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.
An exemplary compact skill body: an explicit five-step interactive workflow with a validation checklist, a fallback protocol for unresolved ambiguity, and crisply specified required sections with concrete examples. The only real gap is actionability detail — placeholder module names in the validation commands and no worked example of a completed task description.
Suggestions
Add one worked example of a fully scoped task (all five sections filled in for a real module) so the agent has a concrete target format to match, closing the actionability gap.
Replace or supplement the ':my-feature-impl' placeholder with a note on how to derive the actual module path (e.g., from the repo's settings.gradle) so the Validation section is fully executable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~55-line body is lean with zero padding: it never explains concepts Claude already knows, and every line adds project-specific rules (section requirements, the [NEEDS INPUT: <what is missing>] convention, the project GID). Concrete anti-examples like 'Vague entries like "clean up the code" are not acceptable' earn their tokens; this matches 'Lean and efficient; assumes Claude's competence; every token earns its place' rather than the anchor 4 case of trimmable over-explanation. | 5 / 5 |
Actionability | The guidance is largely executable: named downstream skill (run-maintenance-task), named creation skill (ddg-asana) with an Asana API fallback, a literal project GID and 'Ready' section, a formatted [NEEDS INPUT] marker, and example validation commands. It falls short of fully copy-paste ready because the gradle commands use placeholder modules (:my-feature-impl) with no instruction on how to resolve them, and there is no worked example of a finished scoped task — matching 'Mostly executable guidance; concrete code or commands with minor gaps' rather than 'specific examples cover the common cases'. | 4 / 5 |
Workflow Clarity | A clear five-step sequence is present with an explicit pre-creation validation checkpoint ('## Checklist before creating the task') and a feedback loop for error recovery (ask clarifying questions, and if anything remains unclear, mark uncertain sections with [NEEDS INPUT]). This matches the top anchor 'Clear sequence with explicit validation steps; feedback loops for error recovery; checklists'; the operation is non-destructive so the validation-cap rule does not bind, and the missing pieces at anchor 4 (checkpoints or feedback loops) are both present. | 5 / 5 |
Progressive Disclosure | This is a simple, self-contained skill: no references/, scripts/, or assets/ directories exist, nothing needs to be split out, and the body is organized into well-signaled sections ('## Required sections', '## Checklist before creating the task') with each required section clearly labeled. Per the rubric's simple-skill guidance, well-organized sections with no need for external references score 5; there is no inlined bulk content that would justify anchor 4 or below. | 5 / 5 |
Total | 19 / 20 Passed |