agentleFS
Sign inStart free
Dragoon0xDragoon0x/taste-skills/skills/articulation/written-critique/SKILL.md

written-critique

Skill5 starsChanged 8 months agoMITView on GitHub

Write a structured design review that someone can act on without follow-up questions. Use when giving async design feedback, writing portfolio case studies, or documenting design decisions.

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write feedback someone can act on without asking you to clarify.

    line 8
  2. Distinctive:

    MUST be specific enough that the designer can act without a follow-up conversation

    line 23
  3. Distinctive:

    MUST separate craft feedback (alignment, consistency) from taste feedback (should this exist at all?)

    line 24
  4. Distinctive:

    MUST reference observable decisions, not feelings

    line 25
  5. Distinctive:

    SHOULD be under 300 words.

    line 26
  6. Distinctive:

    NEVER rewrite the design in the feedback.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Written Critique

Write feedback someone can act on without asking you to clarify.

How to use

  • /written-critique Apply structured critique format to design reviews in this conversation.

Constraints

Critique Structure

  1. Intent (2-3 sentences): What the design is trying to do. Not what it does. What experience it's trying to create.
  2. What works (2-3 specific decisions): Each with the principle behind it.
  3. What doesn't (1-2 specific decisions): Each with reasoning and the impact on the user.
  4. One change (1 recommendation): The single highest-impact change, framed as a direction not a prescription.

Writing Rules

  • MUST be specific enough that the designer can act without a follow-up conversation
  • MUST separate craft feedback (alignment, consistency) from taste feedback (should this exist at all?)
  • MUST reference observable decisions, not feelings
  • SHOULD be under 300 words. Concise feedback gets read. Novels don't.
  • NEVER rewrite the design in the feedback. Diagnose, don't prescribe.

Anti-Patterns

  • Writing a wall of text with no structure
  • Mixing praise and criticism in the same sentence (pick a lane per observation)
  • Giving feedback on every detail equally (prioritize what matters most)
  • Being so diplomatic the feedback has no edge

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free