clarify-ambiguous-requests

Use this skill when the user's request is ambiguous, under-specified, or could be interpreted in multiple ways. If proceeding with a wrong assumption would waste significant work, always ask exactly one focused clarifying question before doing anything.

Quality

83%

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

Quality

Content

100%Weight 40%Scale 1-3

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, well-structured instruction skill: concise, actionable, with a clear sequenced process and an explicit wait-for-answer checkpoint. It earns full marks across all content dimensions.

Dimension	Reasoning	Score
Conciseness	Lean and efficient ('When the task or constraint is unclear, do not guess — ask.') with no padding or explanation of concepts Claude already knows; every line earns its place. Not a 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	Concrete numbered process ('Identify the single most important ambiguity', 'Ask exactly one targeted question. Do not ask several at once', 'Wait for the user's answer') plus example triggers; guidance is specific and executable for an instruction-only skill. Not vague or abstract, so not a 1 or 2.	3 / 3
Workflow Clarity	Clear 3-step sequence with an explicit checkpoint ('Wait for the user's answer before proceeding'). This is a simple, non-destructive skill so the destructive-operations cap does not apply, and the wait step serves as the validation gate.	3 / 3
Progressive Disclosure	Short, well-organized into labeled sections (Process, Example triggers, Anti-pattern) with no monolithic wall of text; no external references are needed or referenced, which is appropriate for a sub-50-line simple skill.	3 / 3
	Total	12 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 well-formed with an explicit 'Use when...' trigger and a concrete core action, but it is a single narrow behavior framed in somewhat abstract request-meta language, which limits specificity, trigger-term naturalness, and distinctiveness.

Suggestions

Add the concrete user phrasings that should trigger this skill (e.g. 'make it better', 'fix it', vague one-liners) so the trigger terms match what users actually say.

Broaden the stated capability slightly or sharpen the niche (e.g. 'before starting non-trivial work') to reduce overlap with general clarifying-question behavior and lift distinctiveness.

Consider naming a second concrete action (e.g. restate the assumed interpretation before asking) to move specificity toward multiple concrete actions.

Dimension	Reasoning	Score
Specificity	Names a concrete action ('ask exactly one focused clarifying question') but the capability set is narrow rather than 'multiple specific concrete actions'. Not vague (rules out 1), but lacks the breadth of a 3.	2 / 3
Completeness	Explicit 'Use this skill when...' clause supplies the when, and the what ('ask exactly one focused clarifying question') is clearly stated, answering both halves. A 2 would require the when to be missing or only implied, which it is not.	3 / 3
Trigger Term Quality	Includes relevant terms ('ambiguous', 'under-specified', 'could be interpreted in multiple ways') but these are meta-descriptions of requests rather than vocabulary users naturally say when needing the skill, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	Has a distinct niche and triggers, but 'ask a clarifying question' is general-purpose behavior that overlaps with many skills, so it could still trigger for the wrong skill rather than having a clearly non-conflicting niche.	2 / 3
	Total	9 / 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: aiming-lab/MetaClaw
Path: memory_data/skills/clarify-ambiguous-requests/SKILL.md
Commit: 922caf3

Reviewed: 9 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.