From armor
Audits API, CLI, or config surfaces for affordances (what is easy to do) and anti-affordances or footguns (what is easy to get wrong). Usable during interface design or review.
How this skill is triggered — by the user, by Claude, or both
Slash command
/armor:affordance-auditThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
A good affordance you never notice. You act through it. A bad one — an
A good affordance you never notice. You act through it. A bad one — an anti-affordance — makes you fight the thing, and the fight shows up as bugs.
A surface can satisfy its main job and still carry secondary anti-affordances that make every other use awkward. That split is the thing to hunt.
Walk the public surface. For each entry point, ask what it invites the caller to do.
Affordances. What does the easy path get you? The good case: the easy path and the correct path are the same thing. The caller falls into success.
Anti-affordances. What is easy to get wrong?
The split smell. Primary use smooth, secondary use awkward. Name both. This is the most common and most missed finding.
For each anti-affordance, the fix is one of three:
Report as a table:
| Surface | Invites | Footgun | Fix |
|---|
A stable, widely-used API you cannot change without breaking callers. Audit those for documentation, not redesign. The footgun you cannot remove still deserves a loud warning sign.
npx claudepluginhub markacianfrani/armor --plugin armorGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.