Dadmin88

Perform a structured accessibility audit of a product experience or implementation and produce prioritized remediation guidance.

Review product design artifacts before implementation for accessibility of information, interaction, focus, input, error recovery, responsive/reflow behavior, motion, contrast, content alternatives, and assistive-technology semantics.

Validate a user flow with keyboard or equivalent non-pointer input by checking reachability, order, focus visibility, activation, escape, shortcuts, custom widgets, and recovery from dynamic UI changes.

Review a critical interface flow with representative screen-reader and accessibility-tree evidence, checking names, roles, states, structure, navigation, announcements, reading order, and task completion.

Review a product flow or implementation against an explicitly identified WCAG version and conformance target by mapping applicable success criteria to reproducible evidence without reducing conformance to scanner output.

Diagnose AI and agent failures from trace evidence by locating the first meaningful divergence across routing, instructions, context, retrieval, tools, state, model behavior, schemas, and runtime.

Design and run an evaluation for an AI or agent feature using representative tasks, explicit success criteria, failure taxonomy, baselines, and reproducible evidence.

Select an AI model for a real workload using representative evaluations, current official capability and pricing data, latency and cost measurements, operational constraints, and explicit fallback tradeoffs.

Route a learning request to the smallest useful set of Academy professors or instructors based on subject, level, and goal.

Use when teaching a Hermes profile a bounded competency.

MUST load first for Academy learning or go-learn requests.

Create a compact teaching brief with learning goal, approximate level, relevant prior knowledge, constraints, and preferred depth or mode.

Decide whether a goal should stay with one specialist, use a paired execution/review pattern, or be decomposed across a larger team before creating coordination overhead.

Review an automotive learning task for lifting, electrical, high-voltage, fuel, heat, pressure, chemical, airbag, rotating-component, and environmental hazards.

Teach an automotive system through components, energy or signal flow, control logic, normal behavior, common failure modes, and inspection points.

Teach automotive diagnosis through symptom clarification, system knowledge, fault hypotheses, safe tests, evidence interpretation, and root-cause verification.

Use when communicating with exact Hermes Fleet nodes, checking live node state, sending non-executing messages, or deliberately running Hermes remotely through Keryx.