access Semrush (public scraping, an existing agent capability, or you must supply an API key) and ensure that matches your security policies. (2) The skill instructs the agent to fetch site pages and perform browser SERP checks, so the agent will make outbound web requests; ensure you are comfortable with that network activity and that no sensitive internal URLs will be exposed. If you require the skill to use a specific Semrush account or avoid live browsing, clarify or supply the needed tooling/credentials and adjust the skill accordingly.Like a lobster shell, security has layers — review code before you run it.
latestvk971bqgzbbyjrwys0r6cwzs0j5846v30
License
MIT-0
Free to use, modify, and redistribute. No attribution required.