ask-questions-if-underspecified

Clarify requirements before implementing. Use when serious doubts arise.

Quality

70%

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 ./skills/ask-questions-if-underspecified/SKILL.md

Quality

Content

82%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 content is a well-structured, highly actionable behavioral skill: a clear decision workflow, copy-paste-ready question templates, and explicit pause/confirm checkpoints, with no filler or concept padding. Its only weaknesses are mild redundancy (Limitations and the step-1 checklist restate earlier content) and a missing branch for handling incomplete or conflicting answers.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence with no concept explanations, but has minor trimmable redundancy — the Limitations section restates the core rule ("Stop and ask for clarification if required inputs... are missing") and the step-1 checklist overlaps the When to Use section — matching the 'efficient; minor instances of over-explanation' anchor.	4 / 5
Actionability	Guidance is fully executable for an instruction-only skill: copy-paste-ready question templates ("Which of these should it be? A) ... B) ... C) ..."), a concrete example question block with an explicit reply format ("Reply with: defaults (or 1a 2a)"), and precise rules like the 1-5 question cap and bolded recommended defaults.	5 / 5
Workflow Clarity	The four-step sequence (decide underspecified → ask must-have questions → pause before acting → confirm then proceed) is clearly ordered with confirmation checkpoints and an explicit proceed-with-assumptions feedback branch, matching anchor 4; a 5 would require explicit handling of partial or conflicting answers after the first pass.	4 / 5
Progressive Disclosure	The ~85-line body has well-organized sections (When to Use / When NOT to Use / Goal / Workflow / templates / Anti-patterns) and needs no external files for a single behavioral skill, matching the 'good structure; most content appropriately placed' anchor — slightly too long to qualify for the under-50-line simple-skill exception.	4 / 5
	Total	17 / 20 Passed

Description

58%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 is functional and correctly structured with both a what- and a when-clause, but it is thin: one action verb, generic trigger conditions, and no natural user phrasings like 'unclear', 'ambiguous', or 'underspecified'. It would benefit from enumerating the concrete behaviors (identify missing objective/scope/constraints, ask batched multiple-choice questions, pause before implementing) and richer trigger terms.

Suggestions

List the concrete actions the skill performs, e.g. "Identify missing objective, scope, constraints, or acceptance criteria, ask a small batch of multiple-choice clarifying questions with suggested defaults, and pause implementation until answers arrive."

Replace the generic "Use when serious doubts arise" with natural trigger phrases users would actually say, such as "Use when the request is ambiguous, unclear, underspecified, or open to multiple interpretations."

Sharpen distinctiveness by stating what distinguishes this from just asking questions ad hoc, e.g. mentioning the batched, low-friction question format with defaults.

Dimension	Reasoning	Score
Specificity	"Clarify requirements before implementing" names one concrete action with timing context, but offers no further actions or elaboration, matching the '1-2 concrete actions, not comprehensive' anchor rather than the several-action anchors above.	3 / 5
Completeness	It answers both what ("Clarify requirements before implementing") and when ("Use when serious doubts arise"), but the when-clause is generic rather than listing concrete trigger phrases, matching anchor 4 rather than the fully explicit anchor 5.	4 / 5
Trigger Term Quality	"Use when serious doubts arise" supplies some relevant keywords (clarify, requirements) but omits the natural phrases users would say such as "unclear", "ambiguous", or "underspecified", fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	"Clarify requirements" is a broad behavioral intent that could overlap with other planning or clarification skills, though the doubts-based trigger gives it some distinctness — fitting 'somewhat specific but could still overlap'.	3 / 5
	Total	13 / 20 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: sickn33/agentic-awesome-skills
Path: skills/ask-questions-if-underspecified/SKILL.md
Commit: 7b534bc

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.