ClawHub

website-structure

v1.5.0

When the user wants to plan website structure, decide which pages to build, or prioritize pages for a new or existing site. Also use when the user mentions "...

⭐ 0· 92·0 current·0 all-time
byKostja Zhang@kostja94
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
CryptoCan make purchases
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (website structure planning) match the SKILL.md content. The skill's checks (project type, stage, growth strategy), page taxonomy, and references to page-generator skills are all coherent with its stated purpose; it does not ask for unrelated credentials or binaries.
ℹ
Instruction Scope
The runtime instructions direct the agent to read local project context files if present (.claude/project-context.md or .cursor/project-context.md) and to consult local docs paths (e.g. ../../../docs/). Reading project context for planning is reasonable, but this grants the skill read access to workspace files — confirm you are comfortable with the agent seeing files in the working directory and that those project-context files do not contain secrets.
✓
Install Mechanism
No install spec or code is present; this is instruction-only and does not write to disk or download external packages, which minimizes install-time risk.
✓
Credentials
The skill requires no environment variables, credentials, or config paths. The lack of requested secrets is proportionate to its stated functionality.
✓
Persistence & Privilege
always is false and the skill does not request persistent system changes or cross-skill configuration. It can be invoked autonomously (platform default), which is expected for skills but not excessive here.
Assessment
This skill appears coherent and low-risk: it only contains prose instructions for planning site structure and requests no credentials or installs. Before enabling, confirm you are comfortable with the agent reading project-context files in the workspace (the SKILL.md explicitly instructs reading .claude/project-context.md or .cursor/project-context.md). If those files might contain private keys, API tokens, or other secrets, remove or sanitize them first. If you want to limit file access, test the skill in a sanitized/project-copy workspace. Finally, note the skill references other "page-generator" skills and docs; check those other skills separately if you plan to use them.

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

latestvk97a9ge0ndskhmcxkgxcn3tgxx84hnsd

License

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

Comments