{"id":"b7270db1-5581-4f4e-81d0-a3d17b525205","shortId":"f7ZzsK","kind":"skill","title":"difficult-workplace-conversations","tagline":"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.","description":"# Difficult Conversations Skill\n\nA structured framework for approaching challenging workplace conversations including conflicts, performance issues, sensitive feedback, and emotionally charged discussions.\n\n## When to Use This Skill\n\n- Preparing for a challenging conversation with a colleague\n- Addressing performance issues with a team member\n- Delivering difficult feedback to a peer or manager\n- Navigating conflict between team members\n- Discussing sensitive topics (salary, promotion, termination)\n- Handling emotional or defensive reactions\n- Following up after difficult discussions\n\n## Core Framework: Preparation-Delivery-Followup\n\nDifficult conversations succeed or fail based on three phases:\n\n### Phase 1: Preparation (Before)\n\n**Purpose:** Set yourself up for a productive conversation\n\n1. **Clarify the Issue**\n   - What specifically happened? (Observable facts only)\n   - What is the impact? (On you, team, work)\n   - What do you need to change?\n\n2. **Check Your Emotions**\n   - What am I feeling? Why?\n   - Am I calm enough to have this conversation?\n   - What might trigger me during this conversation?\n\n3. **Consider Their Perspective**\n   - How might they see this situation?\n   - What constraints or pressures might they have?\n   - What do they care about that I can acknowledge?\n\n4. **Define Your Goal**\n   - What outcome do I want?\n   - What is the minimum acceptable result?\n   - What am I willing to compromise on?\n\n### Phase 2: Delivery (During)\n\n**Purpose:** Have the conversation effectively\n\n1. **Open Neutrally**\n   - Start with facts, not judgments\n   - Express intent to understand, not accuse\n   - Create psychological safety\n\n2. **Share Your Perspective**\n   - Describe behavior, not character\n   - Focus on impact, not intention\n   - Use \"I\" statements, not \"you always\"\n\n3. **Listen Actively**\n   - Ask clarifying questions\n   - Acknowledge their viewpoint\n   - Look for shared interests\n\n4. **Seek Resolution**\n   - Propose specific actions\n   - Agree on next steps\n   - Set check-in timeline\n\n### Phase 3: Followup (After)\n\n**Purpose:** Ensure lasting resolution\n\n1. **Document Agreements**\n   - What was agreed?\n   - Who does what by when?\n   - How will you measure success?\n\n2. **Check Progress**\n   - Follow up as promised\n   - Acknowledge improvements\n   - Address continued issues promptly\n\n3. **Maintain Relationship**\n   - Separate issue from person\n   - Rebuild trust over time\n   - Watch for regression\n\n## Key Principles\n\n### Separate Impact from Intent\n\n**What happened:** Observable behavior\n**What I felt:** Your emotional response\n**What I assume:** Their intention (often wrong)\n\nFocus conversation on behavior and impact, not assumed intentions.\n\n### The SBI Model\n\n**Situation:** When and where did this happen?\n**Behavior:** What specifically did they do/say?\n**Impact:** What was the effect on you, the team, or the work?\n\n### Managing Emotions\n\n| If You Feel | Before Acting |\n| ----------- | ------------- |\n| Angry | Wait 24 hours, write but don't send |\n| Hurt | Talk to neutral party first |\n| Anxious | Practice the conversation |\n| Defensive | Identify your contribution |\n\n### When to Escalate\n\nEscalate when:\n\n- Safety is at risk\n- Legal issues involved\n- Repeated conversations haven't worked\n- Power dynamics prevent resolution\n- You need documentation\n\n## Conversation Types\n\n### Performance Feedback\n\n- Lead with specific examples\n- Connect to expectations/standards\n- Focus on future improvement\n- Offer support and resources\n\n### Conflict Resolution\n\n- Hear both sides separately first\n- Identify underlying interests\n- Look for win-win solutions\n- Document agreements\n\n### Sensitive Topics\n\n- Choose private, neutral setting\n- Allow time for