Facilitating Design Critique logo

Facilitating Design Critique

Organization
bitwarden
facilitating-design-critique

Run or participate in a Bitwarden design critique session — the weekly team critique and one-off product design reviews — grounded in the team's published etiquette guide and the Product Design Review Guidelines.

Overview

Publisherbitwarden
Repositoryai-plugins
Skill namefacilitating-design-critique
Stars
149
Forks
19
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by bitwarden on GitHub. Read the source before you install it.

Installation

Install the Facilitating Design Critique AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bitwarden/ai-plugins.git /tmp/ai-plugins
mkdir -p .claude/skills
cp -r /tmp/ai-plugins/plugins/bitwarden-designer/skills/facilitating-design-critique .claude/skills/facilitating-design-critique
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Facilitating Design Critique in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Facilitating Design Critique on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Facilitating Design Critique is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Facilitating Design Critique

This skill grounds the facilitation of design critique in two Bitwarden sources of truth: the Weekly Design Critique & Etiquette Quick Guide and the Product Design Review Guidelines. Read the Confluence pages directly when prepping a real session — the get_confluence_page MCP tool fetches them. This skill is the practitioner's quick reference, not a replacement for those pages.

Cross-plugin dependency. When the design under discussion lives in a Figma file, this skill composes using-figma from the bitwarden-design-tools plugin — install it alongside bitwarden-designer for the full composition to work.

Pick the right mode

Bitwarden runs two distinct kinds of critique. Treat them differently.

  • Weekly Design Critique. Recurring team session. Presenter sets context for a piece of work-in-progress; the room asks clarifying questions, then gives feedback. Lightweight cadence, peer-to-peer, the presenter decides what to apply.
  • Product Design Review. Stakeholder review for a specific design proposal. Invites product, engineering, research as relevant. Heavier facilitation: scope, criteria, briefing, walkthrough, structured feedback collection.

Ask which mode the user means before suggesting a structure. The roles, prep, and time investment differ.

Roles in the room

  • Presenter. Sets context: the goal of the design, the constraints, the open questions, and what kind of feedback they want. The presenter owns what they apply.
  • Facilitator. Shepherds the session: redirects when discussion drifts, holds a "parking lot" for side issues that aren't central to the scope, and protects the presenter's stated feedback ask. In weekly critique this is usually a rotating role; in product design reviews it's an explicit appointment.
  • Participants. Ask before judging. Share observations, concerns, and ideas. Tied to user and product goals, not personal preference. Don't dominate.

The Weekly Design Critique Quick Guide reduces this to: critique the work, support the person, improve the product.

Session shape

Both modes share the same arc; the depth differs.

  1. Presenter sets context. Goal, constraints, open questions, the kind of feedback wanted. In product design reviews, this also covers background and the "why" — relevant documentation, early iterations, user research findings, business goals, end-user goals.
  2. Clarifying questions. Ask before judging or suggesting. The room doesn't critique what it doesn't yet understand.
  3. Walkthrough and feedback. Presenter walks the design. Participants share feedback tied to user impact, product goals, standards, or technical constraints.
  4. Wrap-up. Key takeaways and next steps. In product design reviews, document feedback for future reference in a preferred format and prioritize issues.

Feedback etiquette — do and don't

Do

  • Be specific and constructive.
  • Explain why something works or doesn't.
  • Ask questions to understand intent.
  • Call out what's working, not just issues.
  • Respect time and stay on topic.

Don't

  • Make it personal.
  • Give vague opinions like "I don't like it."
  • Dominate the conversation.
  • Jump to solutions without context.
  • Design on the spot — describe the gap, let the designer solve.

A useful set of opening phrases when the room stalls:

  • "What problem is this solving for the user?"
  • "I'm unclear about [blank] — could you explain?"
  • "Have we considered [blank] as an alternative?"
  • "This part feels strong because [blank]."

Common participation traps

  • "I don't like it." Not feedback. Tie the observation to a user need, business need, standard, convention, or technical constraint — or skip it.
  • "You are not the user." Personal bias presented as universal experience. Surface it as bias, not as a finding.
  • Asking why badly. "Why did you do that?" puts the designer on the defensive. "What are you trying to achieve by doing X?" gets at the same thing without the edge.
  • Solutioning during the review. A well-meaning suggestion can cascade through a design. Describe the gap. Let the designer weigh the fix offline.
  • Negative-only feedback. Designers move in the direction of what's working as much as away from what isn't. Lead with strengths, then issues.
  • The unconsidered consequence. "Could we just…" requests often spiral. When a suggestion feels simple, name the cascading effects you can see and let the designer decide.

Facilitator playbook for product design reviews

When facilitating (not just participating):

  • Before the review. Pick a method to collect feedback. Identify and invite the right stakeholders. Confirm the presenter has the briefing material ready (goals, background, early iterations, user research, business and end-user goals).
  • During the review. Define scope. Set feedback expectations. Surface the "why." Run the walkthrough. Open the floor with the scope and criteria already named. Document feedback in the agreed format. Hold the parking lot for off-scope discussion.
  • After the review. Prioritize the issues raised. Confirm next steps with the presenter.

Composing with other skills

  • design-review. During the session, the substance of feedback runs through design-review — the 30/60/90 framework, the Code of Conduct, and (at 60%/90%) the content-style-guide. This skill shapes the room; design-review shapes what's said.
  • using-figma. When the presentation is from a Figma file, use using-figma to bring the design context into the discussion (screenshot, metadata, variables) without context-bombing the room.

Output format

When asked to help prep or run a critique:

  1. Mode — Weekly Critique or Product Design Review.
  2. Roles — who's facilitating, who's presenting, who's participating.
  3. Presenter's setup — goal, constraints, open questions, the feedback ask.
  4. Agenda / arc — context → clarifying questions → walkthrough → feedback → wrap-up.
  5. Watch-outs for the room — the specific etiquette traps likely to come up given the work being presented.

Always end with the wrap-up question explicit: what is the presenter going to do next?

Frequently asked questions

What does the Facilitating Design Critique AI skill do?

Run or participate in a Bitwarden design critique session — the weekly team critique and one-off product design reviews — grounded in the team's published etiquette guide and the Product Design Review Guidelines.

Why use Facilitating Design Critique on TypingMind?

Because you install it once and use it with any model. Facilitating Design Critique is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Facilitating Design Critique in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bitwarden/ai-plugins/tree/main/plugins/bitwarden-designer/skills/facilitating-design-critique. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Facilitating Design Critique?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Facilitating Design Critique?

As many as you like. As long as a model supports skills, you can use Facilitating Design Critique with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Facilitating Design Critique AI skill free?

It is published on GitHub by bitwarden. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