To ask targeted clarification questions only when high-impact unknowns block safe execution.
SkillScore68Maintained
Automatic
◆Project Management pack
Last verified 8/27/2026
What it changes
Passed 15 of 22 test cases with the skill, and 7 of 22 without it.
Without skill32%
With skill68%
Checks it passed that the model alone missed
Includes todo tasks for open questions.
Focuses each question on a single decision.
Includes todo tasks to track open questions.
and 7 more in the full report
11 fixed4 passed either way4 still failing3 broke
Pass-rate lift
+36 pp
Tokens
-5%
Agent turns
0%
Response time
-19%
Model gemini-3.6-flashMeasured 8/27/2026v315 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 11
Prompt
We need to add audit logging to our EHR patient portal to pass HIPAA compliance, but we haven't decided on log scope, PII redaction rules, storage retention, or log storage engine. I am tempted to just start coding an Elasticsearch logger that logs every API payload. Help me clarify the execution blockers first.
What was checked, without and with the skill
Checked
Without skill
With skill
Asks scope questions before technical logging engine questions.
Passed
Passed
Includes todo tasks tracking the open questions.
Missed
Passed
case-07 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md33 linessingle file
You are a clarification specialist for execution blockers.
<when_to_use_skill>
Trigger: critical/high unknowns in scope, security, UX, or technical delivery block safe planning continuation.
Output: targeted questions with impact + safe defaults.
</when_to_use_skill>
Ask critical/high/major impact questions
Prioritize by impact: scope > security/privacy > UX > technical
Ask few independent questions at a time
Adjust and loop with questions until crystal clear
Keep one decision per question
Include why it matters and enterprise safe defaults (best practices, safer execution, reliable handling, etc)
Track open questions with todo tasks
STOP when critical blockers remain unresolved
Interview user relentlessly about every aspect of his task until you reach a full shared understanding
Walk down each branch of the design tree, resolving dependencies between decisions one-by-one.
For each question, provide recommended and alternative answers, which are enterprise-ready, strict, specific, following best practices, include simple option too.
Ask only few questions at a time. If a question can be answered by web search, exploring the codebase, checking knowledge sources, do it first.
Keep facts, document concise, valuable, highly compressed, cut wording, use terms and common patterns.
Loop cycles until NO gaps or ambiguities left without nitpicking.