CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mobilebuildmcp-snapshot-fixture-review

Use when reviewing MobileBuildMCP snapshot fixture changes for MCP, CLI, and JSON output contract integrity.

68

Quality

86%

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

92%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 lean review-skill body: exact file targets, crisp guardrails, explicit review limits, and a genuinely non-obvious normalization-sentinel checkpoint, all with zero padding. The only meaningful gap is the absence of a concrete example of a well-formed finding to anchor the output format.

Suggestions

Add a one-line example of a well-formed finding (root cause + affected fixture list) to make the grouping rule directly imitable.

Optionally state where the 'project-defined normalization sentinels' live (file or symbol name) so the pre-report verification step can be executed without searching.

DimensionReasoningScore

Conciseness

Every line is a directive or a concrete file path with zero padding or explanation of concepts Claude already knows; even the multi-line '99999' sentinel note is non-obvious project knowledge that earns its tokens, matching 'lean and efficient; every token earns its place'.

5 / 5

Actionability

Guidance is concrete and executable for an instruction-only skill — seven exact file paths, explicit rules ('Do not run snapshot or smoke suites', 'Group every occurrence of the same root cause into one finding') and a pre-report checkpoint (verify sentinels in normalization code and tests). It stops short of anchor 5 because there is no example of what a well-formed finding or fixture-drift report should look like.

4 / 5

Workflow Clarity

This is a single-task, under-50-line review skill whose sections (scope → files → guardrails → limits) sequence the work unambiguously, with the sentinel-verification rule acting as an explicit checkpoint before reporting; the review-only, non-destructive scope means no validation cap applies.

5 / 5

Progressive Disclosure

The skill is self-contained at ~40 lines with no bundle files and no external references needed, and its well-organized sections (Review scope, Files to inspect, Guardrails, Review limits) satisfy the simple-skill guidance for progressive disclosure.

5 / 5

Total

19

/

20

Passed

Description

73%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 tightly scoped, highly distinctive description with an explicit 'Use when' clause and strong project-specific trigger terms. Its main weakness is that the 'what' is folded into the trigger clause and only a single action ('reviewing') is named, leaving the capability list thin. Suggestions target specificity and trigger coverage.

Suggestions

State the 'what' as concrete actions before the trigger, e.g. 'Reviews snapshot fixture changes for MCP, CLI, and JSON output contract integrity: verifies fixture updates map to intentional behavior changes, checks normalization is done in code, and groups cross-fixture drift into single findings.'

Add natural trigger variations users might say, such as 'snapshot tests', 'golden files', or 'fixture drift', to broaden keyword coverage.

Name the concrete review checks (e.g. 'stable structured output envelopes', 'normalization sentinels') in the description so the capability scope is visible without opening the skill.

DimensionReasoningScore

Specificity

The domain is precisely named ('MobileBuildMCP snapshot fixture changes for MCP, CLI, and JSON output contract integrity') but only one action ('reviewing') is stated, with no enumeration of the concrete checks the review performs — matching the 'names domain and 1-2 concrete actions' anchor rather than the 'lists several specific actions' anchor.

3 / 5

Completeness

The 'when' is explicit ('Use when reviewing MobileBuildMCP snapshot fixture changes') and the 'what' is present but folded into that clause rather than independently stated with concrete capabilities, fitting 'has both what and when; when could be more explicit or specific' — not 5 since the what is not separately enumerated.

4 / 5

Trigger Term Quality

'reviewing', 'snapshot fixture', 'MCP', 'CLI', 'JSON output' are natural terms a user on this project would say, but common variations ('snapshot tests', 'golden files', 'fixtures', 'PR review') are missing, fitting 'good keyword coverage; a few natural terms missing' rather than comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The project-specific trigger 'MobileBuildMCP snapshot fixture changes' carves a clear niche with distinct triggers and minimal risk of firing for unrelated review skills.

5 / 5

Total

16

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

getsentry/XcodeBuildMCP

Path

.agents/skills/mobilebuildmcp-snapshot-fixture-review/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.