{"id":"091c474d-49f4-4a3d-82ff-b27eb60305ac","shortId":"etsC2Z","kind":"skill","title":"having-difficult-conversations","tagline":"Produce a Difficult Conversation Pack (talk track, objection handling, follow-up note).","description":"# Having Difficult Conversations\n\n## Scope\n\n**Covers**\n- Planning and delivering **clear, respectful, direct** conversations about performance, behavior, expectations, and decisions\n- Turning “insight about feedback” into concrete artifacts: **brief → talk track → reactions plan → follow-up**\n- Using **Radical Candor** as a default stance: *care personally* + *challenge directly*\n- Preserving dignity in high-stakes moments (especially **layoffs/terminations**): private, human, and unambiguous\n- Separating **feelings** from **attributions** so feedback stays specific and actionable\n\n**When to use**\n- “Help me prepare a difficult conversation with my direct report / peer.”\n- “Write a talk track for performance feedback (with specific examples).”\n- “I need to deny a promotion—help me be direct and still leave hope + a path.”\n- “Prepare a layoff/termination conversation talk track (I have HR involved).”\n- “Draft a follow-up message after a hard conversation that documents next steps.”\n\n**When NOT to use**\n- You need to decide *whether* to promote/terminate (use your company’s performance process; involve HR/leadership)\n- You’re handling harassment, discrimination, threats, or an investigation (stop and follow HR/legal policy)\n- You need legal advice, severance guidance, or policy interpretation (involve HR/legal)\n- The situation is a mental health or safety crisis (seek professional help and follow company policy)\n- You want an ongoing coaching and 1:1 system for your reports (use `running-effective-1-1s`)\n- You want to develop PM skills through coaching, not deliver specific feedback (use `coaching-pms`)\n- You need to set expectations or push back *upward* with your manager (use `managing-up`)\n- You want to run a blameless retrospective after an incident or failure (use `post-mortems-retrospectives`)\n\n## Inputs\n\n**Minimum required**\n- Conversation type (feedback, performance, promotion denial, layoff/termination) + relationship (manager/report/peer)\n- Desired outcome (what should be true immediately after + in 2–4 weeks)\n- 2–5 concrete examples/facts (what happened, when, impact) + expectations/standards\n- Constraints: timeline/urgency, location (in-person/video), HR/legal involvement (if applicable)\n- Any support you can offer (coaching, resources, training, timeline, check-ins)\n\n**Missing-info strategy**\n- Ask up to 5 questions from [references/INTAKE.md](references/INTAKE.md) (in 3–5 question batches).\n- If key details remain unknown, proceed with explicit assumptions and list **Open questions** that would change the script or follow-up plan.\n- Do not request secrets or sensitive personal data; use anonymized summaries.\n\n## Outputs (deliverables)\n\nProduce a **Difficult Conversation Pack** in Markdown (in-chat; or as files if the user requests):\n\n1) **Conversation brief** (context, decision/outcome, facts, success signals, constraints)\n2) **Message map + talk track/script** (opening, key message, evidence, impact, ask/decision, support, boundaries, close)\n3) **Objection + emotion handling plan** (likely reactions, what to say/do, what not to say/do)\n4) **Follow-up artifacts** (written follow-up note + next steps/check-ins; optional documentation note)\n5) **Risks / Open questions / Next steps** (always included)\n\nTemplates: [references/TEMPLATES.md](references/TEMPLATES.md)  \nExpanded guidance: [references/WORKFLOW.md](references/WORKFLOW.md)\n\n## Workflow (8 steps)\n\n### 1) Intake + classify the conversation (and set safety boundaries)\n- **Inputs:** user request; [references/INTAKE.md](references/INTAKE.md).\n- **Actions:** Determine conversation type and stakes. Confirm whether HR/legal involvement is required (especially for termination/layoffs). Decide deliverable scope (full pack vs just script + follow-up).\n- **Outputs:** Conversation type + constraints + assumptions/unknowns list.\n- **Checks:** You can state: “This is a <type> conversation with <relationship> to achieve <outcome> by <time>.”