ask-questions-if-underspecified
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
62
47%
Does it follow best practices?
Impact
86%
1.56xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-mikeastock/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 extremely vague and lacks specificity about what kind of requirements it clarifies, what domain it operates in, and what concrete actions it performs. While it does include an explicit invocation clause, the overall lack of detail makes it nearly impossible for Claude to distinguish this skill from others or know when it's relevant. The description reads more like a general principle than a skill description.
Suggestions
Add concrete actions describing what 'clarify requirements' entails (e.g., 'Generates clarifying questions, identifies ambiguities in specifications, creates requirement checklists').
Specify the domain or context (e.g., software development, product design, API design) to reduce conflict risk with other skills.
Include natural trigger terms users would say, such as 'gather requirements', 'spec review', 'what questions should I ask', 'requirements analysis', or 'scope definition'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language ('clarify requirements') without listing any concrete actions. It does not specify what kind of requirements, what domain, or what implementation means in this context. | 1 / 3 |
Completeness | It weakly addresses 'what' (clarify requirements before implementing) and has an explicit 'when' clause ('only when invoked explicitly'), but the 'when' guidance is about invocation mode rather than describing the situations or user needs that should trigger this skill. | 2 / 3 |
Trigger Term Quality | The terms 'clarify requirements' and 'implementing' are generic and not natural keywords a user would say. There are no specific trigger terms that would help Claude match this skill to a user request. | 1 / 3 |
Distinctiveness Conflict Risk | 'Clarify requirements before implementing' is extremely generic and could apply to virtually any development or project management skill. It provides no domain-specific niche or distinct triggers. | 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 behavioral skill with clear workflow steps, concrete templates, and explicit guardrails. Its main strengths are the actionable question templates with compact reply formats and the well-defined pause-before-acting checkpoint. Minor weaknesses include some redundancy between the workflow description and the templates section, and the content could be slightly more compact.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining concepts Claude already knows, but some sections could be tightened—e.g., the question templates section is somewhat repetitive with the workflow section, and the enumerated list in step 1 could be more compact. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific question templates with exact formatting, a code block showing the compact reply format, clear anti-patterns, and explicit behavioral rules (pause before acting, state assumptions as numbered list). This is copy-paste ready behavioral instruction. | 3 / 3 |
Workflow Clarity | The four-step workflow is clearly sequenced (decide → ask → pause → confirm), with explicit validation checkpoints (pause before acting, confirm interpretation before proceeding). The feedback loop for when users want to proceed without answers is well-defined with assumption-listing and confirmation steps. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but everything is inline in a single file. The question templates section could potentially be a separate reference file, and the anti-patterns section adds length. For a skill of this size (~80 lines of content), it's acceptable but not optimally organized. | 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
- Dicklesworthstone/pi_agent_rust
- Commit
6e3d68c
- 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.