Content
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-conceived skill that clearly defines an exploratory thinking mode with strong guardrails (no implementation). Its main weakness is verbosity—the extensive example dialogues, while helpful for illustrating the stance, consume significant tokens and could be condensed. The OpenSpec integration section is the most actionable and well-structured part, while the rest is more illustrative than instructive.
Suggestions
Condense the example dialogues significantly—keep one or two brief examples and move the rest to a separate EXAMPLES.md file to improve both conciseness and progressive disclosure.
Tighten the 'What You Might Do' section by removing the ASCII diagram example (which is meta—showing a diagram about using diagrams) and relying on the examples section to demonstrate visualization.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-written but is verbose for what it communicates. The extensive example dialogues with ASCII art, while illustrative, are lengthy and could be condensed. The 'What You Don't Have To Do' section and some repeated emphasis on 'don't implement' add bulk. However, much of the content does earn its place since this is a stance/mode definition rather than a procedural skill. | 2 / 3 |
Actionability | The skill provides some concrete guidance (bash commands like `openspec list --json`, file paths to read, a table mapping insight types to artifacts) but is largely descriptive of a stance rather than prescriptive. The example dialogues show what explore mode looks like but aren't executable instructions—they're illustrative scenarios. The OpenSpec integration section is the most actionable part. | 2 / 3 |
Workflow Clarity | This skill explicitly declares itself as 'a stance, not a workflow' with no fixed steps or required sequence, which is appropriate for its purpose. The content is clear about what to do (think, visualize, investigate) and what not to do (implement, auto-capture). The OpenSpec awareness section provides clear conditional workflows (when no change exists vs. when one exists). For this type of skill, the clarity is excellent. | 3 / 3 |
Progressive Disclosure | The content is entirely self-contained in one file with no bundle files. While the sections are well-organized with clear headers, the extensive example dialogues and ASCII art make this a long document that could benefit from splitting examples into a separate reference file. The OpenSpec artifact paths are referenced but there are no linked supporting documents. | 2 / 3 |
Total | 9 / 12 Passed |