clarify-question-loop

Use when a meta-agent request is too ambiguous to safely generate, package, publish, or adapt without one to five targeted questions.

Quality

81%

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

77%

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

The content is highly actionable with a clear sequenced workflow and feedback loops, and it mostly respects token budget. Its weak point is progressive disclosure: the body points to two external docs that are not present in the bundle.

Suggestions

Add the referenced files (docs/builder-interview-research-gate.md and docs/clarify-question-loop.md) to the bundle, or remove the references and inline the essential content.

De-duplicate the Korean plain-language question so it appears in only one section (Procedure or Default Questions) to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean procedural guidance that assumes Claude's competence, but the Korean plain-language question is duplicated in both Procedure step 2 and Default Questions, and the inline translation table adds length that could be trimmed — mostly efficient but not fully tight, so not level 3 and clearly above the verbose level 1.	2 / 3
Actionability	Provides concrete executable guidance: a literal first-batch question, specific budgets (3-5 chat, <=8 stormbreaker, 8-12 build), a stop rule (three auto-confirmed answers then escalate), and a translation table — fully actionable, matching the level-3 anchor (instruction-only guidance is acceptable per the rubric).	3 / 3
Workflow Clarity	An 8-step procedure with explicit sequencing, classification-before-asking, a stop rule, and a re-classify-after-answers feedback loop; this is a non-destructive clarification flow so the destructive-operation cap does not apply, placing it at the level-3 clear-sequence-with-feedback anchor.	3 / 3
Progressive Disclosure	References are one level deep and clearly signaled (docs/builder-interview-research-gate.md, docs/clarify-question-loop.md), but neither file exists in the bundle (no docs/ directory and no references/scripts/assets dirs), so the signaled references are dangling; some structure present but not verifiable, so not level 3 and above the monolithic level 1.	2 / 3
	Total	10 / 12 Passed

Description

85%

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 specific, complete, and well-scoped to a distinct niche, with explicit Use-when trigger guidance. Its main weakness is trigger-term quality: the phrasing leans on internal "meta-agent" jargon rather than terms a user would naturally say.

Suggestions

Add natural-language trigger variants users might actually say (e.g., "when a build/packaging request is vague", "when requirements are unclear before generating an agent package") alongside the meta-agent phrasing.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ("generate, package, publish, or adapt") and a specific mechanism ("one to five targeted questions"), matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what (clarify via targeted questions before generate/package/publish/adapt) and when ("Use when a meta-agent request is too ambiguous..."), the level-3 both-answered anchor.	3 / 3
Trigger Term Quality	"meta-agent request is too ambiguous" is specialized internal jargon a user would rarely say; some relevant trigger phrasing exists but common natural variations are missing, so it is not the level-3 broad-coverage anchor and above the no-keyword level 1.	2 / 3
Distinctiveness Conflict Risk	Targets a narrow clarification niche with a distinct trigger unlikely to fire for unrelated skills, matching the clear-niche anchor.	3 / 3
	Total	11 / 12 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: agentlas-ai/Agentlas-OS
Path: .agents/skills/clarify-question-loop/SKILL.md
Commit: 2eb39ad

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.