agentleFS
45ck45ck/hci-review-skill/.claude/skills/consistency-audit/SKILL.md

consistency-audit

Skill19 starsChanged 6 days agoMITView on GitHub

Audit a prototype for cross-screen consistency in navigation, actions, states, patterns, and interaction rules.

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, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use ultrathink. Review the interface as a system, not as isolated screens.

    line 11
  2. Very specific:

    Write docs/hci/consistency-audit.md unless the user asked for another path.

    line 14
  3. Distinctive:

    Create the directory if it does not exist.

    line 15
  4. Very specific:

    search/filter/sort behavior

    line 25
  5. Distinctive:

    Do not confuse deliberate variation with accidental inconsistency.

    line 45

“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

Audit consistency for this scope:

$ARGUMENTS

Use ultrathink. Review the interface as a system, not as isolated screens.

Output

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

Check these invariants

  • navigation location and behavior
  • page title structure
  • screen layout rhythm
  • primary / secondary / destructive action treatment
  • form field ordering and validation style
  • status badge style and meaning
  • empty/loading/error/success states
  • search/filter/sort behavior
  • modal / drawer / popover / toast usage
  • back / cancel / close semantics
  • icon meaning
  • terminology

Required output tables

Invariants

| Area | Expected invariant | Observed variants | Risk | Recommendation |

Screen inventory

| Screen/route/component | Primary purpose | Main action | State coverage | Notes |

Required synthesis

Conclude with:

  • top consistency breaks
  • invariants that should be written into the design system
  • issues likely to confuse users because similar things behave differently

Quality bar

Do not confuse deliberate variation with accidental inconsistency. Explain the difference.

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.