agentleFS
45ck45ck/hci-review-skill/.agents/skills/cognitive-walkthrough/SKILL.md

cognitive-walkthrough

Skill19 starsChanged 6 days agoMITView on GitHub

Step through a task as a first-time user and identify where intent, discoverability, feedback, or interpretation will break down.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run a cognitive walkthrough for this task or flow:

    line 7
  2. Distinctive:

    Use ultrathink. Act like a plausible first-time user with only the cues available in the interface.

    line 11
  3. Very specific:

    Write docs/hci/cognitive-walkthrough.md unless the user asked for another path.

    line 14
  4. Distinctive:

    Create the directory if it does not exist.

    line 15
  5. Distinctive:

    After acting, will the feedback make sense?

    line 21

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Run a cognitive walkthrough for this task or flow:

$ARGUMENTS

Use ultrathink. Act like a plausible first-time user with only the cues available in the interface. Use the actual prototype and codebase context.

Output

Write docs/hci/cognitive-walkthrough.md unless the user asked for another path. Create the directory if it does not exist.

Required questions at every step

  1. Will the user form the right goal here?
  2. Will the user notice the correct action?
  3. Will the user understand that the action leads toward the goal?
  4. After acting, will the feedback make sense?

Required format

For each step include:

  • step number
  • user goal
  • visible cues
  • likely action
  • walkthrough answers for Q1 to Q4
  • breakdowns / confusion risks
  • recommendation

Extra checks

Also flag:

  • hidden prerequisites
  • unclear affordances
  • weak or missing feedback
  • misleading labels
  • dead ends
  • unclear recovery path

Synthesis

End with:

  • steps most likely to fail
  • reasons first-time users may hesitate
  • design changes most likely to improve task completion

Deliverable style

  • Clear headings
  • Markdown tables
  • Mermaid diagrams where useful
  • Direct language
  • No filler

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.