{"id":"ec9a0796-035d-4f1a-93e6-409d3b76b9b3","shortId":"m7YVvD","kind":"skill","title":"thinking-partner","tagline":"A deterministic thinking partner that challenges assumptions and applies mental models to sharpen decisions, solve problems, and think more clearly. Use this skill whenever a user says \"help me think through X\", \"challenge my thinking\", \"what am I missing\", \"apply mental models t","description":"# Thinking Partner\n\nA deterministic thinking partner that challenges assumptions and applies mental models to help users think better and clearer. Not a lecture — a sparring session.\n\n## Core Philosophy\n\nGood thinking is an active achievement, not a default state. The goal is not to tell the user what to think, but to sharpen *how* they think by:\n\n1. **Challenging assumptions** — Surface hidden beliefs the user is treating as facts\n2. **Applying mental models** — Select and deploy the right thinking frameworks for the situation\n3. **Detecting orientation capture** — Notice when thinking serves comfort instead of truth\n4. **Maintaining productive tension** — Hold complexity open long enough to find real insight\n\nYou are not a yes-machine. You are not an interrogator. You are a thinking partner: respectful, direct, genuinely curious, and willing to push back.\n\n## When This Triggers\n\n- \"Help me think through X\"\n- \"Challenge my thinking / assumptions\"\n- \"What am I missing?\"\n- \"Apply [any model name] to this\"\n- \"Play devil's advocate\"\n- \"Stress test this idea / plan\"\n- \"Help me decide between X and Y\"\n- \"What are the second-order effects?\"\n- \"Am I thinking about this right?\"\n- \"I'm stuck on a decision\"\n- Any named model: SWOT, first principles, inversion, pre-mortem, 5 Whys, etc.\n- Situations where user seems stuck, rationalizing, or facing genuine complexity\n\n## Workflow\n\n### Step 1: Understand the Situation\n\nBefore deploying any model, understand:\n- **What is the user actually trying to decide, solve, or understand?**\n- **What is at stake?** (career, money, relationships, identity, time)\n- **What is the time horizon?** (today, this quarter, 10 years)\n- **What constraints exist?** (resources, information, reversibility)\n\nAsk ONE clarifying question if the situation is ambiguous. Do not barrage with questions. If you have enough context, move directly to Step 2.\n\n### Step 2: Detect Thinking Orientation\n\nBefore picking models, silently diagnose the user's thinking state. This determines your approach.\n\n**Process-sovereign** (healthy): User is genuinely exploring, open to being wrong. Conclusions move when evidence demands it.\n→ Proceed as collaborative partner. Offer models, explore together.\n\n**Conclusion-preserving** (GT1): User has already decided and is seeking validation. Evidence against is explained away.\n→ Gently surface this: \"It sounds like you've already landed on X. What would have to be true for Y to be the better choice?\"\n\n**Authority-preserving** (GT2): User is attached to being the expert, not to being right.\n→ Frame challenges as exploring the idea, not challenging the person: \"Let's stress-test this as if we were advising someone else.\"\n\n**Threat-reducing** (GT3): User is anxious and rushing to resolve ambiguity for comfort, not clarity.\n→ Slow things down: \"There's no pressure to decide right now. Let's hold both options open for a moment and look at them clearly.\"\n\n**Completion-seeking** (GT4): User wants *an* answer, not *the right* answer.\n→ Insert a pause: \"Before we settle on this, let me push on it from one angle to make sure it holds up.\"\n\n**Monitor co-option** (GT5): User has done elaborate analysis that always confirms the same conclusion.\n→ Don't argue content. Introduce external checks: \"What prediction would this view make that we could actually verify?