Rubrkit
Rubrkit interface system

Style guide for a grading instrument.

The system is dark, quiet, and editorial: graphite surfaces, calibration marks, candid labels, and modules that make weak instructions feel inspectable.
Tokens

Color carries the instrument logic.

Graphite

#080908

Page background

Panel

#11140f

Cards and modules

Paper

#f4f1e8

Primary text

Calibration

#d7ff5f

Primary actions and marks

Signal

#8cb8ff

Secondary metadata

Editorial

#ff6b6b

Errors and hard warnings
Type

Candid hierarchy, no decorative drama.

Grade before you ship.

Clear objective. Bounded agent. Testable result.

Body copy should explain the artifact, the weakness, and the next inspection step without slipping into generic AI optimism.

SPECIMEN RBR-082 / RUBRIC READY
Atoms

Buttons, chips, fields, and feedback.

Actions

Labels
Grade 82
Drift risk
Missing gate
Agent spec
Inputs and status
Modules

Atoms become inspection surfaces.

GRADE

82

agent

Detected artifact type

Verdict

The instruction is usable, but the success gate needs to be explicit before the agent can be trusted in a repeated workflow.

Eval gate module

Objective gate

The output names one measurable success condition.

Drift control

The agent has a fallback path when source evidence is thin.

Format lock

The response follows the requested structure without extra sections.

Free

$0

For quick checks and first rewrites.

Limited audits

Basic score

Top 3 issues

One rewrite

Run an audit
Pro
Popular

Preview

For builders who reuse and test instructions.

Full rubric

Advanced rewrites

Eval kit generation

Version comparison

Saved library

Exports

Run an audit
Team

Preview

For shared standards and review workflows.

Team library

Shared rubric library

Admin controls

Private examples

Review reports

Run an audit