ClawHub

Nm Abstract Modular Skills

v1.8.3

Build composable skill modules with hub-and-spoke loading

⭐ 0· 84·1 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
Name/description (modular/hub-and-spoke skill design) match the content: guidance, templates, and examples for modular skills. The documents reference tooling and patterns that are coherent with the stated purpose.
ℹ
Instruction Scope
SKILL.md and module pages instruct running various scripts (skill-analyzer, token-estimator, module_validator, etc.) and reference relative paths and shared modules. Those scripts are not included in this package (the skill is instruction-only), so using the provided commands requires additional repository files or a separate plugin. The enforcement-patterns content recommends strong 'YOU MUST' style enforcement in some categories, which can cause an agent to prefer this skill aggressively—this is a behavioral design choice rather than a direct security issue.
✓
Install Mechanism
No install spec and no code files are included. That minimizes risk: nothing is downloaded or written to disk by an installer in this package.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. The instructions do not ask for secrets or unrelated system credentials.
✓
Persistence & Privilege
always is false and the skill does not request persistent system presence or elevated privileges. It does not attempt to modify other skills or global agent config.
Assessment
This is a documentation-only skill for designing modular skills; it does not request secrets or install code. Before relying on its command examples, confirm the referenced scripts (skill-analyzer, token-estimator, module_validator, etc.) actually exist in your environment or repository — the SKILL.md assumes those tools are available elsewhere. Also be aware the enforcement-patterns module recommends strong, prescriptive trigger language (e.g., 'YOU MUST'), which can make an agent prefer this skill inappropriately; review and soften enforcement language if you want more balanced behavior. If you plan to run any scripts the documentation references, inspect those script files first (in the source repo or plugin) so you know what filesystem or network access they perform.

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

latestvk97133b5rjwy29anrkae1ger3584k1gt

License

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

Runtime requirements

🦞 Clawdis

Comments