Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval
70%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/recipe-front-design/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow ingests outsider-authored text only through external resources that the orchestrator selects for UI decisions (external-resource-context, Step 3), which the agent must actively fetch, so exposure is low. Codebase analysis reads the user's own repository and the other steps consume first-party or internal artifacts.
shinpr/claude-code-workflows
e9118a0
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.