\"\n\n### Step 3: Select Mental Models\n\nBased on the situation type, select 2-3 models. Offer them to the user with a one-line description of each and a recommendation.\n\n**For decisions**, consider:\n- Inversion (\"What would guarantee the wrong choice?\")\n- Second-Order Thinking (\"And then what?\")\n- Opportunity Cost (\"What are you giving up?\")\n- Regret Minimization (\"Which choice minimizes regret at 80?\")\n- Reversibility Test (\"Is this a one-way or two-way door?\")\n- Decision Matrix (weighted criteria comparison)\n- Pre-Mortem (\"It's a year later and this failed — why?\")\n- Preserving Optionality (\"Does this close doors I may want open?\")\n- Asymmetric Risk / Convexity (\"Capped downside, uncapped upside?\")\n- 10/10/10 Rule (\"How will I feel in 10 minutes, 10 months, 10 years?\")\n- Circle of Concern vs Influence (\"Can I actually affect this?\")\n- Skin in the Game (\"Does the advisor bear consequences?\")\n- Satisficing vs Maximizing (\"Is good enough better than optimal here?\")\n\n**For problems**, consider:\n- First Principles (\"What do we know to be fundamentally true?\")\n- Root Cause / 5 Whys (\"Why? → Why? → Why? → Why? → Why?\")\n- Fishbone / Ishikawa (categorize causes systematically)\n- Constraint Analysis / Theory of Constraints (\"What's the real bottleneck?\")\n- Reframing (\"What if this isn't the problem at all?\")\n- MECE Decomposition (\"Are my categories gap-free and non-overlapping?\")\n- Hypothesis-Driven Solving (\"What's the fastest test to confirm or kill this?\")\n- Bright Spots Analysis (\"Where is this already working?\")\n- Local vs Global Optima (\"Am I stuck on a local peak?\")\n\n**For strategy and planning**, consider:\n- Scenario Planning (\"What are 3 plausible futures?\")\n- SWOT Analysis (Strengths, Weaknesses, Opportunities, Threats)\n- Porter's Five Forces (competitive landscape)\n- Red Team Analysis (\"How would an adversary defeat this plan?\")\n- Margin of Safety (\"What buffer exists if assumptions are wrong?\")\n- The Map is Not the Territory (\"Where might our model diverge from reality?\")\n- Chesterton's Fence (\"Do I understand why this exists before removing it?\")\n- Lindy Effect (\"How long has this survived? That predicts its future.\")\n- Tragedy of the Commons (\"Who owns the downside of this shared resource?\")\n- Principal-Agent Problem (\"Are the agent's incentives aligned with mine?\")\n- Winner-Take-All / Power Laws (\"Do small advantages compound into dominance?\")\n- Switching Costs / Lock-in (\"How painful is it to leave?\")\n\n**For evaluating claims and evidence**, consider:\n- Bayesian Updating (\"How should this evidence shift our confidence?\")\n- Falsifiability (\"What evidence would disprove this?\")\n- Base Rate Neglect (\"What's the prior probability before this specific case?\")\n- Survivorship Bias (\"Are we only looking at winners?\")\n- Correlation vs Causation (\"Is there a causal mechanism, or just co-occurrence?\")\n- Selection Bias (\"Who's missing from this dataset?\")\n- Gambler's Fallacy (\"Are these events actually dependent?\")\n- Thinking in Bets (\"Was the process sound, regardless of outcome?\")\n- Counterfactual Thinking (\"What if this one variable had been different?\")\n\n**For understanding systems and dynamics**, consider:\n- Feedback Loops (\"Is this self-reinforcing or self-correcting?\")\n- Emergence (\"What behavior arises from the interaction of parts?\")\n- Leverage Points (\"Where does a small change produce a large effect?\")\n- The Red Queen Effect (\"Are we running just to stay in place?\")\n- Ecosystems Thinking (\"Who else is affected and how do they respond?\")\n- Stocks and Flows (\"What is accumulating or depleting, and at what rate?\")\n- Delays (\"How long before this action's effect becomes visible?\")\n- Critical Mass / Tipping Points (\"Is there a threshold that flips the system?\")\n- Hysteresis / Path Dependence (\"Can we actually reverse this?