Content
77%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.
A highly actionable, well-sequenced operational skill with strong validation checkpoints and feedback loops. Its main weaknesses are near-verbatim repetition of a few rules and a monolithic structure that inlines material which could live in reference files.
Suggestions
Deduplicate the awaiting_sources 200 no-op explanation and the 'never create a replacement run' rule so each appears once, cross-referencing from the second occurrence.
Extract the CLI command catalog and the access_mode URL/evidence rules into a separate references/ file (e.g. CLI-REFERENCE.md), keeping SKILL.md as an overview that points to it.
Consolidate the update/freshness handling into one subsection to avoid restating the 'never substitute another command/origin' guidance multiple times.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is operational and avoids explaining concepts Claude already knows, but several rules (the awaiting_sources 200 no-op and "never create a replacement run") are restated near-verbatim across sections and could be tightened. | 3 / 5 |
Actionability | Provides fully executable, copy-paste-ready commands (e.g. `personwise auth begin --service personwise.ai --json`, `course create --input <blueprint.json> --json`, `run wait --run-id <run-id> --timeout-seconds 1800 --json`) covering the common cases. | 5 / 5 |
Workflow Clarity | Sequences readiness → blueprint → source-status gate → run-wait checkpoints with explicit validation steps and feedback loops (source retry, detach-and-replace, read_current_state conflict handling) for error recovery. | 5 / 5 |
Progressive Disclosure | Bundle assets (bootstrap.sh/.ps1, service-descriptor.signed.json) are referenced cleanly one level deep, but the bulk of the CLI workflow and access-mode reference is inlined in a single 330-line SKILL.md with no separate reference docs. | 3 / 5 |
Total | 16 / 20 Passed |