CN Content Matrix
PassAudited by ClawScan on May 10, 2026.
Overview
This appears to be a normal content-generation skill, but it can search the web, create local draft files, and produce human-sounding publish-ready posts that should be fact-checked before publishing.
Before installing, be comfortable with the skill sending topic queries to web search, reading any draft file you explicitly ask it to review, and writing generated files under ~/content-output. Review the bundled shell script before running it, avoid confidential campaign topics unless you are comfortable exposing them to search, and carefully fact-check and ethically disclose publish-ready social content.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent may search the web and create or inspect local files as part of generating or reviewing content.
The skill requests broad tool access for a content-generation workflow. The visible instructions use research, file reads, and local file writes, but some permissions such as Edit, WebFetch, and Agent are broader than the core examples require.
allowed-tools:\n - Bash\n - Read\n - Write\n - Edit\n - Grep\n - Glob\n - WebSearch\n - WebFetch\n - Agent
Use it with non-confidential topics and drafts, and confirm any file paths or edits before allowing the agent to act outside the documented ~/content-output workflow.
Users have less external provenance to rely on when deciding whether to trust the included helper script.
The registry metadata does not provide an upstream source or homepage, while the package includes a shell helper script. No remote installer or package dependency risk is shown, but provenance is limited.
Source: unknown; Homepage: none; No install spec — this is an instruction-only skill; 1 code file(s): scripts/content-check.sh
Review scripts/content-check.sh locally before executing it, and prefer installing from a known maintainer or repository when available.
Generated posts may sound like firsthand human endorsements even when the user has not personally verified the claims.
The skill intentionally optimizes generated social-media copy to appear platform-native and less AI-written. This is aligned with its content-creation purpose, but it can create audience-trust issues if used without disclosure or fact-checking.
“reads like it was written by a real KOL” and “Anti-AI Detection — built-in rules to eliminate ‘AI smell’ phrases”
Fact-check all data and product claims, disclose sponsorships or AI assistance where appropriate, and do not fabricate personal experience, credentials, or sources.