user-content-safety

The moment strangers can put content in front of other strangers, the site needs a way to hear about abuse and a way to act on it, and its rendering must not let content attack visitors.

Activate when

• Posts, comments, reviews, profiles with bios/avatars, uploads, messages, public galleries, or shared links exist.
• Not when users only see their own private data, or when content is admin-authored only.

Working alone

This skill is self-contained. Its companions (declared in its metadata) are skills whose method it may need to do its own promised work. Use of a companion can be conditional: declaring one does not mean running it. When a companion's lane applies, use the skill if it is installed; if not, follow its short entry in references/companion-methods.md and say in your report which lanes ran inline at reduced depth. Never skip an applicable lane silently. Skills mentioned here only for escalation, referral, documentation, or optional deeper follow-up are not dependencies: report the hand-off and finish honestly.

Companions: design-system-reconnaissance.

Inspect