Content
81%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, operationally concrete skill body with a clear multi-step workflow, explicit validation/polling checkpoints, and a useful gotchas checklist. It is lean and assumes competence, with only minor room to tighten framing prose and show tool calls verbatim.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Dense and operational throughout, focused on PostHog-specific internals (scaled coordinates, fold fields) Claude would not already know; the opening framing paragraph and a few explanatory sentences could be trimmed slightly, but no generic concept padding. | 4 / 5 |
Actionability | Provides a copy-paste-ready SQL block and names concrete tools with specific parameters (heatmaps-list type/aggregation/limit, viewport_width_min/max, heatmaps-saved-create/get polling); tool invocations are described in prose rather than shown as literal call payloads, a minor gap. | 4 / 5 |
Workflow Clarity | A clear six-step sequence with explicit validation checkpoints — poll heatmaps-saved-get 'until status is completed', check has_more for truncation, and verify opt-in/URL before concluding no engagement — plus a Gotchas section acting as an error-recovery checklist. | 5 / 5 |
Progressive Disclosure | Well-organized into clearly headed sections (Core principle, The flow, Reading the signals, Gotchas) and appropriately self-contained with no nested references; sibling-skill pointers are one level deep and clearly signaled, though some inline material (signals table) could theoretically be split out. | 4 / 5 |
Total | 17 / 20 Passed |