Content
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable orchestration framework with clear routing and a defined execution sequence, but it lacks the concrete, actionable detail needed to guide Claude through actual workflow execution. The content is moderately well-structured but relies heavily on external files (which aren't provided) for the actual substance, and the inline guidance remains too abstract—describing what to do rather than showing how to do it with specific examples or validation criteria.
Suggestions
Add a concrete worked example showing one workflow (e.g., 'ship-saas-mvp') executed end-to-end with specific step names, artifacts produced, and explicit completion criteria for each step.
Define explicit validation/completion criteria for each workflow step rather than the vague 'verify completion criteria before moving to next step'—e.g., 'Step passes when: deployment URL returns 200, all tests green, etc.'
Add a failure/recovery path: what should Claude do when a step fails or a required skill is unavailable? This is critical for an orchestration skill.
Trim the copy-paste prompts section to 1-2 examples and move the rest to a referenced file, or remove entirely since Claude doesn't need prompt templates to execute the skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary sections like 'When to Use This Skill' with bullet points that largely restate what the skill description already conveys. The copy-paste prompts section is somewhat verbose with five similar examples. The limitations section explains obvious things Claude would know. | 2 / 3 |
Actionability | The workflow steps (identify outcome, propose workflows, execute step-by-step) provide a reasonable framework but remain abstract—there are no concrete examples of what 'invoke recommended skills' or 'verify completion criteria' actually look like in practice. The routing table is helpful but the actual execution guidance is vague. | 2 / 3 |
Workflow Clarity | The 5-step execution process is clearly sequenced and includes a verification checkpoint ('verify completion criteria before moving to next step'), but the validation criteria are implicit rather than explicit. There's no feedback loop for what happens when a step fails or completion criteria aren't met, and the actual step content is deferred entirely to external files. | 2 / 3 |
Progressive Disclosure | The skill references `docs/WORKFLOWS.md` and `data/workflows.json` as external sources, which is good progressive disclosure structure. However, no bundle files are provided, so we cannot verify these references exist. The SKILL.md itself contains content that could be trimmed (copy-paste prompts could be in a separate file) while lacking the substantive overview content that should be inline. | 2 / 3 |
Total | 8 / 12 Passed |