ask-questions-if-underspecified

Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.

1.56x

Quality

—

Does it follow best practices?

Impact

86%

1.56x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, actionable, well-sequenced instruction skill: it gives concrete templates and a copy-paste reply format, gates acting on unknowns with explicit checkpoints, and organizes everything into clear self-contained sections with no need for external references.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence—it lists criteria, guidelines, templates, and anti-patterns without explaining concepts Claude already knows—matching the 'lean and efficient; every token earns its place' anchor; not score 2 because there is no concept padding or significant verbosity.	3 / 3
Actionability	As an instruction-only skill it provides concrete, copy-paste-ready guidance—numbered question templates, a literal reply-format code block ('Reply with: defaults (or 1a 2a)'), and specific do/don't lists—meeting the actionable-equivalent of the 'specific examples; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The four-step workflow (decide underspecified -> ask must-haves -> pause -> confirm then proceed) is clearly sequenced with explicit gating checkpoints ('Until must-have answers arrive: do not run commands...') and a confirmation feedback loop, matching the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	The skill is a self-contained, well-organized single file with clear sections (Goal, Workflow, Question templates, Anti-patterns) and no nested or external references; per the guideline a simple skill needing no external references can score 3 with well-organized sections.	3 / 3
	Total	12 / 12 Passed

Description

40%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description conveys the skill's purpose and gating constraint but is written in imperative rather than third-person voice and lacks an explicit 'Use when...' trigger clause with natural keywords, capping several dimensions at 2 and specificity at 1 after the voice penalty.

Suggestions

Rewrite in third person, e.g. 'Clarifies requirements before implementing.'

Add an explicit trigger clause with natural user phrasing, e.g. 'Use when a request is ambiguous or underspecified, or when the user asks to clarify requirements before implementation.'

Name concrete actions (e.g., ask 1-5 scoped questions, restate assumptions, confirm before proceeding) to raise specificity toward multiple concrete actions.

Dimension	Reasoning	Score
Specificity	Base reads as one named action ('Clarify requirements before implementing') matching the score-2 anchor of naming a domain and an action but not multiple concrete actions; reduced by 1 per the third-person-voice guideline because 'Clarify...' is imperative/second-person rather than third person ('Clarifies requirements').	1 / 3
Completeness	It states what the skill does ('Clarify requirements before implementing') but lacks an explicit 'Use when...' trigger clause; per the guideline a missing explicit trigger clause caps completeness at 2, and not score 1 because a partial when ('only when invoked explicitly') is present.	2 / 3
Trigger Term Quality	It includes a relevant term ('requirements') but offers no natural 'Use when...' phrasing or common variations a user would say, matching the 'some relevant keywords but missing common variations' anchor; not score 1 because 'requirements' is a natural word, not jargon.	2 / 3
Distinctiveness Conflict Risk	The 'only when invoked explicitly' constraint lowers auto-trigger conflict risk, but 'Clarify requirements before implementing' is a somewhat generic niche with no distinct trigger terms, matching the 'somewhat specific but could still overlap' anchor rather than a clear distinct-trigger niche.	2 / 3
	Total	7 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Dicklesworthstone/pi_agent_rust
Commit: abece4a

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.