ask-questions-if-underspecified
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
59
42%
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
0%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 provides almost no useful information for skill selection. It lacks concrete actions, natural trigger terms, and meaningful guidance on when to use it. The instruction to only use when explicitly invoked further undermines its utility as a skill description since Claude cannot determine what explicit invocation looks like.
Suggestions
Specify what kind of requirements are being clarified (e.g., 'Asks clarifying questions about software feature requirements, user stories, or acceptance criteria before writing code').
Add explicit trigger terms users would say, such as 'Use when the user explicitly invokes this skill by name or asks to gather requirements, define specs, or scope a feature before coding'.
List concrete actions the skill performs, such as 'Generates structured requirement documents, identifies ambiguities, proposes acceptance criteria, and creates implementation checklists'.
| 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 | The 'what' is extremely vague ('clarify requirements before implementing'), and the 'when' clause explicitly says not to use it automatically and only when invoked explicitly, which provides no guidance on what triggers should cause selection. This fails to answer both questions meaningfully. | 1 / 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 so generic it could apply to virtually any development or project task. It has no distinct niche or specific triggers to differentiate it from other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
85%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 appropriate guardrails. Its main strength is actionability—the question templates and reply format examples give Claude exact patterns to follow. Minor verbosity in overlapping guidance between the workflow steps and templates section prevents a perfect conciseness score, but overall this is a strong skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy—the question templates section partially repeats guidance already given in step 2 (e.g., multiple-choice, defaults, compact reply format). The anti-patterns section is useful but brief enough to fold into the workflow. Overall mostly lean but could be tightened. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific question formats, exact reply patterns (e.g., '1a 2a' or 'defaults'), a ready-to-use code block template, clear anti-patterns, and explicit behavioral rules (pause before acting, restate assumptions). This is copy-paste ready behavioral instruction. | 3 / 3 |
Workflow Clarity | The four-step workflow is clearly sequenced with explicit checkpoints: decide if underspecified → ask questions → pause (with explicit rules about what is/isn't allowed) → confirm interpretation then proceed. The pause-before-acting step with its conditional branch (user says proceed → state assumptions → get confirmation) serves as a validation/feedback loop for this type of non-destructive conversational skill. | 3 / 3 |
Progressive Disclosure | For a standalone skill with no bundle files, the content is well-organized into clear sections (Goal, Workflow with numbered sub-steps, Question Templates, Anti-patterns). The length is appropriate (~80 lines) and doesn't need external references. Sections are logically ordered and easy to navigate. | 3 / 3 |
Total | 11 / 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
895269a
- 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.