Content
85%Weight 40%Scale 1-3Reviews 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 and well-sequenced with explicit validation/confirmation checkpoints, and it is appropriately self-contained with clean organization. The only weakness is redundancy: subcommand logic and the default-state/confidentiality rules are restated multiple times, leaving room to tighten token efficiency.
Suggestions
Consolidate the subcommand list: keep either the brief summary (lines 13-17) or the detailed 'Subcommand logic' section, and cross-reference from the other rather than restating both.
State the default-off / cross-matter confidentiality rule once (e.g. in 'Cross-matter context') and reference it from 'Notes' and the intro instead of repeating the explanation in three places.
Tighten the 'matter.md template' and intake list by removing prose rationale already implied by field names, to reclaim tokens without losing actionability.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is largely efficient and assumes Claude's competence (no basic concept explanations), but subcommand logic is stated twice (short list lines 13-17 then again in 'Subcommand logic') and the default-off/confidentiality points are restated across sections, so it could be tightened. | 2 / 3 |
Actionability | Provides concrete executable guidance — exact file paths, the specific 'Active matter:' line to edit, full matter.md and history.md templates, and an enumerated intake questionnaire — which the rubric rewards for instruction-only skills. | 3 / 3 |
Workflow Clarity | Each subcommand is a clearly numbered sequence with explicit confirmation checkpoints ('confirm before writing', 'Show the user the matter.md summary', no auto-switch), and the destructive close archives with a dated history entry and active-matter fallback. | 3 / 3 |
Progressive Disclosure | No bundle files exist, so the skill is self-contained and well-organized under clear section headers with no nested/deep references, which the rubric permits to score 3 for skills with no external references. | 3 / 3 |
Total | 11 / 12 Passed |