This skill should be used when user appears confused, frustrated, or shows misalignment between expectations and reality.
SkillScore22Maintained
Automatic
◆Coding pack
Last verified 8/30/2026
What it changes
Passed 2 of 10 test cases with the skill, and 2 of 10 without it.
Without skill17%
With skill22%
Checks it passed that the model alone missed
The response provides a categorized assessment section.
The response provides an assessment section categorizing the finding.
The response asks whether to enter plan mode before supplying code changes.
and 1 more in the full report
2 fixed3 passed either way17 still failing1 broke
Pass-rate lift
+4 pp
Tokens
+81%
Agent turns
0%
Response time
+35%
Model gemini-3.6-flashMeasured 8/30/2026v15 of 23 cases passed with skill · 10 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
I expected raising ValueError inside my Python gRPC service method to return gRPC status code INVALID_ARGUMENT to the gRPC client, but the client receives status code UNKNOWN. Something's off. Rewrite my gRPC interceptor code immediately to fix error mapping.
What was checked, without and with the skill
Checked
Without skill
With skill
The response contrasts expected automatic status mapping with actual gRPC unhandled exception handling.
Passed
Passed
The response provides an assessment section categorizing the finding.
Missed
Passed
The response asks whether to enter plan mode before supplying code changes.
Missed
Passed
case-17 · gemini-3.6-flash · 8/30/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md208 linessingle file
Clarify
Handle user confusion by verifying intent, explaining actual behavior, and determining if there's a real issue.
Primary goal: Clarify and explain, not fix. Most confusion stems from misunderstanding or forgetting, not from bugs.
Activation Triggers
"confused", "I'm confused", "this is confusing"
"I don't understand", "doesn't make sense", "makes no sense"
"wait, shouldn't it...", "but I thought..."
"why is this happening", "why does this..."
"I expected X but got Y"
"this is wrong", "something's off"
frustration signals, contradictory statements
questions that reveal misconceptions about system behavior
Important Context
Users often:
Work on multiple projects in parallel and may confuse behaviors between them
Forget how things were implemented especially after time away
Have outdated mental models based on old versions or different projects
Mix up similar concepts from different codebases or frameworks
But also:
Users are experienced developers - their instincts are often correct
Real bugs exist - about half of confusion cases point to actual issues
User expectations are reasonable - if something feels wrong, investigate thoroughly
Do not assume either way. Investigate before concluding. Both outcomes are equally valid:
User misremembered/mixed things up -> clarify with evidence
System has a genuine issue -> proceed to plan mode for fix
Workflow
Phase 1: Identify the Confusion
Extract the core question - What specifically is the user asking about?
Identify the expectation - What did the user expect to happen?
Update project CLAUDE.md with strategic knowledge discovered during this session — or CLAUDE.local.md when the discovery is per-developer/per-checkout and that file already exists. Defers to any project-defined memory-placement guidance instead of overriding it. Use when user says "learn", "save knowledge", "update claude.md", "capture learnings", or at end of significant work sessions. Also used by commit skill for pre-commit knowledge capture.