ClawHub

Site Architecture

v1.0.0

When the user wants to plan, map, or restructure their website's page hierarchy, navigation, URL structure, or internal linking. Also use when the user menti...

⭐ 0· 98·0 current·0 all-time
byMario Karras@mariokarras
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name and description (planning page hierarchy, navigation, URLs, internal linking) align with the contents: templates, mermaid diagrams, ASCII trees, and guidance. No unrelated binaries, env vars, or installs are requested.
ℹ
Instruction Scope
SKILL.md instructs the agent to read an optional local context file (.agents/product-marketing-context.md or .claude/product-marketing-context.md) before asking questions — this is reasonable for tailoring site architecture guidance, but it does grant the skill access to that workspace file if present. All other instructions are confined to producing hierarchies, URL maps, navigation recommendations, and Mermaid diagrams; no instructions to access unrelated system paths, credentials, or external endpoints.
✓
Install Mechanism
No install spec or code files to run; instruction-only skill. This minimizes disk writes and arbitrary code execution risk.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. The single file read requested is specific and related to the skill's function.
✓
Persistence & Privilege
always is false and the skill doesn't request persistent/system-wide privileges or modify other skills. It can be invoked autonomously (platform default), which is expected for a helper skill; that alone is not a concern.
Assessment
This skill appears coherent and low-risk. Before installing: (1) ensure any .agents/product-marketing-context.md or .claude/product-marketing-context.md files in your agent/workspace do not contain secrets (API keys, passwords) you wouldn't want read, since the skill explicitly reads them if present; (2) review the included reference templates to confirm they match your conventions; (3) if you prefer the skill not to read local context files, remove or sanitize those files or deny the skill file-read permissions in your environment. Otherwise the skill's scope and requests are proportionate to its purpose.

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

latestvk970tr0ab7j4m0ghq2bqhxn5ax836dfs

License

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

Comments