Content
71%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.
A well-structured, interactive skill body with a clear sequenced workflow and correct use of a single one-level-deep reference for details. Its main weakness is redundancy — constraint and trigger content is stated twice — plus the absence of an explicit validation step for the generated document.
Suggestions
Consolidate the constraints: keep them in one place (either the '## Constraints' section or Step 1) instead of repeating nearly identical lists twice, and drop the 'When to use this skill' section since the frontmatter description already carries the triggers.
Remove the sentence defining what an epic is ('An epic represents a large body of work that can be broken down into smaller user stories...') — this is knowledge Claude already has and adds no skill-specific value.
Add an explicit validation checkpoint at the end of the workflow (e.g., confirm all date placeholders were replaced and all required sections are present before presenting the epic to the user) to close the feedback loop.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean but repeats itself: the constraint list appears in full under '## Constraints' and again (nearly verbatim) under Step 1's 'Step constraints', the 'When to use this skill' section duplicates the description's trigger list, and the intro defines what an epic is — content Claude already knows. Tightening these would remove noticeable redundancy without losing information. | 3 / 5 |
Actionability | For an instruction-only skill the guidance is mostly executable: a concrete terminal command ('Run `date`'), a strict ordered questioning process with explicit gating ('wait for user responses'), and a concrete output spec ('all required sections (scope, value, features, dependencies, risks, and success criteria)'). Minor gaps remain — e.g., no example of the expected output shape inline. | 4 / 5 |
Workflow Clarity | A clear numbered 0–3 sequence with per-step constraints, and the interactive wait-for-response gating acts as checkpoints between steps. It falls short of 5 because there is no explicit validation or feedback loop on the generated document (e.g., verifying placeholders were replaced or sections complete) before finishing. | 4 / 5 |
Progressive Disclosure | The ~60-line body stays a true overview: detailed questions and constraints are delegated to a single well-signaled, one-level-deep reference ('For detailed guidance, examples, and constraints, see references/012-agile-epic.md'), which exists in the bundle and is the only referenced path. Content is appropriately split and easy to navigate. | 5 / 5 |
Total | 16 / 20 Passed |