CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

axiom-uikit

Use when bridging UIKit and SwiftUI, modernizing UIKit apps (scene lifecycle, resizability), debugging Auto Layout, Combine, TextKit, PencilKit, or UIKit animations.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary router skill: unambiguous, precedence-ordered routing with concrete API-level corrections and strong conflict resolution, held back by presenting the same routing decision three separate ways and by pointing at suite files that are not included in this bundle. The body adds only routing knowledge Claude could not infer, with essentially no concept padding.

Suggestions

Cut one of the two duplicate decision representations — the graphviz digraph or the numbered list — and trim Example Invocations to cases not already covered by the decision tree, which would remove roughly a third of the body without losing any routing information.

Ship the referenced `skills/*.md` files inside the bundle (e.g. under `references/`) or document where they resolve, so the router's destinations — including `skills/resize-auditor.md` from the inline auditor block — are actually reachable.

Merge any Quick Reference rows whose symptom is already an exact decision-tree condition (e.g. the constraint-conflict rows) to reduce the table to symptoms that only it covers.

DimensionReasoningScore

Conciseness

The same routing map is rendered three times — the graphviz "digraph uikit" block, the numbered decision list ("0. Scene-lifecycle migration... → skills/uikit-modernization.md"), and the Example Invocations section — alongside a Quick Reference table. That is roughly 50 lines of duplication, which fits 'mostly efficient but could be tightened' rather than the 'minor trimming' of anchor 4; no concept explanations or padded prose keep it above anchor 2.

3 / 5

Actionability

Routing guidance is exact and executable: literal error strings ("Unable to simultaneously satisfy constraints"), specific APIs ("UIViewRepresentable", "PKStrokeRecognizer", "UINavigationItem.subtitle"), and concrete corrections such as "Persist `drawing.dataRepresentation()`" and "the canvas must `becomeFirstResponder()` after `setVisible(_:forFirstResponder:)`". As an instruction-only router skill its guidance fully covers the common cases, matching the top anchor.

5 / 5

Workflow Clarity

A single-action skill (classify the task, read the mapped file) whose action is unambiguous: ordered precedence rules ("Try uikit FIRST"), explicit conflict-resolution tie-breaks against swiftui/concurrency/performance/axiom-data, and an anti-rationalization table of known wrong turns. Per the simple-skill exception this warrants 5, and no destructive or batch operations exist to impose a validation cap.

5 / 5

Progressive Disclosure

References are one level deep and clearly signaled ("See `skills/uikit-bridging.md`", "See `skills/pencilkit-paperkit-ref.md`"), but the bundle contains no referenced files at all — none of the `skills/*.md` targets or the inline block's `skills/resize-auditor.md` exist in `references/`, `scripts/`, or `assets/`, so the router's destinations cannot be resolved from this bundle. Good structure with an unverifiable target set fits anchor 4; it is not 5 because navigation is not easy when the targets are absent, and not 3 because references are clearly signaled with nothing inlined that belongs elsewhere.

4 / 5

Total

17

/

20

Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A solid trigger-style description with concrete, natural keywords and an explicit 'use when' clause; the 'what' is implicit and a few natural trigger terms (notably the PencilKit/PaperKit subsystem the body routes heavily) are missing. Overall it sits comfortably in the good-examples band, just short of the strongest pattern of separately stating what the skill does plus when to use it.

Suggestions

Add the missing natural trigger terms for the subsystems the body routes — e.g. "PencilKit", "PaperKit", "Apple Pencil" — so users asking about drawing canvases or markup can reach this skill from the description.

State the 'what' explicitly before the trigger clause, e.g. "Routes UIKit work — bridging, adaptive layout, Auto Layout and animation debugging, Combine, TextKit, PencilKit — to detailed guides. Use when..." so the description answers both what and when distinctly.

Qualify "Combine" and "TextKit" with UIKit context (e.g. "Combine in UIKit views", "TextKit in UIKit text views") to reduce overlap with pure concurrency or macOS text skills.

DimensionReasoningScore

Specificity

Lists several specific action+domain pairs — "bridging UIKit and SwiftUI", "modernizing UIKit apps (scene lifecycle, resizability)", "debugging Auto Layout, Combine, TextKit, or UIKit animations" — matching the 'several specific actions; minor gaps' anchor. Not 5 because the verbs are domain-scoped rather than concrete operations, and the PencilKit/PaperKit work the body routes is entirely absent from the description.

4 / 5

Completeness

The 'when' is explicit and concrete ("Use when bridging... modernizing... debugging..."), but the 'what' is only implied through the gerund list with no separate statement of what the skill provides. This lands on 'both present, one could be more explicit' rather than 5, and clearly above the 'what only, when weak' anchor 3.

4 / 5

Trigger Term Quality

Includes the natural terms users actually say — "UIKit", "SwiftUI", "Auto Layout", "Combine", "TextKit", "scene lifecycle", "resizability" — which fits 'good keyword coverage; a few natural terms missing'. Not 5 because whole subsystems a user would name ("PencilKit", "PaperKit", "Apple Pencil", "UIViewRepresentable") are missing despite the skill covering them.

4 / 5

Distinctiveness Conflict Risk

"bridging UIKit and SwiftUI" carves a clear niche distinct from pure-SwiftUI or pure-UIKit skills, matching 'mostly distinct; minor overlap risk'. Not 5 because bare "Combine" and "TextKit" are unqualified as UIKit-context, so a pure Combine or macOS text query could trigger this skill over a concurrency skill.

4 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

CharlesWiltgen/Axiom

Path

.claude-plugin/plugins/axiom/skills/axiom-uikit/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.