ClawHub

content-strategy

v1.1.1

When the user wants to plan content for SEO, create content calendar, or build topic clusters. Also use when the user mentions "content strategy," "content p...

⭐ 0· 82·0 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 (content strategy, topic clusters, editorial calendar) match the SKILL.md guidance. The skill does not request unrelated credentials, binaries, or installs that would be inappropriate for a content-planning helper.
ℹ
Instruction Scope
Instructions are narrowly focused on SEO content planning, topic clusters, pillar/cluster structure, and editorial calendars. The only file reads it suggests are .claude/project-context.md or .cursor/project-context.md for product/audience context — reasonable for content work but those files can contain sensitive internal info, so granting access to workspace files is the main runtime surface to review.
✓
Install Mechanism
No install spec and no code files — instruction-only. Nothing will be written to disk or downloaded during install, which minimizes risk.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. There is no disproportionate request for secrets or unrelated service tokens.
✓
Persistence & Privilege
always:false (default) and normal autonomous invocation are used. The skill does not request persistent system-wide privileges or modification of other skills' configs.
Assessment
This skill appears coherent and low-risk: it is instruction-only and asks only to read optional project-context files for useful context. Before installing, check whether .claude/project-context.md or .cursor/project-context.md (if present) contain sensitive secrets or proprietary data you don't want the agent to read; if so, remove or redact those files or avoid enabling the skill for sensitive projects. If you are concerned about autonomous agent actions, control agent invocation policies (rather than leaving the agent fully autonomous) or review outputs before publishing content.

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

latestvk970ehef1me1yqq1rc0ze87dax846f6q

License

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

Comments