CtrlK
BlogDocsLog inGet started
Tessl Logo

axiom-audit-resize

Use when the user mentions window resizing support, resizable-window readiness, iPhone Mirroring compatibility, scene-lifecycle migration checking, or preparing an app for the 27-cycle resizing model.

59

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./axiom-codex/skills/axiom-audit-resize/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is a highly actionable, well-sequenced audit workflow with concrete greps, fix APIs, and validation checkpoints throughout. Its main weaknesses are length/verbosity in the per-pattern explanations and the absence of any progressive-disclosure file structure for the detailed anti-pattern catalog.

Suggestions

Move the 12 anti-pattern details (Phase 2) into a references/ file (e.g. ANTI_PATTERNS.md) and keep SKILL.md as an overview that links to it, tightening progressive disclosure.

Trim the 'Issue' lines that restate consequences an iOS expert already infers (e.g. why UIScreen.main is wrong) to cut tokens while keeping the grep and Fix.

Drop primer-style explanations of basic UIKit concepts Claude already knows; keep only the 27-cycle-specific implications that are genuinely novel.

DimensionReasoningScore

Conciseness

The body is dense and action-oriented rather than padded with generic filler, but at ~270 lines it restates some consequences an expert would infer (e.g. UIScreen.main 'Returns full-screen values that are wrong in any resized window') and explains UIKit basics Claude already knows, fitting the 'mostly efficient but could be tightened' anchor.

2 / 3

Actionability

It gives fully executable grep regexes (e.g. `UIScreen\.main\.bounds`, `\b(320|375|390|…)\b`), concrete Glob patterns, and copy-paste fix APIs (e.g. `panRecognizer.allowedScrollTypesMask = .all`, `windowScene.effectiveGeometry.coordinateSpace.bounds`), matching the 'fully executable, specific, copy-paste ready' anchor.

3 / 3

Workflow Clarity

A clear five-phase sequence with explicit validation checkpoints ('use Read to verify the surrounding context before reporting', 'verify the translation against a known-positive string'), a False Positives checklist, and output-limit triage rules, meeting the 'clear sequence with explicit validation steps and feedback loops' anchor.

3 / 3

Progressive Disclosure

No bundle files exist (references/scripts/assets absent), and the 12-pattern catalog plus cross-reference tables live inline in a ~270-line monolithic SKILL.md rather than being split into a one-level-deep reference, matching 'some structure but content that should be separate is inline'; it is well-sectioned but does not progressively disclose via files.

2 / 3

Total

10

/

12

Passed

Description

57%

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

The description is a well-scoped trigger statement for a specific iOS resize-readiness niche, but it describes when to invoke the skill rather than what the skill actually does, leaving the action half implicit. It also leans on technical jargon ('27-cycle resizing model') alongside its more natural trigger terms.

Suggestions

Lead with the concrete action before the trigger, e.g. 'Audits UIKit code, Info.plist, and scene manifests for resize-readiness violations. Use when the user mentions window resizing support, iPhone Mirroring compatibility, or scene-lifecycle migration.'

Soften the jargon triggers by adding common developer phrasings (e.g. 'window resizing', 'iPad Split View', 'multi-window') alongside '27-cycle resizing model'.

Name the primary deliverable (a resize-readiness audit report/score) so the 'what' is explicit, not implied.

DimensionReasoningScore

Specificity

The description names the domain ("window resizing support", "iPhone Mirroring compatibility", "scene-lifecycle migration checking") but is framed entirely as trigger conditions ("Use when the user mentions…") rather than concrete actions the skill performs, so it sits at the 'names domain and some actions, not comprehensive' anchor rather than the multi-action level 3.

2 / 3

Completeness

It supplies an explicit 'when' ('Use when the user mentions…') but never states the 'what' — that the skill audits/detects/reports resize-readiness violations — so the action side is only implied, matching the 'has when, what missing or implied' level rather than clearly answering both.

2 / 3

Trigger Term Quality

It pairs natural terms a developer would say ("window resizing support", "iPhone Mirroring") with jargon-heavy phrases ("27-cycle resizing model", "scene-lifecycle migration checking", "resizable-window readiness"), landing in the 'some relevant keywords but missing common variations' band rather than fully natural coverage.

2 / 3

Distinctiveness Conflict Risk

The triggers (iPhone Mirroring compatibility, scene-lifecycle migration, 27-cycle resizing) carve out a clear, narrow niche that is unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

9

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
CharlesWiltgen/Axiom
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.