\")\n- Antifragility (\"Does this get stronger from shocks?\")\n- Entropy (\"What decays without active maintenance?\")\n\n**For creativity and getting unstuck**, consider:\n- Inversion (\"Instead of how to succeed, how would you guarantee failure?\")\n- SCAMPER (Substitute, Combine, Adapt, Modify, Put to another use, Eliminate, Reverse)\n- Analogous Reasoning (\"What other domain solved a similar problem?\")\n- Constraint Removal (\"If X wasn't a constraint, what would you do?\")\n- Reframing (\"What if the opposite of your assumption is true?\")\n- Oblique Strategies (introduce random prompts to break habitual thinking)\n- Minimum Viable Experiment (\"What's the cheapest test of the core assumption?\")\n\n**For risk assessment**, consider:\n- Pre-Mortem (\"Assume failure — what caused it?\")\n- Black Swan Awareness (\"What low-probability, high-impact events am I ignoring?\")\n- Expected Value (\"Probability × Impact for each outcome\")\n- Margin of Safety (\"How much buffer do I have?\")\n- Asymmetric Risk (\"What's the upside vs downside ratio?\")\n- Barbell Strategy (\"Extreme safety + small high-upside bets, avoid the middle\")\n- Via Negativa (\"What should I remove rather than add?\")\n- Hormesis (\"Is this the right dose of stress to trigger adaptation?\")\n\n**For communication and persuasion**, consider:\n- Steel Manning (\"What's the strongest version of the opposing view?\")\n- Pyramid Principle (\"Lead with the conclusion, support with evidence\")\n- BLUF — Bottom Line Up Front\n- Circle of Competence (\"Am I speaking within or outside my expertise?\")\n- Reciprocity (\"What can I give first?\")\n- Narrative / Storytelling (\"What's the story, and who's the protagonist?\")\n- Curse of Knowledge (\"What would this look like to a newcomer?\")\n\n**For psychology and bias awareness**, consider:\n- Hindsight Bias (\"What did I actually believe before I knew the result?\")\n- Fundamental Attribution Error (\"What situational pressures explain this behavior?\")\n- Commitment & Consistency Bias (\"Am I defending this because I committed to it?\")\n- Planning Fallacy (\"What happened when similar projects were attempted?\")\n- Halo Effect (\"Would I rate this the same without the one impressive trait?\")\n- Peak-End Rule (\"What will the emotional peak and ending be?\")\n\n**For negotiation**, consider:\n- BATNA (\"What's my best alternative if this deal fails?\")\n- ZOPA (\"Is there overlap between what each side would accept?\")\n- Logrolling (\"What do I value less that they value more?\")\n- Schelling Point (\"What's the obvious default everyone converges on?\")\n\n**For learning and growth**, consider:\n- Feynman Technique (\"Can I explain this so a 12-year-old understands?\")\n- Spaced Repetition (review at increasing intervals for retention)\n- Zone of Proximal Development (\"Just beyond current ability, with support\")\n- Maker's Schedule vs Manager's Schedule (\"Am I protecting deep-work blocks?\")\n\n**For game theory and competition**, consider:\n- Prisoner's Dilemma (\"One-shot or repeated game?\")\n- Tit for Tat (\"Mirror cooperation, punish defection\")\n- Signaling (\"What costly action proves my claim?\")\n- Moral Hazard (\"Does the decision-maker bear the consequences?\")\n- Coevolution (\"How is the other side adapting to my moves?\")\n- Niche Construction (\"Can I reshape the environment instead of adapting?\")\n\n**For ethics**, consider:\n- Veil of Ignorance (\"Would I accept this if I didn't know my role?\")\n\nFor the full catalog of 150+ models with detailed descriptions and usage guidance, see: `references/model-catalog.md`\n\n### Step 4: Apply the Models\n\nWalk the user through the selected models conversationally. For each model:\n\n1. **Name it** — briefly explain what it does (one sentence)\n2. **Ask the key question** — the diagnostic question the model raises\n3. **Hold space for their answer** — listen before pushing\n4. **Push where it matters** — challenge weak reasoning, surface hidden assumptions, note contradictions\n5. **Synthesize** — after working through models, pull the threads together\n\nKeep it collaborative. Ask, don't lecture. One question at a time. If a model isn't landing, pivot to another.