ClawHub

High Quality Info Sources

v1.0.0

Build, curate, score, and maintain high-quality information source lists for AI, technology, business, or any topic. Use when the user asks to create a skill...

⭐ 0· 72·0 current·0 all-time
by@a1437707640-ui
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 and description (curating and maintaining high-quality source lists) match the skill contents: workflow, output patterns, maintenance rules, and a reference starter set. Nothing requested or installed is unrelated to that purpose.
✓
Instruction Scope
SKILL.md confines the agent to source selection, grouping, scoring, and maintenance workflows. It references the included references/ai-sources.md starter list but does not instruct the agent to read unrelated files, access credentials, call external endpoints, or exfiltrate data.
✓
Install Mechanism
No install spec and no code files — instruction-only. There is nothing written to disk or downloaded during install.
✓
Credentials
The skill declares no environment variables, credentials, or config paths. The guidance in SKILL.md likewise does not reference secrets or external service tokens.
✓
Persistence & Privilege
always is false and there is no indication the skill requests persistent agent-wide changes or modifies other skills. Normal autonomous invocation remains possible (platform default) but is not uniquely privileged here.
Assessment
This skill is instruction-only and internally coherent: it provides an opinionated workflow and a starter list for building curated source lists and does not request credentials or install code. Before enabling it, review the included references/ai-sources.md to ensure the named organizations and individuals fit your needs and regional context (and to avoid unwanted bias or controversial figures). If you’re concerned about autonomous behavior, keep 'user-invocable' usage or test the skill in a sandboxed chat first and review the outputs for accuracy and balance. If you want different regional or domain coverage, edit the reference list or prompt the agent to produce a tailored list rather than relying on the defaults.

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

latestvk975pnwa2872rv450xrnz5j70h83s99d

License

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

Comments