Content
87%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 concise, fully actionable single-purpose skill with excellent token efficiency and clean structure. Its main weakness is the absence of any validation or verification step around a destructive rm -rf reset, which caps workflow clarity at 3.
Suggestions
Add a verification checkpoint after the reset, e.g. confirm `/data/db/app.db` was recreated and services restarted cleanly before declaring success.
Guard the destructive `rm -rf /data/db/* /data/config/*` step by checking the killall succeeded and that the paths exist, with a feedback loop (on failure: re-kill and retry).
Include a brief note that this is irreversible and wipes user config, so the reset is run only when explicitly intended.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient with no padding or explanation of concepts Claude already knows; every section (Command, What This Does, After Reset, Database Location) earns its place. | 5 / 5 |
Actionability | Fully executable, copy-paste-ready bash commands with concrete paths cover the single common case completely, including the post-reset restart command. | 5 / 5 |
Workflow Clarity | Steps are clearly sequenced (kill, delete, provision config, init db, restart), but this destructive rm -rf operation has no validation or verification checkpoint, capping workflow clarity at 3 per the destructive-operations rule. | 3 / 5 |
Progressive Disclosure | Under 50 lines with no need for external references and well-organized section headers, so the simple-skill exception earns the top score. | 5 / 5 |
Total | 18 / 20 Passed |