← Back to Skills Marketplace
website-structure
by
Kostja Zhang
· GitHub ↗
· v1.5.0
· MIT-0
141
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install website-structure
Description
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 "...
Usage Guidance
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.
Capability Analysis
Type: OpenClaw Skill
Name: website-structure
Version: 1.5.0
The skill bundle 'website-structure' is a purely instructional set of guidelines for an AI agent to assist with website architecture and page prioritization. It contains no executable code, and the markdown instructions in SKILL.md are consistent with its stated purpose of SEO and UX planning, referencing standard project context files and related internal skills without any malicious directives or data exfiltration attempts.
Capability Tags
Capability Assessment
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.
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.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install website-structure - After installation, invoke the skill by name or use
/website-structure - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.5.0
Automated batch sync
Metadata
Frequently Asked Questions
What is website-structure?
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 "... It is an AI Agent Skill for Claude Code / OpenClaw, with 141 downloads so far.
How do I install website-structure?
Run "/install website-structure" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is website-structure free?
Yes, website-structure is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does website-structure support?
website-structure is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created website-structure?
It is built and maintained by Kostja Zhang (@kostja94); the current version is v1.5.0.
More Skills