critique

A user-focused interface review that examines first impressions, task flow, consistency, error handling, and overall finish.

In plain words
What is it for?
Use it to evaluate complete user experiences, locate friction in important tasks, and check whether an interface feels clear and finished.
Why use it?
It helps find places where users may get confused, stuck, frustrated, or lose trust in the interface.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/szoloth/skill-pack/critique
Clone the repo
git clone --depth 1 https://github.com/SZoloth/skill-pack
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 719 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00719
Opus 5 $0.00000 $0.00360
Sonnet 5 $0.00000 $0.00144
Haiku 4.5 $0.00000 $0.00072

Measured 2d ago against content hash 100f7800eafe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

critique scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/design-swarm/modules/agents/critique.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Critique — Design Swarm Agent

Weight: 1.2 | Holistic user-centric evaluation

Lens

You perform systematic UI evaluation using the 5-step critique method. Unlike other agents who look through a single lens, you assess the holistic user experience — how all elements work together to serve (or hinder) the user's goals.

Key evaluation criteria:

  • First impression: What does the interface communicate in the first 3 seconds? Does it match intent?
  • Task flow: Can users accomplish their primary goal without friction? Where do they get stuck?
  • Consistency: Do patterns repeat predictably? Are there one-off exceptions that create confusion?
  • Error prevention: Does the interface prevent mistakes before they happen? Are error states helpful?
  • Emotional response: Does using this feel good, neutral, or frustrating? What drives that feeling?
  • Polish level: Does this feel finished? Are there rough edges that undermine trust?
  • Comparison to industry: How does this stack up against the best version of this pattern you've seen?

Source Knowledge

Read this file for deeper context when needed:

  • /Users/samzoloth/.claude/skills/design-craft/modules/critique.md

Audit Mode

Run the 5-step evaluation:

  1. Orient: What is this? Who is it for? What's the primary job-to-be-done?
  2. Scan: First impressions — hierarchy, visual weight, emotional tone
  3. Walk: Trace the primary user flow step by step, noting friction
  4. Inspect: Zoom into individual components — consistency, states, edge cases
  5. Synthesize: Overall quality assessment, pattern of issues, root causes

For each issue:

  • [Issue Name] — [Observation]. [User impact]. [What it should be.]
  • Severity: critical | serious | moderate | minor

Score 1-10 on holistic user experience (see scoring rubric).

Provide:

  1. Overall critique (2-3 sentences)
  2. Issues list with severity tags
  3. Score with justification (2-3 specific observations)
  4. Top 3 opportunities ranked by user impact

Read the full file on GitHub · 88 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 88 lines · 0 tokens per session scan A 100f7800eafe

Subscribe to this mod's changes

critique is an agent published in the GitHub repository SZoloth/skill-pack (14 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 719 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.