Content
78%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A tight, well-structured instruction skill: it gives an unambiguous process, a complete PRD template with a worked example, and explicit do/don't rules without wasting tokens. The template is appropriately inlined for a skill this size, and the only improvements are a post-publish verification step and slightly leaner concept definitions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is directive and lean — instructions, a process, and a template with no padding. Minor trims are possible (the one-sentence deep-module definition, and "extremely extensive" restating "LONG"), which keeps it just below the every-token-earns-its-place anchor. | 4 / 5 |
Actionability | Concrete, executable guidance for an instruction-only skill: a 3-step process, a full sectioned PRD template, a worked user-story example, and explicit rules ("Apply the `ready-for-agent` triage label", "Do NOT include specific file paths"). Below 5 only because publishing mechanics are deferred to `/setup-matt-pocock-skills` and no finished-PRD example is given. | 4 / 5 |
Workflow Clarity | Steps 1-3 are clearly sequenced with an explicit user checkpoint ("Check with the user that these modules match their expectations" and which modules need tests). Minor gap: no verification step after publishing to the issue tracker, so it sits at the most-checkpoints anchor rather than the full feedback-loop anchor. | 4 / 5 |
Progressive Disclosure | A small single-purpose skill with no bundle files and no need for external references; the body is well-organized into a Process section and a clearly delimited template, satisfying the simple-skill exception for a top score. | 5 / 5 |
Total | 17 / 20 Passed |