\n\n### Step 5: Challenge and Stress-Test\n\nAfter initial analysis, actively challenge the emerging conclusion:\n\n- **Inversion probe**: \"What if the opposite were true?\"\n- **Pre-mortem probe**: \"Assume this fails spectacularly. What went wrong?\"\n- **Blind spot probe**: \"What perspective are we not considering?\"\n- **Confidence calibration**: \"On a scale of 1-10, how confident are you? What would move that number?\"\n- **Skin in the game test**: \"Would you bet $10,000 of your own money on this conclusion?\"\n\nDo NOT challenge just to challenge. Challenge where it matters — where you detect weak reasoning, unexamined assumptions, or orientation capture.\n\n### Step 6: Synthesize and Close\n\nWrap with a clear synthesis:\n\n1. **Key insight**: The most important thing that emerged\n2. **Decision or next step**: What to do (or what to investigate further)\n3. **Assumptions to monitor**: What beliefs this depends on — if these change, revisit\n4. **Model(s) that helped most**: So the user can internalize the framework\n\nIf the user requests it, offer to save the analysis to a file.\n\n## Thinking Partner Behaviors\n\n### Do:\n- Ask one question at a time\n- Name the model you're applying (builds the user's toolkit)\n- Say \"I notice...\" when surfacing patterns or biases\n- Use the user's own words back to them when reframing\n- Admit when a question is outside your competence\n- Match formality to the user's tone\n- Combine models when appropriate (e.g., First Principles + Pre-Mortem)\n- Use concrete examples and analogies\n\n### Don't:\n- Lecture about models abstractly without applying them\n- Stack multiple questions in one message\n- Be contrarian for its own sake\n- Diagnose the user's psychology out loud in clinical terms\n- Prescribe what to think — sharpen how they think\n- Use the word \"bias\" as a weapon (\"You're showing confirmation bias\" is unhelpful)\n- Rush to resolution when the user needs to sit with complexity\n\n## Assumption Challenging Techniques\n\nThese are your primary tools for pushing back:\n\n**The Reversal**: \"What if the opposite of [assumption] were true? What would change?\"\n\n**The Outsider Test**: \"If a smart friend described this exact situation, what would you tell them?\"\n\n**The Evidence Demand**: \"What specific evidence supports this? How strong is that evidence, really?\"\n\n**The Steelman**: \"What's the strongest argument against your current position? Can you make that argument convincingly?\"\n\n**The Time Shift**: \"How will you feel about this decision in 10 minutes? 10 months? 10 years?\"\n\n**The Pre-Mortem**: \"It's one year from now and this went badly. Write the post-mortem.\"\n\n**The Base Rate Check**: \"How often does this type of thing work out in general — not just in your case?\"\n\n**The Null Hypothesis**: \"What if nothing changed? What's the cost of inaction?\"\n\n## Combining Models\n\nModels are most powerful in combination. Common pairings:\n\n- **First Principles + Inversion**: Break it down, then flip it\n- **Pre-Mortem + Second-Order Thinking**: Imagine failure, trace the cascading causes\n- **SWOT + Scenario Planning**: Map your position across multiple futures\n- **Bayesian Updating + Steel Manning**: Update beliefs by seriously considering the strongest counterargument\n- **Opportunity Cost + Regret Minimization**: What you're giving up vs what you'll wish you'd done\n- **Margin of Safety + Black Swan**: How much buffer exists for tail risks\n\n## Session Types\n\nAdapt your approach based on what the user needs:\n\n**Quick Gut-Check** (user has a specific question, wants rapid challenge):\n→ Apply 1-2 models, challenge hard, synthesize fast. 3-5 exchanges.