\n\n### 2) Define the outcome and non‑negotiables\n- **Inputs:** intent; constraints.\n- **Actions:** Write the “desired after” (immediate + 2–4 weeks). Identify non-negotiables (e.g., decision already made, behavior must change, timeline is fixed). Decide what support you can offer and what you cannot.\n- **Outputs:** Outcome statement + non-negotiables + support menu.\n- **Checks:** Non-negotiables are explicit and do not contradict HR/legal policy.\n\n### 3) Build the fact base (specific examples, not labels)\n- **Inputs:** examples/facts; expectations/standards.\n- **Actions:** Convert vague labels (“unreliable”, “not strategic”) into 2–5 concrete observations with impact. Separate **facts** from **interpretations**. Prepare a short “evidence” list you can calmly repeat.\n- **Outputs:** Evidence bullets + expectations statement.\n- **Checks:** Each example is time-bounded, observable, and tied to impact.\n\n### 4) Draft the message map (care + directness + hope/path when relevant)\n- **Inputs:** outcome + evidence + support.\n- **Actions:** Create a message map: opening, key message, evidence, impact, ask/decision, support, boundaries, close. For disappointing news (e.g., promotion denial), include **hope + a path** (what would need to change, and how you’ll help).\n- **Outputs:** Message map (ready for scripting).\n- **Checks:** The core message is deliverable in 1–2 sentences without hedging.\n\n### 5) Turn the map into a talk track/script (with pauses)\n- **Inputs:** message map; time box.\n- **Actions:** Write a short script with natural language, planned pauses, and 2–3 “anchor phrases” you can repeat under stress. Add 3–5 questions that invite understanding (not debate).\n- **Outputs:** Talk track/script.\n- **Checks:** Script uses respectful language and avoids “kitchen-sinking” unrelated issues.\n\n### 6) Plan logistics (privacy, timing, who attends, documentation)\n- **Inputs:** constraints; HR/legal involvement.\n- **Actions:** Choose private setting and sufficient time. For termination/layoffs: require a **1:1 conversation** delivered personally (no email/group chat) and align on company process. Decide what you will document and what you will not.\n- **Outputs:** Logistics plan + documentation plan.\n- **Checks:** Logistics preserve dignity and follow policy; no surprises that should have been coordinated with HR.\n\n### 7) Anticipate reactions (emotion vs attribution) and write response options\n- **Inputs:** relationship history; likely reactions.\n- **Actions:** Create a reaction map (shock/anger/sadness/defensiveness). Draft empathy statements, listening moves, and boundary lines. Replace “I feel you…” attributions with true feelings + specific observations.\n- **Outputs:** Objection + emotion handling plan.\n- **Checks:** Responses acknowledge emotion without walking back the core message.\n\n### 8) Follow up + quality gate\n- **Inputs:** full draft pack.\n- **Actions:** Draft the follow-up note (summary + next steps + check-in). If appropriate, draft a documentation note aligned with policy. Run [references/CHECKLISTS.md](references/CHECKLISTS.md) and score with [references/RUBRIC.md](references/RUBRIC.md). Add **Risks / Open questions / Next steps**.\n- **Outputs:** Final Difficult Conversation Pack.\n- **Checks:** Checklist passes with no “stop” items; next steps have owners and dates.\n\n## Quality gate (required)\n- Use [references/CHECKLISTS.md](references/CHECKLISTS.md) and [references/RUBRIC.md](references/RUBRIC.md).\n- Always include: **Risks**, **Open questions**, **Next steps**.\n\n## Examples\n\n**Example 1 (performance feedback):** “I’m a manager. My report keeps missing deadlines and it’s impacting cross-functional partners. Help me prepare the conversation and a follow-up plan.”  \nExpected: evidence-based brief, direct script with care, reaction handling, and a documented 2–4 week improvement plan with check-ins.\n\n**Example 2 (promotion denial):** “I’m denying a promotion this cycle. I want to be clear and still leave hope + a path.”  \nExpected: a clear decision statement, concrete gaps vs expectations, and an explicit growth plan (what to do next, how the manager will support, when to revisit).