ClawHub

Nm Cartograph Architecture Diagram

v1.0.0

Generate Mermaid architecture diagrams from codebase structure. Use for onboarding, PR reviews

⭐ 0· 60·1 current·1 all-time
by@athola
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
The name/description (generate Mermaid architecture diagrams from a codebase) aligns with the runtime instructions: explore the codebase, build a structural model, produce Mermaid flowchart syntax, and render it. No extra binaries, credentials, or unrelated resources are requested.
ℹ
Instruction Scope
Instructions delegate code analysis to a 'codebase-explorer' agent and call an MCP renderer. This is within scope for generating diagrams, but it means the agent will read project files (default project root if no scope) and send the structural model/mermaid code to the renderer. Users should be aware that repository structure (and any paths or filenames) will be transmitted to the rendering service.
✓
Install Mechanism
There is no install spec and no code files; the skill is instruction-only, so nothing is downloaded or written to disk by the skill itself.
✓
Credentials
The skill does not require environment variables, credentials, or config paths. That is proportional to the stated purpose.
✓
Persistence & Privilege
always is false and no special persistence or system-wide changes are requested. The default ability for the model to invoke the skill autonomously remains enabled, which is platform default but not elevated by this skill.
Assessment
This skill appears coherent and does what it says: it will run a codebase analysis agent (which reads files under the provided scope, defaulting to project root), convert that model to Mermaid, and send the diagram to an MCP renderer. Before using it: (1) avoid running it on repositories containing secrets or sensitive file paths you don't want transmitted to a renderer service; (2) restrict the analysis scope to specific directories when possible; (3) verify you trust the rendering MCP/provider since structural data and generated mermaid are sent there; and (4) review generated output before sharing. No credentials or installs are required by this skill.

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

latestvk972gc2g904w0a1sgt0dsbn4kh84jts2

License

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

Runtime requirements

🦞 Clawdis

Comments