Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Structured approach to workplace conflicts, performance discussions, and challenging feedback using preparation-delivery-followup framework. Use when preparing for tough conversations, addressing conflicts, giving critical feedback, or navigating sensitive workplace discussions.
.claude/skills/davila7-difficult-workplace-conversations/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 78% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 73% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 89% | 0% |
| case-10 | ✓→✗ | ▼ Worse | 79% | 0% |
A structured framework for approaching challenging workplace conversations including conflicts, performance issues, sensitive feedback, and emotionally charged discussions.
Difficult conversations succeed or fail based on three phases:
Purpose: Set yourself up for a productive conversation
Purpose: Have the conversation effectively
Purpose: Ensure lasting resolution
What happened: Observable behavior What I felt: Your emotional response What I assume: Their intention (often wrong)
Focus conversation on behavior and impact, not assumed intentions.
Situation: When and where did this happen? Behavior: What specifically did they do/say? Impact: What was the effect on you, the team, or the work?
| If You Feel | Before Acting | | ----------- | ------------- | | Angry | Wait 24 hours, write but don't send | | Hurt | Talk to neutral party first | | Anxious | Practice the conversation | | Defensive | Identify your contribution |
Escalate when:
feedback-mastery skill - SBI feedback model (overlaps but more feedback-focused)professional-effective-communication skill - General communication patternsmarkdown**Issue:** Team member missed 3 deadlines in past month **Impact:** Project delayed, others blocked **Goal:** Understand root cause, agree on prevention plan **Opening:** "I wanted to check in about the recent deliverables. I've noticed the last three have come in past deadline, and I'd like to understand what's happening and how we can address it together."
markdown**Issue:** Colleague publicly criticized your work in meeting **Impact:** Embarrassed, trust damaged **Goal:** Address behavior, rebuild working relationship **Opening:** "I'd like to talk about what happened in yesterday's standup. When you said my code 'missed obvious issues,' I felt called out in front of the team. I'd like to understand your concerns and find a better way to handle code quality feedback."
markdown**Issue:** Feel underpaid relative to market/contribution **Impact:** Demotivation, considering leaving **Goal:** Discuss compensation, get timeline or adjustment **Opening:** "I'd like to discuss my compensation. I've been here two years, taken on the payments project leadership, and want to make sure my salary reflects my contributions and the current market."
A successful difficult conversation:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 11,863 | 9,269 | -22% | 1 | 1 | 0% | 2,070 | 3,173 | +53% | 0 | 0 | — |
case-02 | fail→pass | 10,030 | 8,856 | -12% | 1 | 1 | 0% | 1,665 | 2,963 | +78% | 0 | 0 | — |
case-03 | pass→pass | 8,933 | 6,746 | -24% | 1 | 1 | 0% | 1,550 | 2,686 | +73% | 0 | 0 | — |
case-04 | pass→pass | 11,435 | 9,228 | -19% | 1 | 1 | 0% | 1,899 | 3,014 | +59% | 0 | 0 | — |
case-05 | pass→pass | 7,543 | 7,349 | -3% | 1 | 1 | 0% | 1,410 | 2,788 | +98% | 0 | 0 | — |
case-06 | pass→pass | 8,570 | 6,726 | -22% | 1 | 1 | 0% | 1,336 | 2,644 | +98% | 0 | 0 | — |
case-07 | pass→pass | 12,505 | 9,277 | -26% | 1 | 1 | 0% | 2,008 | 3,197 | +59% | 0 | 0 | — |
case-08 | fail→pass | 11,090 | 8,528 | -23% | 1 | 1 | 0% | 1,743 | 3,021 | +73% | 0 | 0 | — |
case-09 | pass→pass | 12,708 | 8,491 | -33% | 1 | 1 | 0% | 2,129 | 2,966 | +39% | 0 | 0 | — |
case-10 | pass→fail | 10,574 | 8,042 | -24% | 1 | 1 | 0% | 1,597 | 2,860 | +79% | 0 | 0 | — |
case-11 | pass→pass | 11,948 | 10,043 | -16% | 1 | 1 | 0% | 1,773 | 3,228 | +82% | 0 | 0 | — |
case-12 | pass→pass | 11,416 | 6,359 | -44% | 1 | 1 | 0% | 1,806 | 2,491 | +38% | 0 | 0 | — |
case-13 | fail→pass | 12,717 | 11,676 | -8% | 1 | 1 | 0% | 1,975 | 3,289 | +67% | 0 | 0 | — |
case-14 | fail→pass | 10,230 | 8,778 | -14% | 1 | 1 | 0% | 1,550 | 2,937 | +89% | 0 | 0 | — |
case-15 | pass→pass | 15,202 | 11,929 | -22% | 1 | 1 | 0% | 2,192 | 3,243 | +48% | 0 | 0 | — |
case-16 | pass→pass | 8,988 | 7,083 | -21% | 1 | 1 | 0% | 1,395 | 2,687 | +93% | 0 | 0 | — |
case-17 | pass→pass | 10,660 | 9,458 | -11% | 1 | 1 | 0% | 1,569 | 2,872 | +83% | 0 | 0 | — |
case-18 | pass→pass | 8,096 | 7,143 | -12% | 1 | 1 | 0% | 1,321 | 2,693 | +104% | 0 | 0 | — |
case-19 | pass→pass | 12,800 | 17,690 | +38% | 1 | 1 | 0% | 1,984 | 3,403 | +72% | 0 | 0 | — |
case-20 | pass→pass | 6,043 | 3,774 | -38% | 1 | 1 | 0% | 1,194 | 2,166 | +81% | 0 | 0 | — |
case-21 | pass→pass | 4,511 | 2,805 | -38% | 1 | 1 | 0% | 926 | 2,124 | +129% | 0 | 0 | — |
case-22 | pass→pass | 2,783 | 2,430 | -13% | 1 | 1 | 0% | 462 | 2,068 | +348% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +14 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.