ask-questions-if-underspecified

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

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/00-utilities/ask-questions-if-underspecified/SKILL.md

Quality

Content

88%Weight 40%Scale 1-5

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 well-structured, actionable instruction skill with a clear sequenced workflow, concrete templates, and explicit checkpoints. Minor conciseness and length-driven progressive-disclosure refinements would bring it to full marks.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence, with no padding explaining concepts Claude already knows; minor tightening is possible in the question-templates section. Efficient but not perfectly lean, so 4 rather than 5.	4 / 5
Actionability	Concrete numbered steps, specific question templates, a copy-paste-ready reply-format code block, multiple-choice option formats, and a fast-path "defaults" response give fully executable, instruction-ready guidance.	5 / 5
Workflow Clarity	A clear 4-step sequence with an explicit pause-checkpoint before acting and a feedback loop (state assumptions, confirm before proceeding) for the proceed-without-answers case; not a destructive/batch skill, so no validation cap applies.	5 / 5
Progressive Disclosure	A single well-organized file with clear sections (Goal, Workflow, Question templates, Anti-patterns) and no nested references; slightly above the 50-line simple-skill threshold keeps it at 4 rather than 5.	4 / 5
	Total	18 / 20 Passed

Description

38%Weight 40%Scale 1-5

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 a clear purpose but lacks concrete trigger phrases and a "Use when..." clause, capping completeness and trigger-term quality. Its meta-skill nature creates broad overlap risk with other implementation skills.

Suggestions

Add an explicit "Use when..." clause with natural trigger phrases users would say, e.g., "Use when a request is ambiguous about scope, acceptance criteria, or constraints before implementation."

List 2-3 concrete actions (e.g., "Ask 1-5 numbered clarifying questions, surface assumptions, confirm interpretation") to raise specificity and distinctiveness.

Narrow the trigger to specific underspecification signals (missing scope, "done" criteria, or constraints) to reduce conflict with general implementation skills.

Dimension	Reasoning	Score
Specificity	"Clarify requirements before implementing" names a domain (requirements clarification) and one concrete action, but coverage is not comprehensive. Not vague enough for 2, not comprehensive enough for 4.	3 / 5
Completeness	The "what" is clear, but "when" is only a restriction ("Do not use automatically, only when invoked explicitly") rather than an explicit "Use when..." clause with concrete triggers; per guidelines this caps completeness at 3.	3 / 5
Trigger Term Quality	Only generic terms ("requirements", "implementing") appear; the natural phrases a user would actually say to invoke this skill are absent. Notably below the midpoint toward missing natural terms.	2 / 5
Distinctiveness Conflict Risk	"Clarify requirements before implementing" is a meta-skill with high overlap risk against virtually any implementation skill, since requirements-gathering precedes most work.	2 / 5
	Total	10 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: marchatton/agent-skills
Path: .agents/skills/00-utilities/ask-questions-if-underspecified/SKILL.md
Commit: a0eadb2

Reviewed: 5 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.