CtrlK
BlogDocsLog inGet started
Tessl Logo

analyze-mcp-server

Analyze MCP server usage instrumented with Amplitude's MCP Analytics SDK: break usage and errors down by tool, read the rationales within each tool to see what callers are trying to do, and produce a prioritized write-up of actionable fixes. Use this skill whenever the user asks to understand how their MCP server is being used, what agents/users are trying to do with it, why tool calls are failing, what to fix or improve in their MCP server, or asks for an "MCP usage report", "tool error analysis", "intent analysis", "rationale clustering", or "MCP insights". Also trigger when the user mentions [MCP]-prefixed events, tool rationale, tool call errors, or just finished instrumenting their MCP server and wants to see what the data says. Requires the Amplitude MCP connector.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

70%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.

The body is highly actionable with a well-sequenced, validated workflow, but it leans long and keeps material (a query cookbook and archetype table) inline that would fit a reference file. Tightening repeated warnings and splitting the cookbook would lift conciseness and progressive disclosure.

Suggestions

Deduplicate the [MCP]-prefix/Title-Case guidance into a single 'Known pitfalls' note and reference it from Prerequisites and Phase 0 rather than restating it.

Move the Query Cookbook (and optionally the error-archetype table) into a references/ file and link to it from SKILL.md so the overview stays lean.

Name the concrete Amplitude chart/render tools instead of the abstract 'ad-hoc chart query + render tools' phrasing so the charting step is copy-paste ready.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept padding, but the [MCP]-prefix/Title-Case warning recurs in Prerequisites, Phase 0, and Known pitfalls, and rationale-hygiene guidance repeats; the dense ~275-line body could be tightened.

3 / 5

Actionability

Executable JSON query definitions with specific groupByLimit values and exact property names, plus a fix-archetype table and a report template; minor gaps where chart-rendering and Amplitude tool names stay abstract ('use the ad-hoc chart query + render tools').

4 / 5

Workflow Clarity

A clear Phase 0→5 sequence with explicit validation checkpoints — Phase 0 warns on low volume, Phase 5 mandates re-verifying a headline number a second way and recomputing every percentage, cutting or labeling unverifiable figures.

5 / 5

Progressive Disclosure

Well-organized into named phases, but no bundle files exist and nothing is offloaded to references; the large query cookbook and archetype table are inlined where a one-level-deep reference file would aid navigation.

3 / 5

Total

15

/

20

Passed

Description

100%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.

The description is exemplary: it states concrete capabilities, supplies a rich set of natural trigger phrases, and explicitly covers both what and when with low conflict risk. No meaningful gaps to flag.

DimensionReasoningScore

Specificity

Lists multiple concrete, distinct actions — 'break usage and errors down by tool', 'read the rationales within each tool', 'produce a prioritized write-up of actionable fixes' — matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers both what (analyze/break down/read rationales/produce write-up) and when, with multiple 'Use this skill whenever...' and 'Also trigger when...' clauses carrying concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural phrasing users would say — 'MCP usage report', 'tool error analysis', 'intent analysis', 'rationale clustering', 'MCP insights' — plus behavioral triggers like 'just finished instrumenting their MCP server'.

5 / 5

Distinctiveness Conflict Risk

A clearly defined niche (Amplitude MCP Analytics SDK analysis) with distinct, instrumentation-specific triggers; minimal risk of firing for an unrelated skill.

5 / 5

Total

20

/

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
amplitude/builder-skills
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.