Content
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is concise, actionable, and well-organized for a simple single-purpose tool-dispatch skill. The main gap is an explicit validation/feedback loop for the riskier rename and post-edit diagnostics workflows.
Suggestions
Add an explicit edit->re-run diagnostics (severity: 'error')->fix->retry loop so post-edit verification is unambiguous.
For lsp.rename, add a checkpoint: run lsp.prepare_rename first, confirm the workspace edit is safe, apply lsp.rename, then re-run lsp.diagnostics to verify no breakage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean — a one-line intro, a terse tool list, an executable config block, and one triage tip — with no explaining of concepts Claude already knows, matching the score-3 lean-and-efficient anchor. | 3 / 3 |
Actionability | Provides concrete tool names with parameter hints ('severity: "error"', file/line/char for goto_definition), a copy-paste-ready JSON config, and a concrete triage step, matching the score-3 fully-executable anchor. | 3 / 3 |
Workflow Clarity | A sequencing hint exists ('Use lsp.status first when diagnostics report a missing language server') but the risky rename operation (prepare_rename -> rename) and the edit-then-recheck flow lack an explicit validate->fix->retry checkpoint, which per the rubric caps workflow_clarity at 2. | 2 / 3 |
Progressive Disclosure | Under 50 lines, single-purpose, and organized into clear ## Tools and ## Config sections with no external references needed, matching the rubric's guidance that such simple skills can score 3 on well-organized sections alone. | 3 / 3 |
Total | 11 / 12 Passed |