Content
92%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 tight, highly actionable skill body: executable JSON examples, a clear format-selection table, and an explicit decision flow for the seconds case. The only minor weakness is slight redundancy across the five examples.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and assumes Claude's competence — no padding about what PostHog or formulas are, and every section earns its place — but the five JSON examples carry minor redundancy (e.g. the revenue and fixed-currency snippets overlap), keeping it just short of fully token-optimal. | 4 / 5 |
Actionability | Fully executable: a format-value table mapping series type to rendered output, named trendsFilter fields, and five complete copy-paste-ready JSON snippets covering the common cases (duration_ms, duration, currency, fixed-currency, percentage_scaled). | 5 / 5 |
Workflow Clarity | The seconds-section decision flow is unambiguous with explicit checkpoints (silently default to duration; confirm only when the user pins a fixed unit; in one-shot MCP contexts just pick duration), and the update section sequences the fix with an explicit scope guard. The non-destructive, single-purpose nature lets the simple-skill exception apply. | 5 / 5 |
Progressive Disclosure | Self-contained with no bundle files present or referenced, and well-organized sections (anti-pattern, available formats, currency, seconds, examples, updating) with nothing oversized inlined that belongs in a separate file. | 5 / 5 |
Total | 19 / 20 Passed |