processing\n- Be direct but compassionate\n- Respect confidentiality\n\n### Receiving Feedback\n\n- Thank them for feedback\n- Ask clarifying questions\n- Don't defend immediately\n- Reflect before responding\n\n## References (Load When Needed)\n\n### Detailed Frameworks\n\n- **[Conversation Framework](references/conversation-framework.md)**: Complete three-phase framework with scripts and examples\n- **[Preparation Template](references/preparation-template.md)**: Worksheet for preparing before difficult conversations\n- **[Delivery Scripts](references/delivery-scripts.md)**: Opening lines, response handling, reframing techniques\n- **[Emotional Regulation](references/emotional-regulation.md)**: Managing your own emotions before and during\n\n## See Also\n\n- `feedback-mastery` skill - SBI feedback model (overlaps but more feedback-focused)\n- `professional-effective-communication` skill - General communication patterns\n\n## Example Scenarios\n\n### Scenario 1: Addressing Missed Deadlines\n\n```markdown\n**Issue:** Team member missed 3 deadlines in past month\n**Impact:** Project delayed, others blocked\n**Goal:** Understand root cause, agree on prevention plan\n\n**Opening:** \"I wanted to check in about the recent deliverables. I've noticed\nthe last three have come in past deadline, and I'd like to understand what's\nhappening and how we can address it together.\"\n```\n\n### Scenario 2: Peer Conflict\n\n```markdown\n**Issue:** Colleague publicly criticized your work in meeting\n**Impact:** Embarrassed, trust damaged\n**Goal:** Address behavior, rebuild working relationship\n\n**Opening:** \"I'd like to talk about what happened in yesterday's standup.\nWhen you said my code 'missed obvious issues,' I felt called out in front\nof the team. I'd like to understand your concerns and find a better way\nto handle code quality feedback.\"\n```\n\n### Scenario 3: Asking Manager for Raise\n\n```markdown\n**Issue:** Feel underpaid relative to market/contribution\n**Impact:** Demotivation, considering leaving\n**Goal:** Discuss compensation, get timeline or adjustment\n\n**Opening:** \"I'd like to discuss my compensation. I've been here two years,\ntaken on the payments project leadership, and want to make sure my salary\nreflects my contributions and the current market.\"\n```\n\n## Anti-Patterns to Avoid\n\n### In Preparation\n\n- **Scripting every word** - You'll sound robotic; prepare themes, not scripts\n- **Building a case** - This isn't a trial; seek understanding, not winning\n- **Waiting too long** - Issues compound; address promptly\n\n### In Delivery\n\n- **Starting with \"You always...\"** - Triggers defensiveness immediately\n- **Burying the lead** - Get to the point; don't soften excessively\n- **Asking leading questions** - \"Don't you think...\" isn't asking\n\n### In Followup\n\n- **Forgetting to check in** - Without follow-up, nothing changes\n- **Holding grudges** - Issue resolved means relationship continues\n- **Over-documenting** - Not everything needs written record\n\n## Success Metrics\n\nA successful difficult conversation:\n\n- Both parties feel heard\n- Specific actions are agreed\n- Relationship is preserved or improved\n- The issue doesn't recur (or has clear escalation)\n- Neither party is blindsided later","tags":["difficult","workplace","conversations","agent","toolkit","softaworks","agent-skills","automation","claude","claude-code","coding-agent","development"],"capabilities":["skill","source-softaworks","skill-difficult-workplace-conversations","topic-agent-skills","topic-automation","topic-claude","topic-claude-code","topic-coding-agent","topic-development"],"categories":["agent-toolkit"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/softaworks/agent-toolkit/difficult-workplace-conversations","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add softaworks/agent-toolkit","source_repo":"https://github.com/softaworks/agent-toolkit","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 1847 github stars · SKILL.md body (6,902 