Content
81%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 fully sequenced, validation-checkpointed workflow and real bundle-file references. Its main weakness is conciseness — guidance on source states, freshness, and conflict handling is restated across multiple sections, inflating the token budget.
Suggestions
Consolidate the repeated awaiting_sources / source-state and idempotency guidance into a single section; it is currently restated in the blueprint, checkpoint, and finish sections.
Move the long CLI freshness / update-check protocol into a separate reference file (e.g. references/update-protocol.md) and summarize it in SKILL.md with a one-line pointer, to improve both conciseness and progressive disclosure.
Trim redundant restatements of the 'never create a replacement run/course' rule, which appears several times, to a single canonical statement.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient and densely packed with operational facts, but it runs to ~320 lines of repetitive guidance on CLI freshness, source states, conflicts, and idempotency that overlaps across sections (e.g., awaiting_sources no-op behavior restated multiple times), so it is noticeably over budget for what Claude needs. | 3 / 5 |
Actionability | Fully executable: every key step is a concrete command (`personwise version --json`, `course readiness --json`, `source add --run-id <run-id> --path <exact-path> --json`, etc.) with explicit flags, matching the copy-paste-ready anchor that covers the common cases. | 5 / 5 |
Workflow Clarity | Clear sequenced workflow with explicit validation checkpoints and feedback loops — readiness check before design, no `run advance` while sources are pending, validate fresh state before each mutation, read fresh state on CONFLICT rather than retrying — matching the anchor for explicit validation steps and error-recovery loops. | 5 / 5 |
Progressive Disclosure | Well-organized into clearly headed sections with bundle files referenced by real paths (`assets/bootstrap.sh`, `assets/bootstrap.ps1`) that exist in the bundle, but nearly all operational detail is inlined in SKILL.md rather than split into separate reference files, leaving minor organization gaps versus the ideal one-level-deep split. | 4 / 5 |
Total | 17 / 20 Passed |