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.

79

Quality

100%

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

100%

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

A lean, highly actionable body that leads with the one non-obvious data fact, gives complete executable HogQL recipes plus typed-tool alternatives, and cleanly splits the headline query inline from the rest in a shared one-level-deep reference. Workflow sections are clearly sequenced with explicit guardrails appropriate to read-only analytics.

DimensionReasoningScore

Conciseness

Opens with the non-obvious fact Claude would not know ("no dedicated ClickHouse table — every field lives as a `$mcp_*` property on `events`") and never pads with basic PostHog/ClickHouse/MCP explanations; the 'two rules that matter most' framing keeps every token earning its place, matching the 'lean and efficient' anchor.

3 / 3

Actionability

Provides two complete, copy-paste-ready HogQL queries with exact property names, required casts (toBool/toFloat), HAVING volume floors and LIMIT clauses, plus named typed tools with their toolName + dateRange parameters and concrete UI link templates — fully executable, not pseudocode.

3 / 3

Workflow Clarity

The canonical 'which tool has the highest error rate' workflow is fully sequenced with explicit guardrails (effective-tool-name rule, mandatory time range, volume floor) and a report-both-rate-and-volume follow-up; the read-only nature means the destructive-ops validation cap does not apply, fitting the top anchor.

3 / 3

Progressive Disclosure

Inlines only the headline query and defers matrix/latency/harness recipes to a single shared, well-signaled one-level-deep reference with explicit 'Read it before writing queries' navigation; the local bundle dirs (references/scripts/assets) are empty, so scoring reflects the clean repo-external reference structure rather than bundle files.

3 / 3

Total

12

/

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.

A precise, third-person description that names specific metric capabilities and pairs them with a rich, verbatim set of natural-language triggers. It clearly answers both what the skill does and when to invoke it, and is well-distinguished from adjacent MCP analytics skills.

DimensionReasoningScore

Specificity

Names concrete capabilities across multiple dimensions — "error rates, latency, reach, and which tools are failing or slow" — matching the 'lists multiple specific concrete actions' anchor rather than the 'names domain and some actions' anchor at 2.

3 / 3

Completeness

Explicitly answers both what (investigate PostHog MCP tool-call quality across error rate/latency/reach/failures) and when (an explicit 'Use when...' clause with several concrete triggers), satisfying the top anchor rather than the 'when missing or only implied' anchor at 2.

3 / 3

Trigger Term Quality

Quotes natural user phrasing verbatim ("which MCP tool has the highest error rate?", "what's the slowest tool?", "how reliable is tool X?") plus 'tool-quality matrix' and pasted-URL trigger, giving full coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Scoped tightly to PostHog MCP tool-quality analytics with triggers unlikely to fire for sibling skills (sessions, intent clusters referenced in the body), fitting the 'clear niche with distinct triggers' anchor.

3 / 3

Total

12

/

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

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.