New to Claude Skills? Learn how to install them →

nexu-io on GitHub

Critique Theater

Free

Streamlined design reviews with actionable feedback.

by nexu-io84.9k stars on nexu-io/open-design
1 views
Updated Aug 10, 2026
Get this skill

Free · Opens the source repo

What Critique Theater does

Critique Theater, also known as Design Jury, is a structured review system designed for evaluating design artifacts through a collaborative scoring process. When activated, it orchestrates a critique session involving five predefined roles: Designer, Critic, Brand, Accessibility, and Copy. Each role contributes to the evaluation by scoring their respective areas, generating actionable feedback in a consistent format. This setup ensures that all aspects of the design are thoroughly assessed, leading to a more refined final product.

The process is initiated by the Designer, who drafts the artifact to be reviewed. The Critic, Brand, Accessibility, and Copy roles then evaluate the work according to their designated scopes, recording any must-fix items that need addressing before the artifact can be considered for shipping. The scoring is done on a scale from 0 to 10, with a shipping threshold set at 8.0, ensuring that only well-reviewed artifacts proceed to the next stage.

Critique Theater operates within a command-line interface (CLI) session, allowing for real-time collaboration and immediate feedback. The results of each round are stored in a structured format, enabling the persistence of the review process and the ability to replay the critique session through a transcript. This replayability is crucial for teams looking to analyze past decisions and improve future design processes.

This skill is particularly useful for design teams looking to enhance their review workflows, ensuring that all critical aspects of a design are evaluated systematically. By providing a clear structure and actionable insights, Critique Theater can help teams produce higher-quality designs more efficiently.

When to use it

Use this skill when conducting design reviews that require input from multiple perspectives, ensuring comprehensive evaluation and actionable feedback.

When not to use it

This skill may not be suitable for informal design discussions or when quick feedback is needed without a structured process.

What you can build with it

Formal Design Review

When preparing for a formal design review, use Critique Theater to ensure all aspects of the design are evaluated by multiple roles.

Iterative Design Process

In an iterative design process, utilize Critique Theater to gather structured feedback across multiple rounds, refining the artifact before shipping.

Team Collaboration

For teams collaborating on design projects, Critique Theater provides a clear framework for discussion and feedback, improving overall design quality.

How to install Critique Theater

View source

1. Install with the skills CLI

npx skills add nexu-io/open-design/critique-theater --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by nexu-io

Critique Theater

Design Jury is the user-facing name for Critique Theater. When the daemon enables it for an artifact-generating run, it appends the active protocol, brand source, thresholds, and weights to the agent prompt. The agent then plays the fixed v1 cast — Designer, Critic, Brand, Accessibility, and Copy — as turns inside the same CLI session.

Runtime contract

  • Follow the daemon-injected tagged protocol exactly: one <CRITIQUE_RUN> envelope containing <ROUND>, <PANELIST>, and <ROUND_END> blocks and, only after a ship decision, one final <SHIP> block. Do not emit prose outside the envelope.
  • Designer drafts the artifact. Critic, Brand, Accessibility, and Copy score their own scopes and record actionable <MUST_FIX> items. The cast is fixed in v1; a plugin does not replace it with a custom list of axes.
  • The daemon parses the stream incrementally into typed PanelEvent variants and publishes them on critique.* SSE channels. It recomputes the composite from the scoring panelists, so an agent-supplied composite is advisory.
  • Do not write critique.json in the project cwd or emit a kind: "critique-panel" object. Those were the pre-orchestrator shape and are not inputs to the current runtime.

Convergence and persistence

The default review uses a 0–10 scale, an 8.0 ship threshold, and at most three rounds. A round ships only when its daemon-computed composite reaches the configured threshold and no open must-fix items remain. The active values come from OD_CRITIQUE_* configuration, including OD_CRITIQUE_MAX_ROUNDS, OD_CRITIQUE_SCORE_THRESHOLD, and the fallback policy.

OD_MAX_DEVLOOP_ITERATIONS still caps an outer plugin pipeline stage; it is not the Design Jury round limit or ship rule. Likewise, a pipeline's critique.score signal is a scheduler-facing projection, not the wire output the agent should manufacture.

The daemon stores the terminal run and per-round summaries in SQLite and writes the ordered PanelEvent stream as a replayable NDJSON transcript (gzip-compressed when large). Final artifact bytes are stored separately; the ship event carries only an artifactRef.

Interrupting a run

The web Design Jury surface exposes Interrupt and an Esc shortcut. After the user triggers either, the web app posts to /api/projects/:projectId/critique/:runId/interrupt; the daemon aborts the registered run, persists the partial best-so-far state, and emits critique.interrupted. od ui respond handles GenUI surfaces and does not provide a break-loop action for Critique Theater.

Frequently asked questions about Critique Theater

Similar skills