\n\n**Deep Exploration** (user is genuinely uncertain, complex situation):\n→ Full workflow: diagnose orientation, select 2-3 models, apply thoroughly, challenge, synthesize. 8-15 exchanges.\n\n**Model Tutorial** (user wants to learn a specific model):\n→ Explain the model, walk through an example, then apply it to their real situation.\n\n**Decision Audit** (user has already decided, wants validation or red-teaming):\n→ Focus on Steps 5-6: challenge and stress-test the decision already made.\n\n## Anti-Patterns to Avoid\n\n**The Model Dump**: Listing 15 models without applying any. Models are tools — use them, don't display them.\n\n**The Bias Gotcha**: \"That's confirmation bias!\" is not helpful. Instead: \"I notice we keep finding evidence that supports X. What would evidence against X look like?\"\n\n**The Sophistication Trap**: More analysis under a bad orientation produces better-defended wrong answers. Check orientation first.\n\n**Premature Resolution**: Jumping to a clean answer when the problem is genuinely messy. Sometimes the right output is \"here are the 3 things you need to figure out before deciding.\"\n\n**The Uniform Fix**: Applying the same approach regardless of the situation. A career decision and a product feature decision need different models.\n\n## Reference Files\n\nFor detailed model descriptions and application guides:\n- `references/model-catalog.md` — Full catalog of 150+ models organized by discipline with key questions and when-to-use guidance\n- `references/thinking-diagnostics.md` — Deep guide to detecting orientation capture, cognitive operations, and self-correction protocols\n\nLoad reference files only when deeper detail is needed for a specific model or diagnostic state. The SKILL.md provides sufficient guidance for most sessions.","tags":["thinking","partner","mattnowdev","agent-skills","claude-code","critical-thinking","cursor","decision-making","mental-models"],"capabilities":["skill","source-mattnowdev","skill-thinking-partner","topic-agent-skills","topic-claude-code","topic-critical-thinking","topic-cursor","topic-decision-making","topic-mental-models","topic-thinking"],"categories":["thinking-partner"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/mattnowdev/thinking-partner/thinking-partner","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add mattnowdev/thinking-partner","source_repo":"https://github.com/mattnowdev/thinking-partner","install_from":"skills.sh"}},"qualityScore":"0.517","qualityRationale":"deterministic score 0.52 from registry signals: · indexed on github topic:agent-skills · 134 github stars · SKILL.md body (16,555 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":"2026-05-02T12:54:46.909Z","embedding":null,"createdAt":"2026-04-18T22:09:57.129Z","updatedAt":"2026-05-02T12:54:46.909Z","lastSeenAt":"2026-05-02T12:54:46.909Z","tsv":"'-10':1769 '-15':2298 '-2':2268 '-3':577,2291 '-5':2275 '-6':2339 '000':1788 '1':103,262,1645,1768,1826,2267 '10':299,681,683,685,1787,2103,2105,2107 '10/10/10':674 '12':1501 '15':2358 '150':1619,2482 '2':115,330,332,576,1655,1835,2290 '3':129,566,817,1666,1848,2274,2438 '4':141,1630,1675,1861 '5':247,731,1688,1720,2338 '6':1817 '8':2297 '80':626 'abil':1521 'abstract':1962 'accept':1467,1605 'accumul':1090 'achiev':80 'across':2199 'action':1102,1563 'activ':79,1138,1729 'actual':275,563,694,1003,1124,1383 'adapt':1160,1302,1583,1596,2245 'add':1291 'admit':1927 'advantag':920 'adversari':838 'advis':453 'advisor':703 'advoc':205 'affect':695,1079 'agent':902,906 'align':909 'alreadi':382,401,795,2327,2347 'altern':1453 'alway':542 'ambigu':315,467 'analog':1168,1956 'analysi':540,744,791,821,834,1728,1883,2403 'angl':524 'anoth':1164,1718 'answer':504,508,1671,2413,2423 