Content
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body has sound progressive disclosure and a workable workflow, but it is weighed down by templated redundancy and lacks a complete executable command plus a validation step. Tightening the boilerplate and fixing the broken step-3 bullet would raise the lower dimensions.
Suggestions
Remove the duplicated description text in "When to Use" and "Key Features" and the generic template bullets; keep only trigger guidance specific to this skill.
Add a complete copy-paste run command showing all required args (e.g. `python scripts/main.py --desc ... --egger ... --begg ... --trim ... --lang English`) instead of only `--help`.
Fix the broken step-3 bullet and the duplicated "(Figure 3)" label, and insert an explicit validation checkpoint (confirm LLM tables are valid Markdown before assembly).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The core Usage/Workflow/Quality Rules sections are lean, but the body restates the description three times and includes generic template bullets ("Use this skill when a academic writing task needs a packaged method", "See ## Usage above") that are padded filler, so it is mostly efficient with unnecessary content that could be tightened rather than fully lean. | 2 / 3 |
Actionability | It points to a real executable `scripts/main.py` and a `references/prompts.md` with concrete prompts, but the example only shows `python scripts/main.py --help` and never gives a complete invocation with the required --desc/--egger/--begg/--trim/--lang args, leaving key details missing per the score-2 anchor. | 2 / 3 |
Workflow Clarity | The three-step Workflow is sequenced, but step 3 has a broken bullet ("* Insert figure reference \"(Figure 3)\" or \"(Figure 3)\"") with a duplicated identical label and no validation checkpoint before assembly, fitting the score-2 anchor of steps present but with gaps. | 2 / 3 |
Progressive Disclosure | The body is an overview that cleanly signals one-level-deep references to a real `references/prompts.md` and `scripts/main.py`, both confirmed to exist in the bundle, with content appropriately split — matching the score-3 anchor. | 3 / 3 |
Total | 9 / 12 Passed |