CtrlK
BlogDocsLog inGet started
Tessl Logo

xcodebuildmcp

Official skill for XcodeBuildMCP. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).

76

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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 tight, actionable orchestration guide with concrete tool names and a clear step sequence, but its validation checkpoints are implicit rather than explicit gates, capping workflow clarity. Organization is appropriate for a short single-file skill.

Suggestions

Add an explicit validation/verification checkpoint — e.g., after session_show_defaults, state "only proceed when project/workspace/scheme context is confirmed" — to lift workflow_clarity above 2.

Show one concrete tool-call example (e.g., a sample session_show_defaults invocation with expected output) so guidance is copy-paste ready rather than directional.

Make the failure feedback loop explicit as a loop ("on failure: fix context, re-run session_show_defaults, then retry") rather than a one-line reporting instruction.

DimensionReasoningScore

Conciseness

The body is lean with no concept explanations Claude already knows; the capabilities list and three steps each earn their place by conveying tool availability and sequencing rather than padding, matching the lean-and-efficient anchor.

3 / 3

Actionability

Concrete, specific guidance names exact tools ("session_show_defaults", "discover_projs", "combined build-and-run tool") and an exact config path (".xcodebuildmcp/config.yaml") with clear selection rules; per the instruction-only scoring note, absence of code is not penalized when guidance is this actionable.

3 / 3

Workflow Clarity

A clear three-step sequence exists with a failure-reporting feedback loop in Step 3, but there are no explicit validate-then-proceed checkpoints — validation of context and tool availability is implicit rather than gated, so it sits below the anchor requiring explicit validation steps.

2 / 3

Progressive Disclosure

Under 50 lines with no bundle files and well-organized sections (intro, capabilities, three steps) plus a single clearly-signaled one-level external link to the configuration docs, which the rubric permits to score 3 for a simple skill with no external references needed.

3 / 3

Total

11

/

12

Passed

Description

100%

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 concise, specific, and complete: it states what the skill does and gives an explicit Use-when trigger with natural platform and action keywords, minimizing conflict risk. Voice is appropriately third-person/imperative trigger form, matching the good examples.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "build, test, run, debug, log, UI automation" — across named platforms, matching the anchor that requires several specific concrete actions rather than vague language.

3 / 3

Completeness

Explicitly answers both what ("Official skill for XcodeBuildMCP" doing the listed actions) and when via the "Use when doing iOS/macOS/watchOS/tvOS/visionOS work" trigger clause, satisfying the full what-and-when anchor.

3 / 3

Trigger Term Quality

Natural terms a user would say for Xcode work ("build", "test", "run", "debug", "iOS", "macOS") appear alongside platform names, giving good coverage of how the request is actually phrased.

3 / 3

Distinctiveness Conflict Risk

The named MCP plus platform-specific Apple-ecosystem triggers carve a clear niche unlikely to fire for unrelated skills; it is well distinguishable rather than generic.

3 / 3

Total

12

/

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
getsentry/XcodeBuildMCP
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.