Content
70%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 content is highly actionable with a well-sequenced, validation-rich workflow, but it is long for a SKILL.md with some repetition and would benefit from splitting detailed reference material into separate files.
Suggestions
Consolidate the repeated awaiting_sources no-op and 'never create a replacement run' guidance into a single authoritative section to reduce token cost.
Move the version/update state-machine and source-lifecycle detail into a one-level-deep reference file (e.g. references/cli-workflow.md) and link to it from the main body.
Enumerate the blueprint JSON fields explicitly so the create step is fully copy-paste ready.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense and assumes Claude's competence, but several instructions repeat across sections (the awaiting_sources no-op behavior and 'never create a replacement run' each appear ~3 times), so it could be tightened. | 3 / 5 |
Actionability | Provides concrete, executable commands with exact flags and JSON I/O ('personwise --account <alias> course readiness --json', 'course create --input <blueprint.json> --json'), with minor gaps such as partial blueprint field enumeration. | 4 / 5 |
Workflow Clarity | Clearly sequenced workflow with explicit validation checkpoints (readiness can_create=false blocks; source status must be ready before run advance; re-read run before mutation) and detailed feedback loops for source retry/detach and conflict recovery. | 5 / 5 |
Progressive Disclosure | Section structure is good and the asset references (assets/bootstrap.sh, assets/bootstrap.ps1) are real and clearly signaled, but the entire workflow plus sizable state-machine detail is inlined rather than split into one-level-deep reference files. | 3 / 5 |
Total | 15 / 20 Passed |