General-purpose coding policy for Baruch's AI agents
73
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Use for a new or confusing user journey, competing interaction choices, or a gap between the requested outcome and proposed flow. A cosmetic change with an established pattern may need only a focused consultation.
Name the target user, their goal, the actual entry point, and the accepted behavior. Supply the current flow, relevant user feedback, screenshots or a usable build, and established interaction conventions. State whether the deliverable is an interaction proposal or an assessment of implemented behavior. Name any available design or user-research skill and the tools that can inspect the actual surface. Screenshots alone cannot establish keyboard or recovery behavior; record the missing access.
Provide an annotated flow or concrete interaction proposal, the alternatives that could change the decision, and observable acceptance criteria. For a review, link each finding to a reproducible user step and show the effect on completion or understanding. Name inaccessible states and untested assumptions. For accessibility-specific uncertainty, use the accessibility profile rather than asserting that a visual review establishes accessibility.
Record interaction decisions you helped originate in the contribution section. Proposed project lessons should name their source and revalidation condition.
.tessl-plugin
hooks
rules
skills
adopt-fork-pr
herdr-standup
herdr-teamlead
references
teamlead
templates
tests
migrate-to-plugin
onboard-repo
release
tests