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T18:52:57.029Z","embedding":null,"createdAt":"2026-04-18T20:27:54.255Z","updatedAt":"2026-05-18T18:52:57.029Z","lastSeenAt":"2026-05-18T18:52:57.029Z","tsv":"'1':123,134,239,311,609 '2':158,231,256,327,674 '24':423 '3':182,275,304,340,618,744 '4':208,288 'accept':221 'accus':252 'acknowledg':207,281,334 'act':420 'action':293,906 'activ':277 'address':27,71,336,610,670,691,836 'adjust':766 'agre':294,316,632,908 'agreement':313,504 'allow':511 'also':584 'alway':274,843 'angri':421 'anti':802 'anti-pattern':801 'anxious':436 'approach':6,44 'ask':278,527,745,858,867 'assum':372,384 'avoid':805 'base':118 'behavior':261,363,380,396,692 'better':736 'blindsid':926 'block':627 'build':819 'buri':847 'call':719 'calm':169 'care':202 'case':821 'caus':631 'challeng':13,45,66 'chang':157,879 'charact':263 'charg':56 'check':159,300,328,640,872 'check-in':299 'choos':507 'clarifi':135,279,528 'clear':921 'code':713,740 'colleagu':70,679 'come':653 'communic':601,604 'compassion':518 'compens':762,774 'complet':546 'compound':835 'compromis':228 'concern':732 'confidenti':520 'conflict':9,28,49,87,487,676 'connect':476 'consid':183,758 'constraint':193 'continu':337,886 'contribut':443,796 'convers':4,26,38,47,67,114,133,174,181,237,378,439,457,468,543,563,900 'core':107 'creat':253 'critic':30,681 'current':799 'd':659,698,727,769 'damag':689 'deadlin':612,619,656 'defend':532 'defens':100,440,845 'defin':209 'delay':625 'deliv':78 'deliver':645 'deliveri':18,111,232,564,839 'demotiv':757 'describ':260 'detail':541 'difficult':2,37,79,105,113,562,899 'difficult-workplace-convers':1 'direct':516 'discuss':11,36,57,91,106,761,772 'do/say':401 'document':312,467,503,889 'doesn':916 'dynam':462 'effect':238,406,600 'embarrass':687 'emot':55,98,161,368,415,573,579 'enough':170 'ensur':308 'escal':446,447,922 'everi':809 'everyth':891 'exampl':475,554,606 'excess':857 'expectations/standards':478 'express':247 'fact':142,244 'fail':117 'feedback':14,31,53,80,471,522,526,586,590,596,742 'feedback-focus':595 'feedback-masteri':585 'feel':165,418,751,903 'felt':366,718 'find':734 'first':435,493 'focus':264,377,479,597 'follow':102,330,876 'follow-up':875 'followup':19,112,305,869 'forget':870 'framework':20,42,108,542,544,550 'front':722 'futur':481 'general':603 'get':763,850 'give':29 'goal':211,628,690,760 'grudg':881 'handl':97,570,739 'happen':140,361,395,665,704 'haven':458 'hear':489 'heard':904 'hold':880 'hour':424 'hurt':430 'identifi':441,494 'immedi':533,846 'impact':147,266,357,382,402,623,686,756 'improv':335,482,913 'includ':48 'intent':248,268,359,374,385 'interest':287,496 'involv':455 'isn':823,865 'issu':51,73,137,338,344,454,614,678,716,750,834,882,915 'judgment':246 'key':354 'last':309,650 'later':927 'lead':472,849,859 'leadership':786 'leav':759 'legal':453 'like':660,699,728,770 'line':568 'listen':276 'll':812 'load':538 'long':833 'look':284,497 'maintain':341 'make':790 'manag':85,414,576,746 'markdown':613,677,749 'market':800 'market/contribution':755 'masteri':587 'mean':884 'measur':325 'meet':685 'member':77,90,616 'metric':896 'might':176,187,196 'minimum':220 'miss':611,617,714 'model':388,591 'month':622 'navig':33,86 'need':155,466,540,892 'neither':923 'neutral':241,433,509 'next':296 'noth':878 'notic':648 'observ':141,362 'obvious':715 'offer':483 'often':375 'open':240,567,636,696,767 'other':626 'outcom':213 'over-docu':887 'overlap':592 'parti':434,902,924 'past':621,655 'pattern':605,803 'payment':784 'peer':83,675 'perform':10,50,72,470 'person':346 'perspect':185,259 'phase':121,122,230,303,549 'plan':635 'point':853 'power':461 'practic':437 'prepar':17,23,63,110,124,555,560,807,815 'preparation-delivery-followup':16,109 'preserv':911 'pressur':195 'prevent':463,634 'principl':355 'privat':508 'process':514 'product':132 'profession':599 'professional-effective-commun':598 'progress':329 'project':624,785 'promis':333 'promot':95 'prompt':339,837 'propos':291 'psycholog':254 'public':680 'purpos':126,234,307 'qualiti':741 