\n\n**Boundary example:** “Write an email to fire someone so I don’t have to talk to them.”\nResponse: do not proceed; termination/layoffs should be delivered personally in a private 1:1 per policy with HR involvement.\n\n**Boundary example 2:** “Help me set up a regular coaching cadence with my team.”\nResponse: this skill is for preparing specific difficult conversations, not designing ongoing coaching systems. Use `running-effective-1-1s` for 1:1 cadence and coaching toolkits, or `coaching-pms` for PM skill development.\n\n## Anti-patterns (common failure modes)\n\n1. **Kitchen-sinking**: Piling every past frustration into one conversation instead of focusing on 2-3 specific, recent, observable examples. The recipient feels ambushed and shuts down.\n2. **The empathy sandwich gone wrong**: Opening with excessive praise, burying the real message in the middle, and closing with more praise. The recipient walks away confused about what actually needs to change.\n3. **Label-based feedback**: Using character judgments (“you’re not strategic”, “you’re unreliable”) instead of describing specific observable behaviors and their impact. Labels trigger defensiveness and are unfalsifiable.\n4. **Deferred decision delivery**: Spending 10 minutes “setting context” before revealing that a decision has already been made (e.g., promotion denied, role change). The recipient feels manipulated. Lead with the decision.\n5. **Missing follow-up loop**: Delivering the conversation well but failing to send a written follow-up with next steps, check-in dates, and documented expectations. Without a paper trail, accountability evaporates.","tags":["having","difficult","conversations","lenny","skills","plus","liqiongyu","agent-skills","ai-agents","automation","claude","codex"],"capabilities":["skill","source-liqiongyu","skill-having-difficult-conversations","topic-agent-skills","topic-ai-agents","topic-automation","topic-claude","topic-codex","topic-prompt-engineering","topic-refoundai","topic-skillpack"],"categories":["lenny_skills_plus"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/liqiongyu/lenny_skills_plus/having-difficult-conversations","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add liqiongyu/lenny_skills_plus","source_repo":"https://github.com/liqiongyu/lenny_skills_plus","install_from":"skills.sh"}},"qualityScore":"0.474","qualityRationale":"deterministic score 0.47 from registry signals: · indexed on github topic:agent-skills · 49 github stars · SKILL.md body (9,751 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":"2026-04-22T00:56:22.778Z","embedding":null,"createdAt":"2026-04-18T22:16:38.186Z","updatedAt":"2026-04-22T00:56:22.778Z","lastSeenAt":"2026-04-22T00:56:22.778Z","tsv":"'-1':226,1148 '-3':1187 '/video':316 '1':215,216,225,403,473,711,798,799,977,1108,1109,1147,1151,1152,1171 '10':1267 '2':298,301,412,531,547,614,712,742,1022,1032,1117,1186,1199 '3':346,426,594,743,752,1232 '4':299,440,548,650,1023,1262 '5':302,340,347,455,615,716,753,1293 '6':775 '7':842 '8':471,896 'account':1326 'achiev':529 'acknowledg':888 'action':84,487,541,606,664,731,787,857,905 'actual':1228 'add':751,935 'advic':185 'align':807,924 'alreadi':556,1277 'alway':461,968 'ambush':1195 'anchor':744 'anonym':382 'anti':1166 'anti-pattern':1165 'anticip':843 'applic':320 'appropri':919 'artifact':42,444 'ask':337 'ask/decision':422,674 'assumpt':358 'assumptions/unknowns':517 'attend':781 'attribut':78,847,875 'avoid':769 'away':1224 'back':251,892 'base':598,1011,1235 'batch':349 'behavior':32,558,1252 'blameless':265 'bound':644 'boundari':424,481,676,869,1079,1115 'box':730 'brief':43,405,1012 'build':595 'bullet':635 'buri':1209 'cadenc':1125,1153 'calm':631 'candor':53 'cannot':573 'care':58,655,1016 'challeng':60 'chang':365,560,692,1231,1284 'charact':1238 'chat':395,805 'check':331,519,582,638,704,763,826,886,916,946,1029,1316 'check-in':330,915,1028,1315 'checklist':947 'choos':788 'classifi':475 'clear':26,1046,1055 'close':425,677,1217 'coach':213,235,242,326,1124,1141,1155,1159 'coaching-pm':241,1158 'common':1168 'compani':162,207,809 'concret':41,303,616,1058 'confirm':493 'confus':1225 'constraint':310,411,516,540,784 