Content
78%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A well-structured, actionable body that gives concrete tool params, a CLI example, and clear result interpretation with a diagnosis loop. It is concise and appropriately scoped for a simple skill, with only minor trimmable redundancy and a small gap in full example invocations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence (no padding about what PostHog or cookies are), but the explanatory line 'This matches the behavior of a single visitor browsing multiple pages on the same site' and overlap between the intro and 'When to use' bullets are minor trimmable instances, keeping it just below fully lean. | 4 / 5 |
Actionability | Provides the concrete MCP tool name `simulate_returning_user`, all parameters with defaults, a copy-paste CLI command (`traffic-sim returning-user --url A --url B --url C`), and specific result signals; a full sample tool invocation and slight ambiguity around MCP-vs-CLI multi-page support are minor gaps below fully copy-paste ready. | 4 / 5 |
Workflow Clarity | Clear invoke-then-interpret sequence with an explicit pass criterion ('verified: true and pageviews >= page_views') and an error-recovery feedback loop ('Different distinct_id per visit... Inspect the raw posthog_requests for $session_id values to diagnose'); not a rigorous numbered multi-step validated workflow, so it sits below the checklist-level 5. | 4 / 5 |
Progressive Disclosure | Under 50 lines with no external references needed and no bundle files present; content is organized into three clearly headed sections (When to use, How to invoke, Interpreting the result), satisfying the simple-skill exception for a top score on well-organized structure. | 5 / 5 |
Total | 17 / 20 Passed |