'question':280,529,860 'rais':748 'reaction':101 'rebuild':347,693 'receiv':521 'recent':644 'record':894 'recur':918 'refer':537 'references/conversation-framework.md':545 'references/delivery-scripts.md':566 'references/emotional-regulation.md':575 'references/preparation-template.md':557 'reflect':534,794 'refram':571 'regress':353 'regul':574 'relat':753 'relationship':342,695,885,909 'repeat':456 'resolut':290,310,464,488 'resolv':883 'resourc':486 'respect':519 'respond':536 'respons':369,569 'result':222 'risk':452 'robot':814 'root':630 'safeti':255,449 'said':711 'salari':94,793 'sbi':387,589 'scenario':607,608,673,743 'script':552,565,808,818 'see':189,583 'seek':289,827 'send':429 'sensit':34,52,92,505 'separ':343,356,492 'set':127,298,510 'share':257,286 'side':491 'situat':191,389 'skill':39,62,588,602 'skill-difficult-workplace-conversations' 'soften':856 'solut':502 'sound':813 'source-softaworks' 'specif':139,292,398,474,905 'standup':708 'start':242,840 'statement':271 'step':297 'structur':5,41 'succeed':115 'success':326,895,898 'support':484 'sure':791 'taken':781 'talk':431,701 'team':76,89,150,410,615,725 'techniqu':572 'templat':556 'termin':96 'thank':523 'theme':816 'think':864 'three':120,548,651 'three-phas':547 'time':350,512 'timelin':302,764 'togeth':672 'topic':93,506 'topic-agent-skills' 'topic-automation' 'topic-claude' 'topic-claude-code' 'topic-coding-agent' 'topic-development' 'tough':25 'trial':826 'trigger':177,844 'trust':348,688 'two':779 'type':469 'under':495 'underpaid':752 'understand':250,629,662,730,828 'use':15,21,60,269 've':647,776 'viewpoint':283 'wait':422,831 'want':216,638,788 'watch':351 'way':737 'will':226 'win':500,501,830 'win-win':499 'without':874 'word':810 'work':151,413,460,683,694 'workplac':3,8,35,46 'worksheet':558 'write':425 'written':893 'wrong':376 'year':780 'yesterday':706","prices":[{"id":"14761d30-4c29-43b7-b890-75be502e9628","listingId":"b7270db1-5581-4f4e-81d0-a3d17b525205","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"softaworks","category":"agent-toolkit","install_from":"skills.sh"},"createdAt":"2026-04-18T20:27:54.255Z"}],"sources":[{"listingId":"b7270db1-5581-4f4e-81d0-a3d17b525205","source":"github","sourceId":"softaworks/agent-toolkit/difficult-workplace-conversations","sourceUrl":"https://github.com/softaworks/agent-toolkit/tree/main/skills/difficult-workplace-conversations","isPrimary":false,"firstSeenAt":"2026-04-18T21:54:28.448Z","lastSeenAt":"2026-05-18T18:52:57.029Z"},{"listingId":"b7270db1-5581-4f4e-81d0-a3d17b525205","source":"skills_sh","sourceId":"softaworks/agent-toolkit/difficult-workplace-conversations","sourceUrl":"https://skills.sh/softaworks/agent-toolkit/difficult-workplace-conversations","isPrimary":true,"firstSeenAt":"2026-04-18T20:27:54.255Z","lastSeenAt":"2026-05-07T22:40:51.046Z"}],"details":{"listingId":"b7270db1-5581-4f4e-81d0-a3d17b525205","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"softaworks","slug":"difficult-workplace-conversations","github":{"repo":"softaworks/agent-toolkit","stars":1847,"topics":["agent-skills","ai","automation","claude","claude-code","coding-agent","development"],"license":"mit","html_url":"https://github.com/softaworks/agent-toolkit","pushed_at":"2026-03-05T16:46:24Z","description":"A curated collection of skills for AI coding agents. Skills are packaged instructions and scripts that extend agent capabilities across development, documentation, planning, and professional workflows.","skill_md_sha":"be42193f5f4617554acdd744c34e33430c991660","skill_md_path":"skills/difficult-workplace-conversations/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/softaworks/agent-toolkit/tree/main/skills/difficult-workplace-conversations"},"layout":"multi","source":"github","category":"agent-toolkit","frontmatter":{"name":"difficult-workplace-conversations","description":"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."},"skills_sh_url":"https://skills.sh/softaworks/agent-toolkit/difficult-workplace-conversations"},"updatedAt":"2026-05-18T18:52:57.029Z"}}