axiom-test-simulator

Use when the user mentions simulator testing, visual verification, push notification testing, location simulation, screenshot capture, OR live accessibility validation (VoiceOver announcements, Dynamic Type, ADA checks) on the simulator.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./axiom-codex/skills/axiom-test-simulator/SKILL.md

Quality

Content

77%

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

A highly actionable, well-structured simulator-testing reference with strong executable commands and real validation/feedback loops. Its weaknesses are verbosity from duplicated and restated sections, and a monolithic body that could offload more detail into the referenced skill files.

Suggestions

De-duplicate the simctl diagnose material: it appears in capability #11 and again as the 'Comprehensive Diagnostics' section — keep it in one place and cross-reference.

Trim explanatory prose that restates what tools do (e.g. the devicectl rationale paragraph and AXe installation narrative); the commands and a one-line purpose each are sufficient.

Move the long catalog portions (full diagnostics collection, the complete AXe command reference) into the already-referenced skill files so SKILL.md stays a lean overview with one-level-deep pointers.

Dimension	Reasoning	Score
Conciseness	The ~420-line body is mostly efficient executable code, but it is padded by restated explanations (devicectl rationale, AXe install prose) and duplicated content — simctl diagnose appears in capability #11 and again as its own 'Comprehensive Diagnostics' section — so it could be tightened.	2 / 3
Actionability	Nearly every section provides concrete, copy-paste-ready commands (xcrun simctl, axe, xcui, devicectl) with exact flags and worked examples, matching the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	A clear 7-step Test Workflow is reinforced by explicit validation checkpoints in the Mandatory First Steps preflight and a real crash-detection feedback loop (check for new .ips files, run xcsym, branch on hang_report), satisfying the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	External skill references are one level deep and clearly signaled (axiom-tools skills/device-control-ref.md, xcui-ref.md, ui-testing.md, xcsym-ref.md), but the body itself is a monolithic ~420-line catalog with inline content (full diagnostics section, AXe reference) that could be split into reference files.	2 / 3
	Total	10 / 12 Passed

Description

82%

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 strong, trigger-rich description that clearly signals when to use the skill and lists specific capabilities. Its main weakness is that it expresses 'what' only as a list of trigger contexts rather than as explicit capability verbs.

Suggestions

Lead with a third-person capability verb statement (e.g. 'Drives the iOS Simulator for automated testing and closed-loop visual debugging') before the 'Use when…' clause so 'what' is stated as actions, not just trigger nouns.

Keep the 'Use when…' trigger list, but consider trimming the OR-separated list slightly to preserve scannability without losing the natural trigger terms.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ('simulator testing, visual verification, push notification testing, location simulation, screenshot capture') plus specific accessibility checks, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	The 'when' is explicit and strong ('Use when the user mentions…'), but the 'what does this do' is only implied via trigger-noun lists rather than stated as capabilities (e.g. 'Captures screenshots, simulates location…'), so it sits at the 'has when, what implied' level rather than clearly answering both.	2 / 3
Trigger Term Quality	Natural trigger phrasing ('Use when the user mentions') paired with concrete user-facing terms (simulator testing, push notification testing, location simulation, screenshot capture, VoiceOver announcements, Dynamic Type) gives good coverage of terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	The iOS-simulator testing niche is narrow with distinct, specific triggers (simulator testing, VoiceOver/Dynamic Type/ADA, push testing), making it unlikely to fire for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: CharlesWiltgen/Axiom
Path: axiom-codex/skills/axiom-test-simulator/SKILL.md
Commit: ea3be7c

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.