Content
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A concise, highly actionable skill body with concrete Amplitude tool calls and a clear output template. Its main weakness is workflow clarity: the sequence is clear but lacks validation checkpoints or error-recovery guidance for edge cases like empty results.
Suggestions
Add validation checkpoints between steps — e.g. after `get_feedback_sources` and `get_feedback_insights`, verify data was returned before proceeding, and if a theme is empty expand the date range or filter set.
Include an explicit error-recovery/feedback loop (e.g. 'If no insights match, broaden `types` or widen the date range, then re-run') to lift workflow clarity toward the level-3 anchor.
Fix the 'Inlcude' typo in the Prioritized Recommendations bullet so the guidance is copy-clean.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean — concrete tool calls, filter value lists, and a compact output template — and assumes Claude's competence without explaining concepts Claude already knows, fitting the 'every token earns its place' anchor rather than the padded level-2 example. | 3 / 3 |
Actionability | Provides specific executable tool calls (e.g. `Amplitude:get_feedback_insights` with filter values `request`, `complaint`, `lovedFeature`, `bug`, `painPoint`) plus a copy-ready output structure with `[p0]`-`[p3]` priorities, matching the fully-executable anchor. | 3 / 3 |
Workflow Clarity | The five steps are clearly sequenced, but there are no validation checkpoints or feedback loops (e.g. verify sources returned data, handle empty insights by widening filters), matching 'steps listed but validation gaps; checkpoints missing or implicit' rather than the level-3 anchor requiring explicit validation steps. | 2 / 3 |
Progressive Disclosure | No bundle files exist and the ~50-line skill is self-contained with well-organized section headers (Instructions steps + Best Practices), so the 'under 50 lines, no external references needed, well-organized sections' guideline yields a 3. | 3 / 3 |
Total | 11 / 12 Passed |