Content
96%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.
An exceptionally lean, actionable skill body with strong multi-phase workflow sequencing, explicit validation checkpoints, and error-recovery feedback loops. The only slight gap is progressive disclosure, where some troubleshooting or auth detail could be externalized.
Suggestions
Consider moving the detailed troubleshooting/error-code matrix and per-method auth instructions into a reference file (e.g. TROUBLESHOOTING.md) with a one-level-deep pointer, to tighten progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is almost entirely executable commands with no padded concept explanations, no library tutorials, and no over-explanation of things Claude already knows, matching the "lean and efficient; every token earns its place" anchor. | 5 / 5 |
Actionability | Provides fully executable, copy-paste-ready commands throughout (git merge, npm install, npx tsx setup invocations, polling loops, sqlite queries) covering the common cases including env-conditional auth method selection, fitting the top anchor. | 5 / 5 |
Workflow Clarity | Five clearly sequenced phases with explicit validation checkpoints (build clean + tests pass, verify creds.json, poll auth status) and error-recovery feedback loops (qr_timeout/logged_out/515/timeout handling), matching the "explicit validation steps; feedback loops" anchor. | 5 / 5 |
Progressive Disclosure | Single self-contained file with well-organized section headers and no nested references, but for a longer multi-phase skill some reference material (e.g. the troubleshooting/error-code detail or per-method auth steps) could be split into separate files, so it sits at "good structure; minor organization gaps" rather than a clear 5. | 4 / 5 |
Total | 19 / 20 Passed |