'context':406,1270 'contradict':591 'convers':4,8,20,29,93,128,144,280,389,404,477,489,514,526,800,944,1001,1137,1181,1301 'convert':607 'coordin':839 'core':706,894 'cover':22 'creat':665,858 'crisi':201 'cross':994 'cross-funct':993 'cycl':1041 'data':380 'date':958,1318 'deadlin':988 'debat':759 'decid':156,502,564,811 'decis':35,555,1056,1264,1275,1292 'decision/outcome':407 'default':56 'defens':1258 'defer':1263 'defin':532 'deliv':25,237,801,1103,1299 'deliver':385,503,709 'deliveri':1265 'deni':112,1037,1282 'denial':285,683,1034 'describ':1249 'design':1139 'desir':289,544 'detail':352 'determin':488 'develop':231,1164 'difficult':3,7,19,92,388,943,1136 'digniti':63,829 'direct':28,61,96,118,656,1013 'disappoint':679 'discrimin':172 'document':146,453,782,815,824,922,1021,1320 'draft':135,651,863,903,906,920 'e.g':554,681,1280 'effect':224,1146 'email':1083 'email/group':804 'emot':428,845,883,889 'empathi':864,1201 'especi':69,499 'evapor':1327 'everi':1176 'evid':420,627,634,662,672,1010 'evidence-bas':1009 'exampl':108,600,640,975,976,1031,1080,1116,1191 'examples/facts':304,604 'excess':1207 'expand':466 'expect':33,248,636,1008,1053,1061,1321 'expectations/standards':309,605 'explicit':357,587,1064 'fact':408,597,621 'fail':1304 'failur':271,1169 'feedback':39,80,105,239,282,979,1236 'feel':76,873,878,1194,1287 'file':398 'final':942 'fire':1085 'fix':563 'focus':1184 'follow':15,49,138,179,206,370,442,447,511,831,897,909,1005,1296,1310 'follow-up':14,48,137,369,441,446,510,908,1004,1295,1309 'frustrat':1178 'full':505,902 'function':995 'gap':1059 'gate':900,960 'gone':1203 'growth':1065 'guidanc':187,467 'handl':13,170,429,884,1018 'happen':306 'harass':171 'hard':143 'having-difficult-convers':1 'health':198 'hedg':715 'help':88,115,204,697,997,1118 'high':66 'high-stak':65 'histori':854 'hope':122,685,1050 'hope/path':657 'hr':133,841,1113 'hr/leadership':167 'hr/legal':180,192,317,495,592,785 'human':72 'identifi':550 'immedi':295,546 'impact':308,421,619,649,673,992,1255 'improv':1025 'in':332,1030 'in-chat':393 'in-person':313 'incid':269 'includ':462,684,969 'info':335 'input':277,482,538,603,660,726,783,852,901 'insight':37 'instead':1182,1247 'intak':474 'intent':539 'interpret':190,623 'investig':176 'invit':756 'involv':134,166,191,318,496,786,1114 'issu':774 'item':952 'judgment':1239 'keep':986 'key':351,418,670 'kitchen':771,1173 'kitchen-sink':770,1172 'label':602,609,1234,1256 'label-bas':1233 'languag':738,767 'layoff/termination':127,286 'layoffs/terminations':70 'lead':1289 'leav':121,1049 'legal':184 'like':431,855 'line':870 'list':360,518,628 'listen':866 'll':696 'locat':312 'logist':777,822,827 'loop':1298 'm':981,1036 'made':557,1279 'manag':255,258,983,1073 'manager/report/peer':288 'managing-up':257 'manipul':1288 'map':414,654,668,700,719,728,861 'markdown':392 'mental':197 'menu':581 'messag':140,413,419,653,667,671,699,707,727,895,1212 'middl':1215 'minimum':278 'minut':1268 'miss':334,987,1294 'missing-info':333 'mode':1170 'moment':68 'mortem':275 'move':867 'must':559 'natur':737 'need':110,154,183,245,690,1229 'negoti':537,553,579,585 'news':680 'next':147,450,459,913,939,953,973,1070,1313 'non':536,552,578,584 'non-negoti':551,577,583 'note':17,449,454,911,923 'object':12,427,882 'observ':617,645,880,1190,1251 'offer':325,569 'one':1180 'ongo':212,1140 'open':361,417,457,669,937,971,1205 'option':452,851 'outcom':290,534,575,661 'output':384,513,574,633,698,760,821,881,941 'owner':956 'pack':9,390,506,904,945 'paper':1324 'partner':996 'pass':948 'past':1177 'path':124,687,1052 'pattern':1167 'paus':725,740 'peer':98 'per':1110 'perform':31,104,164,283,978 'person':59,315,379,802,1104 'phrase':745 'pile':1175 'plan':23,47,372,430,739,776,823,825,885,1007,1026,1066 'pm':232,1162 'pms':243,1160 'polici':181,189,208,593,832,926,1111 'post':274 'post-mortems-retrospect':273 'prais':1208,1220 'prepar':90,125,624,999,1134 'preserv':62,828 'privaci':778 'privat':71,789,1107 'proceed':355,1099 'process':165,810 'produc':5,386 'profession':203 'promot':114,284,682,1033,1039,1281 'promote/terminate':159 'push':250 'qualiti':899,959 'question':341,348,362,458,754,938,972 'radic':52 