Content
78%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 exemplary lean, actionable skill body that teaches only the non-obvious judgment (result interpretation, cost etiquette) and provides runnable commands. Its weaknesses are external: the helper script it depends on is missing from the bundle, and there is no error-handling guidance for API failures.
Suggestions
Ship the referenced helper script in the skill bundle (e.g. scripts/dataforseo.py) — the body's entire usage section depends on it, but it is absent from the reviewed files, so the commands cannot run as shipped.
Add brief error-recovery guidance for API failures (e.g. what to do on auth errors, insufficient balance, or per-call errors, and whether/how to retry) to close the workflow feedback-loop gap.
Clarify the helper's actual location: the given path (~/.claude/.bootstrap-dir/skills/dataforseo/dataforseo.py) is environment-specific and unverifiable; a bundle-relative path would make the reference resolvable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient throughout: no re-explanation of concepts Claude already knows, and the "Reading the results" heuristics ("Zero / n/a volume on every candidate is itself the answer", "Wrong-intent volume is a trap") are judgment calls Claude could not derive on its own — every token earns its place. | 5 / 5 |
Actionability | Copy-paste-ready commands with real arguments ("python3 \"$DFS\" volume \"claude code\" \"coding agent\"") plus an auth check, options, and concrete cost figures, but the referenced helper dataforseo.py is not present in the reviewed bundle, so the commands cannot actually run as shipped — a gap beyond fully executable. | 4 / 5 |
Workflow Clarity | The sequence (whoami auth check → query → interpret results) is clear with an explicit validation checkpoint for the batch operation ("Check whoami for balance before large runs"), but there is no error-recovery guidance for failed or errored API calls, keeping it below the feedback-loop anchor. | 4 / 5 |
Progressive Disclosure | Sections are well-organized and the skill is short enough to live in one file, but its single referenced file — "dataforseo.py in this skill folder" — does not exist in the reviewed bundle (no scripts/, references/, or assets/ directories), so the core reference cannot be verified as real. | 3 / 5 |
Total | 16 / 20 Passed |