Content
71%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.
The body is a tight, well-structured deprecation shim: a clear 3-step activation workflow with a concrete resolve command and an explicit hand-off terminator. Its only weakness is an over-described introductory paragraph that enumerates the target skill's full surface unnecessarily.
Suggestions
Trim the introductory paragraph to one sentence; the enumerated modes and research types of bmad-deep-recon belong in that skill, not this shim.
Optionally state the expected outcome of the resolve_customization command (e.g. 'emits the four legacy field values') so the hand-off data contract is explicit.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient, but the introductory paragraph padding the full capability surface of bmad-deep-recon ('drafts deep-research prompts... across market, domain, technical, competitive, user-voice, and academic-lit types') is unnecessary detail for a forwarding shim. | 3 / 5 |
Actionability | It provides a concrete, copy-paste-ready resolve_customization command and explicit hand-off instructions, with only the final 'Invoke bmad-deep-recon with...' being descriptive rather than a literal command. | 4 / 5 |
Workflow Clarity | Three steps are clearly sequenced with an explicit terminator ('do not execute any further steps in this shim'), but there are no validation checkpoints; this is acceptable for a non-destructive handoff yet keeps it below a 5. | 4 / 5 |
Progressive Disclosure | The skill is well under 50 lines, has no bundle files, and is organized into a heading plus a numbered activation list, satisfying the simple-skill exception for a top score. | 5 / 5 |
Total | 16 / 20 Passed |