CtrlK
BlogDocsLog inGet started
Tessl Logo

exploring-mcp-tool-quality

Investigate the quality of PostHog MCP tool calls — error rates, latency, reach, and which tools are failing or slow. Use when the user asks "which MCP tool has the highest error rate?", "what's the slowest tool?", "which tools fail most often?", "how reliable is tool X?", wants a tool-quality matrix, or pastes an MCP analytics tool-quality / dashboard URL and asks what it shows.

71

Quality

87%

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

83%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.

A well-organized, actionable skill body that inlines the canonical query and delegates the rest to a single shared reference with clear navigation. Minor conciseness trimming and a more explicit cross-tool validation checkpoint would lift it to the top anchors.

Suggestions

Tighten the 'two rules' and matrix/failures prose to bullets or shorten the repeated models-mcp.md cross-links to recover conciseness.

Add an explicit verification checkpoint to the cross-tool workflow — e.g. 'if your SQL ranking disagrees with the tool-quality screen, prefer the typed tool' as a numbered validate step rather than a note.

Consider moving the failure-bucketing SQL inline block entirely to the reference since the typed posthog:query-mcp-tool-failures tool is the recommended path, leaving only the headline error-rate query in the body.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's competence — inlines only the headline query and defers the rest to the shared reference — but the two-rules section, the matrix/failures prose, and repeated cross-links to models-mcp.md add a little that could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready HogQL/SQL for the canonical error-rate and failure-bucketing queries, names the exact typed tools with their parameters, and gives explicit UI link templates — covering the common cases concretely.

5 / 5

Workflow Clarity

The error-rate workflow is well sequenced with a HAVING-volume guard and rate+volume reporting guidance, but the queries are read-only analytics rather than destructive/batch operations, and the cross-tool path lacks an explicit validate-against-the-screen checkpoint beyond a 'prefer the typed tool' note.

4 / 5

Progressive Disclosure

Good structure with clear section headers and well-signaled one-level-deep references to a single shared reference (models-mcp.md) plus related skills; the inline headline query is justified, though the body still carries a fair amount of detail that lives in the reference.

4 / 5

Total

17

/

20

Passed

Description

91%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 strong description: concrete capabilities, multiple natural trigger phrases, an explicit 'Use when' clause, and a distinctive niche. It is one of the longer descriptions, but the length is earned by trigger-phrase coverage rather than padding.

DimensionReasoningScore

Specificity

Lists concrete capabilities — 'error rates, latency, reach' and 'which tools are failing or slow' — but reaches those via typed-tool names and a tool-quality matrix rather than a flat enumeration of actions, so minor coverage gaps keep it just below comprehensive.

4 / 5

Completeness

Explicitly answers 'what' (investigate tool quality: error rates, latency, reach, failing/slow tools) and 'when' via an explicit 'Use when...' clause listing concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Quotes a broad set of natural trigger phrases users would actually say — 'which MCP tool has the highest error rate?', 'what's the slowest tool?', 'which tools fail most often?', 'how reliable is tool X?' — plus a tool-quality matrix and pasted-URL case.

5 / 5

Distinctiveness Conflict Risk

The MCP analytics / tool-quality niche is narrow with distinctive triggers tied to PostHog MCP tool quality and dashboard URLs, minimizing overlap with sibling skills like session or intent exploration.

5 / 5

Total

19

/

20

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

relative_links

Relative link issues: 5 suspicious

Warning

Total

15

/

16

Passed

Repository
PostHog/posthog
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.