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.
The body is an exemplar of a lean, single-purpose skill: it states the decision rule, an explicit interaction checkpoint, five concrete editor commands, and a failure fallback with zero padding. The only notable flaw is inconsistent placeholder style across the command examples.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~45-line body is lean and assumes Claude's competence: no explanations of what editors or CLIs are, just the decision rule ("Depending on which EDITOR the user says they are using... If no editor specified, you must ask"), the critical interaction constraint ("you MUST wait for the user to say something before moving on"), five terse command blocks, and a one-line failure fallback ("If any of these fail tell the user to install the corresponding CLI tool"). Every token earns its place. | 5 / 5 |
Actionability | Concrete, executable commands are given for five editors ("code --goto <file_path>:<line_number>", "pycharm --line <line_number> <file_path>", etc.), covering the common cases. It sits below a 5 because the placeholder formats are inconsistent across examples (<file_path>:<line_number> vs. "path/to/file.md:43" vs. "+42 blah.py") and the IntelliJ command name is stated without the general parameter convention used for the others. | 4 / 5 |
Workflow Clarity | For this simple, single-purpose skill the sequence is unambiguous: determine the user's editor (asking if unspecified), show a file at an optional line, and the explicit checkpoint "you MUST wait for the user to say something before moving on to the next file", plus an error-recovery instruction if a CLI command fails. No destructive or batch operations are involved, so no validation cap applies. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines with no bundle files (references/, scripts/, assets/ are absent) and no need for external references. Per the simple-skill guideline, well-organized sections alone warrant a 5: the single "## Instructions" section cleanly separates the decision rule, the one-by-one/wait constraint, per-editor commands, and the failure fallback. | 5 / 5 |
Total | 19 / 20 Passed |