ask-questions-if-underspecified
Clarify requirements before implementing. Use when serious doubts arise.
56
47%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/ask-questions-if-underspecified/SKILL.mdQuality
Discovery
17%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is too vague and generic to be useful for skill selection. It lacks concrete actions, specific domain context, and natural trigger terms. The 'when' clause ('serious doubts arise') is subjective and provides no clear signal for when Claude should select this skill over others.
Suggestions
Specify the domain and concrete actions, e.g., 'Asks clarifying questions about ambiguous software requirements, user stories, or feature requests before writing code' instead of the generic 'clarify requirements before implementing'.
Replace the vague trigger 'when serious doubts arise' with explicit, observable conditions, e.g., 'Use when the user provides an underspecified task, conflicting instructions, or when key details like input format, expected output, or edge cases are missing'.
Add natural trigger terms users might use, such as 'unclear spec', 'ambiguous request', 'what do you mean', 'need more details', or 'before starting'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'clarify requirements' and 'implementing' without specifying what kind of requirements, what domain, or what concrete actions are taken. No specific capabilities are listed. | 1 / 3 |
Completeness | It has a weak 'what' (clarify requirements before implementing) and a weak 'when' ('when serious doubts arise'), but the 'when' clause is too vague and subjective to serve as an effective trigger. The 'Use when' clause exists but provides minimal actionable guidance. | 2 / 3 |
Trigger Term Quality | The terms 'requirements', 'implementing', and 'serious doubts' are overly generic and not natural keywords a user would say. Users wouldn't typically phrase requests using these terms to trigger this skill. | 1 / 3 |
Distinctiveness Conflict Risk | This description is extremely generic and could apply to virtually any skill involving planning, coding, design, or project work. 'Clarify requirements' and 'implementing' overlap with countless potential skills. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted instructional skill with clear workflow steps, concrete question templates, and good anti-patterns. Its main strengths are actionability and workflow clarity—Claude knows exactly when to ask, how to format questions, and when to proceed. Minor weaknesses include some redundancy in the Limitations section and slightly verbose formatting instructions that could be tightened.
Suggestions
Remove or significantly trim the 'Limitations' section, as its points are already covered by the workflow steps and 'When NOT to Use' section.
Tighten the bullet about formatting defaults—the parenthetical about bold/recommended is overly prescriptive and could be condensed to a single sentence.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but has some redundancy. The 'Limitations' section repeats guidance already covered in the workflow (e.g., 'stop and ask for clarification' is the entire point of the skill). The question templates section, while useful, is somewhat verbose with the detailed formatting instructions for defaults/bold. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific question templates with copy-paste-ready code blocks, exact reply formats (e.g., '1a 2a' or 'defaults'), numbered workflow steps, and clear anti-patterns. The guidance is specific enough that Claude knows exactly what to do at each step. | 3 / 3 |
Workflow Clarity | The four-step workflow is clearly sequenced with explicit checkpoints: decide if underspecified → ask questions → pause before acting → confirm interpretation. The 'pause before acting' step serves as a validation gate, and there's a clear feedback loop for when users want to proceed without answers (state assumptions → get confirmation). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's all inline in a single file. The question templates section could potentially be separated into a reference file. However, for a skill of this size (~80 lines of meaningful content), the inline approach is reasonable, though the organization could be slightly tighter. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
b938655
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.