Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Design Critique Partner

ASecurity

Run structured design critiques with frameworks for feedback that is honest, specific, and actionable.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill design-critique-partner --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Design Critique Partner?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Design Critique Partner
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-design-critique-partner/badge)](https://www.skillsdirectory.com/skills/aicodedecode-design-critique-partner)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: design-critique-partner
description: Run structured design critiques with frameworks for feedback that is honest, specific, and actionable.
category: creative-design
---

## Overview

Critique is design's quality control — but most "feedback" is either vague
praise or personal taste
masquerading as judgment. A good critique partner evaluates work against its
goals, separates
problems from preferences, and delivers feedback the designer can actually act
on. This skill
provides critique frameworks for both giving and receiving design feedback.

## When to use

- Reviewing a design before stakeholder presentation or launch

- Running team critique sessions (design crits)

- Giving feedback on a colleague's or freelancer's work

- Preparing to receive critique on your own designs

- Building a culture of honest feedback

## Core concepts

- - - **Critique against goals, not taste.** Every critique starts with: what is
  this trying to
  achieve, for whom? "I don't like blue" is taste; "the blue CTA doesn't stand
out against the blue
  hero, hurting conversion" is critique.
- - - **The 3-level framework.** Level 1: Does it work? (goals, usability,
  clarity). Level 2: Is it
  coherent? (hierarchy, consistency, craft). Level 3: Is it excellent?
(distinctiveness, delight,
  memorability). Fix level 1 before debating level 3.
- - - **Specific, observable, actionable.** "The headline hierarchy is unclear
  because the subhead is
  larger than the headline on mobile" beats "the typography feels off." Point to
the thing, explain
  the effect, suggest a direction.
- - - **Questions over declarations.** "What happens when the username is 40
  characters?" or "What's
  the primary action you want here?" Questions invite thinking; declarations
invite defensiveness.
- - - **Separate the problem from the solution.** "Users might miss the CTA" is
  the problem
  (valuable). "Make it red and bigger" is a solution (maybe wrong). Good
critique identifies
  problems clearly and lets the designer solve.
- - - **Receiving critique well.** Listen without defending, ask clarifying
  questions, separate useful
  signal from noise, and decide later what to change. Defensiveness in the room
kills future
  honesty.

## Practical workflow

1. 1. 1. **Set up the critique.** Presenter shares: the goal, the audience,
   constraints, and what
   feedback they need (what's decided vs open). Timebox: 20-30 minutes per
piece.
2. 2. 2. **Silent review first.** 3-5 minutes of silent looking. Prevents
   anchoring on the first loud
   opinion and gives introverts equal footing.
3. 3. 3. **Clarifying round.** Questions only — no opinions yet. Ensures
   everyone understands what
   they're looking at before judging it.
4. 4. 4. **Structured feedback.** Go level by level: does it achieve the goal?
   (biggest issues first),
   then craft and coherence, then polish. Each person: one strength, then
concerns with specifics.
5. 5. 5. **Prioritize the fixes.** End with: the 2-3 changes that matter most,
   ranked. A list of 20
   nits helps nobody; the top 3 change the design.
6. 6. 6. **Document decisions.** What feedback was accepted, what was rejected
   (with reason), and
   what's still open. Prevents re-litigating the same points next crit.
7. 7. 7. **Follow up.** Review the revision against the critique. Close the loop
   — critique without
   follow-through is just opinion theater.

## Common pitfalls

- - - **Taste disguised as critique.** "I would have done it differently"
  without tying to goals.
  Always anchor feedback to the stated objectives.
- - - **Praise sandwiches.** Burying real feedback in fluff. Professionals can
  handle direct, kind,
  specific critique — the sandwich just confuses the message.
- - - **Designing in the crit.** The group art-directing pixel by pixel.
  Critique identifies problems;
  the designer owns solutions. Stop the group redesign.
- - - **Piling on.** Five people repeating the same point. Facilitator's job:
  acknowledge, capture
  once, move on.
- - - **Critiquing the person.** "You always..." or questioning competence.
  Critique the work, in this
  version, against these goals. Nothing else.
- - - **No goals stated.** Critiquing without knowing what the design is for.
  The first question is
  always: "what's this trying to do?" — if nobody knows, that's the feedback.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →