Content
100%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A concise, well-structured instruction skill that gives concrete tool-driven guidance and explicit bucket heuristics with a clearly sequenced, conditionally-gated workflow. It stays lean while remaining fully actionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~30-line body is lean and assumes Claude's competence, with no concept explanations or filler; every section earns its tokens. | 3 / 3 |
Actionability | Names specific tools (search_emails, batch_read_email, read_email_thread) with concrete decision rules for when to use each and explicit bucket criteria, giving actionable guidance despite the absence of code. | 3 / 3 |
Workflow Clarity | The numbered 1-6 workflow is clearly sequenced with explicit conditional gates ('only when snippets are not enough', 'when a message appears to be part of an active conversation') plus verification caveats in the Output section. | 3 / 3 |
Progressive Disclosure | Well-organized into Overview, Workflow, Bucket Heuristics, and Output sections, with the single external reference (../gmail/SKILL.md) clearly signaled and one level deep; no unnecessary bundle files. | 3 / 3 |
Total | 12 / 12 Passed |