ClawHub

keyword-research

v1.3.1

When the user wants to research keywords, find target keywords, or analyze search intent. Also use when the user mentions "keyword research," "keyword tool,"...

⭐ 0· 94·0 current·0 all-time
by@kostja94
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (keyword research, search intent, clustering) match the SKILL.md steps (autocomplete, alphabet method, SERP checks, clustering). The skill does not request unrelated binaries, credentials, or config paths.
ℹ
Instruction Scope
The runtime instructions are detailed but stay within keyword-research tasks (discovery methods, intent, clustering, SERP checks). The skill asks the agent to read project context files (.claude/project-context.md or .cursor/project-context.md) to learn product/audience—this is relevant to the task but is an unstated file-read requirement (no config path declared). There are no instructions to exfiltrate secrets or to post data to unknown endpoints.
✓
Install Mechanism
No install spec and no code files — instruction-only skills have the lowest install risk and nothing will be written to disk by an installer.
✓
Credentials
The skill requires no environment variables or credentials. It mentions using external SEO tools (Google Keyword Planner, Trends, etc.) but does not demand API keys or credentials in its manifest.
✓
Persistence & Privilege
always:false (default) and model invocation is allowed (normal). The skill does not request permanent/privileged presence or attempt to modify other skills or system-wide settings.
Assessment
This skill is coherent and low-risk: it only contains runtime instructions for SEO keyword research and asks for no installs or credentials. Two practical notes before installing: (1) it will look for and read project context files (.claude/project-context.md or .cursor/project-context.md) if present in the agent workspace — remove or redact any sensitive info from those files if you don't want them used; (2) the skill may recommend using external tools (Google Keyword Planner, Trends, SEO tools). If you later provide API keys or connect those tools, review permissions and trust the endpoint. Otherwise, it's safe to enable from a scope/privilege perspective.

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

latestvk976q9y8vw4xgasp22gr6e287n846syh

License

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

Comments