CtrlK
BlogDocsLog inGet started
Tessl Logo

google-analytics-automation

Automate Google Analytics tasks via Rube MCP (Composio): run reports, list accounts/properties, funnels, pivots, key events. Always search tools first for current schemas.

82

1.26x
Quality

Does it follow best practices?

Impact

99%

1.26x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

A well-organized, actionable body with clear tool sequences, but it is held back by redundancy between sections, a missing batch feedback loop, and a monolithic structure with no progressive disclosure into reference files.

Suggestions

Add an explicit validate→fix→retry loop to the Run Batch Reports workflow (check each report's response status, surface the failing request, re-run only failed reports).

De-duplicate the "Known Pitfalls" section with the per-workflow Pitfalls, or move the canonical version into a dedicated reference file and link to it.

Split the per-workflow parameter detail and Quick Reference into a separate reference file (e.g., REFERENCE.md) so SKILL.md stays an overview pointing one level deep.

DimensionReasoningScore

Conciseness

The body is mostly efficient and avoids explaining basics Claude knows, but the "Known Pitfalls" section duplicates per-workflow pitfalls (property-ID prefix, date formats, compatibility), which could be tightened rather than the lean every-token-earns-its-place level.

2 / 3

Actionability

Concrete tool slugs, named parameters, example values ('properties/123456', '7daysAgo'), and a task→tool→params Quick Reference table give copy-paste-ready guidance; absence of literal code is not penalized for an instruction-only MCP skill.

3 / 3

Workflow Clarity

Workflows are clearly sequenced and Setup includes an ACTIVE-status validation checkpoint plus CHECK_COMPATIBILITY, but the batch workflow only mentions checking responses without a validate→fix→retry feedback loop, so it is capped at 2 per the batch-operations guideline.

2 / 3

Progressive Disclosure

Sections are well organized, but the skill is a ~224-line monolith with all detail inline and no reference files, so the <50-line exemption does not apply and content that could be split is not split.

2 / 3

Total

9

/

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 specific, distinctive description with good natural trigger terms, but it omits an explicit "Use when..." trigger clause, which caps completeness at 2.

Suggestions

Add an explicit "Use when..." clause (e.g., "Use when the user asks for Google Analytics reports, account/property listings, funnels, pivots, or key events") so both what and when are explicit.

Move the instruction "Always search tools first for current schemas" into the body Setup section so the description stays focused on capability and trigger guidance.

DimensionReasoningScore

Specificity

"run reports, list accounts/properties, funnels, pivots, key events" lists multiple specific concrete actions matching the score-3 anchor rather than the partial score-2 anchor.

3 / 3

Completeness

Clearly answers "what" but has no "Use when..." clause or explicit trigger guidance, so it is capped at 2 per the rubric guideline; the closing sentence is an instruction, not a trigger.

2 / 3

Trigger Term Quality

Natural terms a user would say (reports, accounts/properties, funnels, pivots, key events) give good coverage; not the generic/jargon-only case of score 1 or the partial coverage of score 2.

3 / 3

Distinctiveness Conflict Risk

Scoped to Google Analytics via Rube MCP (Composio) with distinct GA-specific triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
davepoon/buildwithclaude
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.