Content
93%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 skill body: executable commands, a clear failure-remediation workflow, and proper progressive disclosure that pushes class policy and exclusion format into references/policy.md. The only minor gap is that the verify-after-fix re-run step is implicit.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every sentence carries skill-specific policy ("at the root and at any depth, and no other file", "cut restated content first... never delete a rule to fit") with no padding and no explanation of concepts Claude already knows. Lean and efficient; every token earns its place. | 5 / 5 |
Actionability | Two copy-paste-ready commands with both invocation modes, a concrete ordered remediation strategy for over-limit documents, and an explicit pointer for where exclusion rows go. The guidance is fully executable and covers the common cases. | 5 / 5 |
Workflow Clarity | The sequence is clear: run the check (mode selection stated, including the pre-commit staged mode), then a decision path for failures with an ordered fix strategy and an exclusion escape hatch. Not 5 because the re-run-to-verify loop after a fix is implied rather than an explicit step, though the check itself is non-destructive so no validation cap applies. | 4 / 5 |
Progressive Disclosure | A short overview body with a well-signaled, one-level-deep reference ([references/policy.md](references/policy.md), verified to exist) linked twice with a section anchor, while flags and exit codes are delegated to `doc-limits --help`. Content is appropriately split with easy navigation and no nested doc references. | 5 / 5 |
Total | 19 / 20 Passed |