Content
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a well-structured procedural skill with clear sequencing, actionable defaults, explicit quality gates, and clean one-level-deep references. The only soft spot is mild redundancy between the frontmatter triggers and the 'When to Use' list, plus portability notes that slightly pad the token budget.
Suggestions
Trim the 'When to Use' list or fold it into the frontmatter to avoid re-stating the same triggers already in the description.
Shorten 'Notes for Other Clients' to only the portability essentials, since the Open-Brain-tool-name adaptation is already covered in the Process step.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient procedural prose with no explanations of concepts Claude already knows, but the 'When to Use' section duplicates the frontmatter triggers and 'Notes for Other Clients' adds portability commentary that could be tightened, matching the mostly-efficient-but-could-be-tighter anchor. | 2 / 3 |
Actionability | As an instruction-only skill it gives concrete, specific guidance: an 8-step process, a default output structure with per-item sub-fields, explicit defaults (7-day window), and a 'score before writing' gate; per scoring notes the absence of code is not penalized when guidance is this actionable. | 3 / 3 |
Workflow Clarity | A clearly sequenced 8-step workflow with explicit checkpoints and feedback (e.g. 'If live search is not available... say the diff is source-bounded', 'explicitly label speculation', 'If evidence is thin, say the week was thin'), matching the clear-sequence-with-checkpoints anchor. | 3 / 3 |
Progressive Disclosure | The overview points to two real, clearly-signaled one-level-deep references (starter-universe.md and live-search-upgrade.md), both present and relevant, each invoked conditionally — matching the clear-overview-with-well-signaled-references anchor with no nested chaining. | 3 / 3 |
Total | 11 / 12 Passed |