Content
85%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.
The body is a well-structured, highly actionable workflow with explicit validation and error-recovery steps, appropriate for an explicit-invocation command skill. Its main weakness is redundancy: the command block is repeated across two sections, slightly inflating the token budget.
Suggestions
De-duplicate the bash command block between section 2 and section 3 by defining it once and referencing it, to reduce token waste.
Consider trimming the 'guidelines, not a rigid script / defer to CLAUDE.md' boilerplate if project conventions already cover it.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean with concrete commands, but the full bash command block (the read/heredoc + git rev-parse + roborev review snippet) is duplicated verbatim in both section 2 and section 3, and the 'guidelines, not a rigid script' boilerplate could be trimmed, fitting 'mostly efficient but could be tightened.' | 2 / 3 |
Actionability | It provides fully executable, copy-paste-ready bash commands including the heredoc ref capture, git rev-parse validation, and the exact roborev review invocation with flag variations, matching the 'fully executable code/commands' anchor. | 3 / 3 |
Workflow Clarity | A clearly sequenced 5-step workflow with an explicit validation checkpoint (input validation / git rev-parse), error-handling feedback loop (report errors, suggest roborev status/init), and a checklist for presenting results matches the top anchor. | 3 / 3 |
Progressive Disclosure | No bundle files are needed and the content is well-organized into clearly signaled sections (Usage, Instructions, Examples, See also) with only shallow one-level cross-skill links, which for a self-contained skill earns the top anchor per the simple-skills note. | 3 / 3 |
Total | 11 / 12 Passed |