Content
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A high-quality instructional skill body: actionable, well-sequenced, and well-organized. Its only real weakness is conciseness — the closing recap section duplicates earlier guidance and could be tightened.
Suggestions
Trim the 'What consistently goes wrong' section where it restates earlier points (over-questioning, hidden answers, jargon-as-skip-signal, overdelivering visuals); keep only anti-patterns not already covered to remove redundancy.
Consolidate 'Showing, not just telling' with the visual guidance already in 'A toolkit of moves' to reduce re-explanation of the same scaffold idea.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is information-dense and avoids explaining basics Claude already knows, but the 'What consistently goes wrong' recap restates points made earlier (over-questioning, hidden answers, jargon-as-skip-signal, overdelivering visuals), adding length that could be trimmed. | 2 / 3 |
Actionability | Concrete, specific guidance throughout: example calibrating questions ('Is it the setup or the mechanics that's throwing you?'), named moves with examples, an explicit widget-call sequence (read_me then show_widget with prose outside the call), and ready-to-use response lines. | 3 / 3 |
Workflow Clarity | Clear sequenced flow — diagnose first, one-step-per-turn rhythm, then detect completion — with explicit checkpoints (a diagnosis gate, done-signals like 'explains it back correctly') and branch handling for stuck vs impatient learners. | 3 / 3 |
Progressive Disclosure | Self-contained and well-organized into clear headed sections with an overview opening paragraph; no external references are needed and none are nested, so the single-file structure is appropriate for a skill of this size. | 3 / 3 |
Total | 11 / 12 Passed |