Official Anthropic Agent Skills repo with document and example packs
Commerce Trust & Safety Rules
SkillThe guardrails Anthropic's commerce agents enforce for untrusted content, writes, identity and memory.
Clone or download it from github.com, then drop the folder into ~/.claude/skills/ (Claude Code) or your agent's skills directory.
Product badge
Share this product's name and rating in your README or on your website.
Updates may be delayed by image caching.
About Commerce Trust & Safety Rules
From Anthropic's commerce-agents repo. Lays out the rules the reference agents enforce in code: treating third-party content as untrusted, guarding write tools, grounding claims, checking identity and scoping what the agent remembers, each mapped to the module that implements it, plus two adversarial-eval rules.
No reviews yet
Used it? Write the first review.
Similar skills
Official Browserbase skills for cloud browser automation
Production agent skills from Matt Pocock's .agents directory
Official OpenAI Agent Skills for Codex and ChatGPT workflows
Official Claude document skills for Word, PDF, PowerPoint, Excel
Curated collection of 1000+ SKILL.md packs for coding agents