ce-test-xcode

Build and test iOS apps on simulator with XcodeBuildMCP.

Quality

67%

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 ./skills/ce-test-xcode/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

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

The body is highly actionable with a clear, validated workflow and concrete tool calls, but it is monolithic and somewhat verbose in its templates. Splitting long reference material into bundle files and trimming redundant sections would lift the two level-2 dimensions.

Suggestions

Move the full test-summary template and the human-verification flow table into a reference file (e.g. references/TEMPLATES.md) and link to it from the body, improving progressive disclosure.

Trim the "Quick Usage Examples" section, which restates invocations already implied by the argument-hint and workflow, to improve conciseness.

Consider shortening or collapsing the prerequisites list into a single sentence, since most items (Xcode installed, simulator available) are implied by the workflow steps.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (it lists MCP tool names without explaining what they are), but sections like the long test-summary template, the prerequisites list, and the redundant "Quick Usage Examples" could be tightened. This fits level 2 ("Mostly efficient but includes some unnecessary explanation or could be tightened") rather than the lean level-3 anchor.	2 / 3
Actionability	It gives fully concrete, executable guidance throughout — named MCP tool calls (list_simulators, boot_simulator, build_ios_sim_app, install_app_on_simulator, etc.), copy-paste install commands (brew tap, npx), and a fallback command (xcrun simctl openurl). This matches the level-3 anchor "Fully executable code/commands; specific examples; copy-paste ready."	3 / 3
Workflow Clarity	The nine numbered steps (0–9) are clearly sequenced with explicit validation checkpoints ("Do NOT proceed until XcodeBuildMCP is confirmed working", "Wait for the simulator to be ready") and feedback loops (build failure reporting, "Fix now"/"Skip" with rebuild-and-retest). This matches the level-3 anchor "Clear sequence with explicit validation steps; feedback loops for error recovery."	3 / 3
Progressive Disclosure	The ~200-line skill is well organized into sections but is monolithic — no references/scripts/assets bundle exists, and inline material such as the test-summary template and human-verification table could plausibly live in separate reference files. Per the scoring note this exceeds the <50-line simple-skill case, so it sits at level 2 ("Some structure but could be better organized; content that should be separate is inline").	2 / 3
	Total	10 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 specific to a clear niche and unlikely to conflict, but it only lists two actions and lacks an explicit "Use when..." trigger clause. Adding a trigger clause and a few more concrete actions would raise the weaker dimensions.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to build or test an iOS app on the simulator, run UI tests, or verify app behavior on a simulated device."

List additional concrete actions in the description (e.g. install, launch, capture screenshots/logs) so specificity reaches the level-3 anchor.

Soften reliance on the jargon term "XcodeBuildMCP" for the trigger phrasing, or pair it with natural user wording like "run iOS simulator tests" to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Build and test iOS apps on simulator with XcodeBuildMCP." names the domain and two concrete actions (build, test) plus the environment and tool, matching the level-2 anchor "Names domain and some actions, but not comprehensive." It stops short of the level-3 anchor which expects multiple distinct concrete actions listed.	2 / 3
Completeness	It clearly states what the skill does (build and test iOS apps on simulator) but has no "Use when..." clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2 — "Has what, but when is missing or only implied."	2 / 3
Trigger Term Quality	Natural terms like "build", "test", "iOS apps", and "simulator" are present, but "XcodeBuildMCP" is technical jargon and common phrasings a user would say (e.g. "test my app", "run on simulator") are not covered. This fits level 2 (some relevant keywords, missing common variations) rather than level 3's broad coverage.	2 / 3
Distinctiveness Conflict Risk	The combination of "iOS apps", "simulator", and a named tool (XcodeBuildMCP) carves out a clear, narrow niche unlikely to fire for unrelated skills, matching the level-3 anchor "Clear niche with distinct triggers; unlikely to conflict."	3 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: EveryInc/compound-engineering-plugin
Path: skills/ce-test-xcode/SKILL.md
Commit: a9f6d53

Reviewed: 7 days 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.