Content
86%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 body is highly actionable and well-structured for a self-contained CLI skill, with concrete commands and clear workflows; its only weakness is minor redundancy in the prohibition warnings and the absence of explicit verification steps.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and assumes Claude's competence (no explaining what a KPI is), but the `write_file`/`mkdir` prohibition appears both in the CRITICAL banner and the "What NOT to do" section, a minor trim opportunity. Not 5 due to that duplication; not 3 because it is efficient, not padded. | 4 / 5 |
Actionability | Copy-paste-ready `hivemind goal`/`kpi` commands with flags and arguments, plus a fully worked multi-line `--agent capture` example covering the common cases. Not 4 because there are no meaningful execution gaps. | 5 / 5 |
Workflow Clarity | Numbered workflows for adding and resuming goals are clearly sequenced with guardrails ("always use `goal get`"). No validate→fix→retry loop, but goal ops are non-destructive so the cap-at-3 does not apply; not 5 because there are no explicit verification checkpoints. | 4 / 5 |
Progressive Disclosure | A self-contained ~58-line body with clean section headers (Commands, Workflow, Capture, Resume, What NOT to do), no nested file references, and no need for bundle files. Per the simple-skills note, well-organized sections alone warrant a 5 here. | 5 / 5 |
Total | 18 / 20 Passed |