're':169,1241,1245 'reaction':46,432,844,856,860,1017 'readi':701 'real':1211 'recent':1189 'recipi':1193,1222,1286 'references/checklists.md':928,929,963,964 'references/intake.md':343,344,485,486 'references/rubric.md':933,934,966,967 'references/templates.md':464,465 'references/workflow.md':468,469 'regular':1123 'relationship':287,853 'relev':659 'remain':353 'repeat':632,748 'replac':871 'report':97,220,985 'request':375,402,484 'requir':279,498,796,961 'resourc':327 'respect':27,766 'respons':850,887,1096,1129 'retrospect':266,276 'reveal':1272 'revisit':1078 'risk':456,936,970 'role':1283 'run':223,263,927,1145 'running-effect':222,1144 'safeti':200,480 'sandwich':1202 'say/do':435,439 'scope':21,504 'score':931 'script':367,509,703,735,764,1014 'secret':376 'seek':202 'send':1306 'sensit':378 'sentenc':713 'separ':75,620 'set':247,479,790,1120,1269 'sever':186 'shock/anger/sadness/defensiveness':862 'short':626,734 'shut':1197 'signal':410 'sink':772,1174 'situat':194 'skill':233,1131,1163 'skill-having-difficult-conversations' 'someon':1086 'source-liqiongyu' 'specif':82,107,238,599,879,1135,1188,1250 'spend':1266 'stake':67,492 'stanc':57 'state':522 'statement':576,637,865,1057 'stay':81 'step':148,460,472,914,940,954,974,1314 'steps/check-ins':451 'still':120,1048 'stop':177,951 'strateg':612,1243 'strategi':336 'stress':750 'success':409 'suffici':792 'summari':383,912 'support':322,423,566,580,663,675,1075 'surpris':834 'system':217,1142 'talk':10,44,101,129,415,722,761,1093 'team':1128 'templat':463 'termination/layoffs':501,795,1100 'threat':173 'tie':647 'time':643,729,779,793 'time-bound':642 'timelin':329,561 'timeline/urgency':311 'toolkit':1156 'topic-agent-skills' 'topic-ai-agents' 'topic-automation' 'topic-claude' 'topic-codex' 'topic-prompt-engineering' 'topic-refoundai' 'topic-skillpack' 'track':11,45,102,130 'track/script':416,723,762 'trail':1325 'train':328 'trigger':1257 'true':294,877 'turn':36,717 'type':281,490,515 'unambigu':74 'understand':757 'unfalsifi':1261 'unknown':354 'unrel':773 'unreli':610,1246 'upward':252 'use':51,87,152,160,221,240,256,272,381,765,962,1143,1237 'user':401,483 'vagu':608 'vs':507,846,1060 'walk':891,1223 'want':210,229,261,1043 'week':300,549,1024 'well':1302 'whether':157,494 'without':714,890,1322 'workflow':470 'would':364,689 'write':99,542,732,849,1081 'written':445,1308 'wrong':1204","prices":[{"id":"4d600571-943d-4d77-b2e2-34a800d76e9f","listingId":"091c474d-49f4-4a3d-82ff-b27eb60305ac","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"liqiongyu","category":"lenny_skills_plus","install_from":"skills.sh"},"createdAt":"2026-04-18T22:16:38.186Z"}],"sources":[{"listingId":"091c474d-49f4-4a3d-82ff-b27eb60305ac","source":"github","sourceId":"liqiongyu/lenny_skills_plus/having-difficult-conversations","sourceUrl":"https://github.com/liqiongyu/lenny_skills_plus/tree/main/skills/having-difficult-conversations","isPrimary":false,"firstSeenAt":"2026-04-18T22:16:38.186Z","lastSeenAt":"2026-04-22T00:56:22.778Z"}],"details":{"listingId":"091c474d-49f4-4a3d-82ff-b27eb60305ac","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"liqiongyu","slug":"having-difficult-conversations","github":{"repo":"liqiongyu/lenny_skills_plus","stars":49,"topics":["agent-skills","ai-agents","automation","claude","codex","prompt-engineering","refoundai","skillpack"],"license":"apache-2.0","html_url":"https://github.com/liqiongyu/lenny_skills_plus","pushed_at":"2026-04-04T06:30:11Z","description":"86 agent-executable skill packs converted from RefoundAI’s Lenny skills (unofficial). Works with Codex + Claude Code.","skill_md_sha":"325f3619cda4cdbc2edc719ec963dc538d4824f2","skill_md_path":"skills/having-difficult-conversations/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/liqiongyu/lenny_skills_plus/tree/main/skills/having-difficult-conversations"},"layout":"multi","source":"github","category":"lenny_skills_plus","frontmatter":{"name":"having-difficult-conversations","description":"Produce a Difficult Conversation Pack (talk track, objection handling, follow-up note)."},"skills_sh_url":"https://skills.sh/liqiongyu/lenny_skills_plus/having-difficult-conversations"},"updatedAt":"2026-04-22T00:56:22.778Z"}}