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, actionable deprecation shim: it provides an executable customization step, an explicit handoff to bmad-deep-recon with the right parameters, and a clear stopping point, with only minor verbosity in the opening summary.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient with concrete steps and no explanation of concepts Claude already knows, but the opening sentence's full enumeration of bmad-deep-recon's surface (draft/process/run modes, six research types, custom shapes) is informational padding that could be tightened, matching the 'mostly efficient but could be tightened' anchor rather than the fully lean 3-anchor. | 2 / 3 |
Actionability | It gives an executable command (`uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow`), explicit invocation parameters (research type technical, the four legacy fields, original input verbatim), and a clear stopping directive, matching the 'fully executable guidance; copy-paste ready' anchor. | 3 / 3 |
Workflow Clarity | The 'On Activation' section is a clearly numbered 3-step sequence with an explicit handoff and stop condition ('bmad-deep-recon takes the workflow from here — do not execute any further steps in this shim'); as a simple non-destructive forwarding shim, the simple-skills note allows a 3 without validation feedback loops. | 3 / 3 |
Progressive Disclosure | At under 50 lines with no bundle files and no need for external references, the well-organized sections (deprecation heading, summary paragraph, 'On Activation' steps) satisfy the rubric's note that such simple skills can score 3 on structure alone. | 3 / 3 |
Total | 11 / 12 Passed |