copy-editing
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily instructional, providing a structured framework ('The Seven Sweeps') for the AI agent to follow when editing marketing copy. It does not contain executable code, scripts, or network operations.
- [SAFE]: It implements localized context awareness by checking for product-marketing documentation within the project (e.g.,
.agents/product-marketing.md), which is a standard practice for project-specific agents. - [SAFE]: The skill uses relative filesystem paths (e.g.,
../deslopify-writing/SKILL.md) to reference shared editorial rules, promoting consistency across a local skill library without relying on external or remote sources. - [SAFE]: Comprehensive evaluation data is provided in
evals.json, confirming the skill's intended behavior focuses on editorial quality, tone consistency, and removing formulaic writing patterns.
Audit Metadata