Content
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A tightly written, actionable activation workflow with clear sequencing and a verification checkpoint. The main weakness is progressive disclosure: the core detail is delegated to ./instructions.md, which is not present in the bundle, leaving a dead reference.
Suggestions
Include the referenced ./instructions.md (or place it under references/) so the primary delegated content actually exists in the bundle.
For the fallback merge procedure, consider moving the detailed base->team->user merge rules into a short reference note to keep the activation section even leaner.
Add a one-line note clarifying that the {project-root}/_bmad/* paths are external to the skill bundle, so readers do not expect them under the skill root.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence — no concept explanations or padding — with every section (conventions, activation steps, config loading) earning its place; the dense merge rules are necessary procedural detail, not fluff. | 3 / 3 |
Actionability | It gives concrete executable guidance: an exact resolve script invocation ('python3 {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --key workflow') plus a precise ordered fallback (three named files in base->team->user order with explicit merge rules). | 3 / 3 |
Workflow Clarity | The activation process is a clearly sequenced Step 1-6 workflow with an explicit failure fallback and a final verification checkpoint ('confirm every entry was executed in order before proceeding'), matching the level-3 anchor. | 3 / 3 |
Progressive Disclosure | Sections are well-organized and the main reference ('Read fully and follow: ./instructions.md') is clearly signaled, but that referenced file is absent from the bundle (no references/scripts/assets dirs exist), so the one-level-deep pointer is to a missing target. | 2 / 3 |
Total | 11 / 12 Passed |