Content
92%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 well-structured, highly actionable skill body: copy-paste commands, a sequenced workflow with exit-code validation and feedback loops, and clean one-level-deep progressive disclosure to real bundle files. The only slack is mild redundancy between the 'What this does' lede and the workflow section.
Suggestions
Tighten or fold the 'What this does' paragraph into the workflow, since it restates the gate/agenda/extract capabilities already covered by the numbered steps and the description.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is efficient and assumes Claude's competence (no 'what is a meeting' padding), but the 'What this does' section largely restates the description and the numbered workflow, so a few tokens could be trimmed. Not a 5 because of that mild redundancy; not a 3 because the rest is lean and load-bearing. | 4 / 5 |
Actionability | Provides fully executable, copy-paste-ready bash commands with concrete flags ('python scripts/meeting_cost_calculator.py --attendees 6 --minutes 60 --avg-rate 90 --include-refocus --has-decision --has-agenda --has-owner') plus a scripts-role table covering the common cases. | 5 / 5 |
Workflow Clarity | A clearly sequenced gate → agenda → run → extract flow with explicit validation via exit codes (exit 2 ASYNC, exit 3 NOT-READY, exit 0 MEET), a feedback loop ('Iterate — trim or split the named topic and re-run until it fits; the stop condition is exit 0'), and a completion check ('done when every action has an owner and a date'). | 5 / 5 |
Progressive Disclosure | SKILL.md is a concise overview that points one level deep to 3 reference files, 3 scripts, and 2 assets, each rendered as a clearly signaled markdown link with a one-line description; all referenced paths resolve to real files in the bundle. | 5 / 5 |
Total | 19 / 20 Passed |