Name: exploring-mcp-tool-usage
Rating: 72 (1 reviews)
Author: PostHog

exploring-mcp-tool-usage

Starting point for exploring how a PostHog MCP server's tools are used — routes a broad question to the typed tool that answers it. Use when the user asks "how is my MCP doing?", "what should I look at?", "explore my tool calls", "who uses my MCP tools?", "what are agents doing with the MCP?", or pastes an MCP analytics URL without a specific question. Offers a menu of questions, each backed by a query tool, then hands off to the focused skill.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%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-structured, highly actionable routing skill that assumes competence and delegates detail to one-level-deep references. The main cleanup is consolidating the repeated effective-vs-raw tool-name caveat.

Suggestions

State the query-mcp-tool-failures raw-vs-effective tool-name exception once in 'Finding the tool name' and reference it from the other two spots instead of repeating the full explanation each time.

Add a one-line validation note for the governed-metric path (e.g., confirm mcp_tool_call_fail_pct was returned and not drifted before reporting the headline) to strengthen the existing checkpoint.

Consider a second short copy-paste example for a second common case (e.g., query-mcp-tool-failures with neighborDirection) so the most frequent flows each have an executable template.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence — no generic explanation of what an MCP server is — but the effective-vs-raw tool-name exception for query-mcp-tool-failures is stated three times (governed-metric section, suggested-questions table, finding-the-tool-name section) and could be consolidated.	4 / 5
Actionability	Fully executable guidance: concrete tool names, exact parameters (toolName, dateRange, neighborDirection), a copy-paste call example with JSON, and a question→tool mapping table covering the common cases.	5 / 5
Workflow Clarity	Clear sequenced gates — governed-metric-first before typed tools, rank→pick→drill-in for the tool name, call→offer-follow-up — with the noncanonical-labeling checkpoint; this is a routing skill (not destructive/batch), with only minor validation gaps.	4 / 5
Progressive Disclosure	Well-organized sections with SQL schema/recipes delegated to a clearly signaled one-level-deep models-mcp.md reference and a Related skills section; no monolithic bulk content is inlined and navigation is easy.	5 / 5
	Total	18 / 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, trigger-rich description that clearly states both what the skill does (route broad MCP-usage questions to the right typed tool) and when to use it. Minor room to tighten distinctiveness against the sibling focused skills.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete routing actions — 'routes a broad question to the typed tool that answers it', 'Offers a menu of questions, each backed by a query tool, then hands off to the focused skill' — but coverage of the underlying analytical operations is indirect via the menu rather than enumerated.	4 / 5
Completeness	Explicitly answers both 'what' (front door for exploring MCP tool usage; menu → route → hand off) and 'when' via an explicit 'Use when...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases a user would actually say — 'how is my MCP doing?', 'what should I look at?', 'explore my tool calls', 'who uses my MCP tools?', 'what are agents doing with the MCP?', plus 'pastes an MCP analytics URL without a specific question'.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche as the 'starting point' / 'front door' for broad questions with PostHog-MCP-specific triggers, but has minor overlap risk with the focused sibling skills it routes to.	4 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 suspicious	Warning

	Total	15 / 16 Passed

Repository: PostHog/posthog
Path: products/mcp_analytics/skills/exploring-mcp-tool-usage/SKILL.md
Commit: 57503b8

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.