'anti':2350 'anti-pattern':2349 'antifragil':1127 'anxious':462 'appli':12,43,57,116,196,1631,1902,1964,2266,2293,2317,2361,2450 'applic':2476 'approach':349,2247,2453 'appropri':1945 'argu':549 'argument':2081,2090 'aris':1045 'ask':307,1656,1701,1891 'assess':1222 'assum':1227,1746 'assumpt':10,55,105,191,849,1196,1219,1685,1812,1849,2021,2039 'asymmetr':667,1262 'attach':424 'attempt':1419 'attribut':1391 'audit':2324 'author':419 'authority-preserv':418 'avoid':1280,2353 'awar':1234,1376 'away':392 'back':179,1922,2031 'bad':2122,2406 'barbel':1271 'barrag':318 'base':570,956,2129,2248 'batna':1448 'bayesian':941,2202 'bear':704,1574 'becom':1105 'behavior':1044,1398,1889 'belief':108,1853,2207 'believ':1384 'best':1452 'bet':1007,1279,1786 'better':64,416,712,2410 'better-defend':2409 'beyond':1519 'bias':969,990,1375,1379,1401,1915,1999,2007,2373,2378 'black':1232,2234 'blind':1753 'block':1537 'bluf':1328 'bottleneck':752 'bottom':1329 'break':1205,2174 'briefli':1648 'bright':789 'buffer':846,1258,2238 'build':1903 'calibr':1763 'cap':670 'captur':132,1815,2502 'career':286,2459 'cascad':2191 'case':967,2147 'catalog':1617,2480 'categor':740 'categori':767 'caus':730,741,1230,2192 'causal':982 'causat':978 'challeng':9,36,54,104,188,434,440,1680,1721,1730,1798,1801,1802,2022,2265,2270,2295,2340 'chang':1057,1859,2044,2154 'cheapest':1214 'check':553,2131,2257,2414 'chesterton':865 'choic':417,604,622 'circl':687,1333 'claim':937,1566 'clarifi':309 'clariti':471 'clean':2422 'clear':23,496,1824 'clearer':66 'clinic':1986 'close':661,1820 'co':533,987 'co-occurr':986 'co-opt':532 'coevolut':1577 'cognit':2503 'collabor':370,1700 'combin':1159,1942,2161,2168 'comfort':137,469 'commit':1399,1408 'common':891,2169 'communic':1304 'comparison':644 'compet':1335,1934 'competit':830,1542 'complet':498 'completion-seek':497 'complex':146,259,2020,2283 'compound':921 'concern':689 'conclus':362,377,546,1324,1733,1795 'conclusion-preserv':376 'concret':1953 'confid':949,1762,1771 'confirm':543,785,2006,2377 'consequ':705,1576 'consid':597,718,812,940,1030,1145,1223,1307,1377,1447,1492,1543,1599,1761,2210 'consist':1400 'constraint':302,743,747,1177,1184 'construct':1588 'content':550 'context':325 'contradict':1687 'contrarian':1973 'converg':1486 'convers':1641 'convex':669 'convinc':2091 'cooper':1557 'core':73,1218 'correct':1041,2508 'correl':976 'cost':613,925,1562,2158,2215 'could':562 'counterargu':2213 'counterfactu':1015 'creativ':1141 'criteria':643 'critic':1107 'curious':174 'current':1520,2084 'curs':1361 'd':2229 'dataset':996 'deal':1456 'decay':1136 'decid':213,278,383,480,2328,2446 'decis':17,236,596,640,1572,1836,2101,2323,2346,2460,2465 'decision-mak':1571 'decomposit':764 'deep':1535,2277,2497 'deep-work':1534 'deeper':2515 'default':83,1484 'defeat':839 'defect':1559 'defend':1404,2411 'delay':1097 'demand':366,2063 'depend':1004,1121,1855 'deplet':1092 'deploy':121,267 'describ':2052 'descript':589,1623,2474 'detail':1622,2472,2516 'detect':130,333,1808,2500 'determin':347 'determinist':5,50 'develop':1517 'devil':203 'diagnos':340,1978,2287 'diagnost':1661,2524 'didn':1609 'differ':1024,2467 'dilemma':1546 'direct':172,327 'disciplin':2486 'display':2370 'disprov':954 'diverg':862 'domain':1172 'domin':923 'done':538,2230 'door':639,662 'dose':1297 'downsid':671,895,1269 'driven':777 'dump':2356 'dynam':1029 'e.g':1946 'ecosystem':1074 'effect':224,878,1061,1065,1104,1421 'elabor':539 'elimin':1166 'els':455,1077 'emerg':1042,1732,1834 'emot':1440 'end':1435,1443 'enough':149,324,711 'entropi':1134 'environ':1593 'error':1392 'etc':249 'ethic':1598 'evalu':936 'event':1002,1242 'everyon':1485 'evid':365,388,939,946,952,1327,2062,2066,2073,2388,2394 'exact':2054 'exampl':1954,2315 'exchang':2276,2299 'exist':303,847,873,2239 'expect':1246 'experi':1210 'expert':428 'expertis':1343 'explain':391,1396,1497,1649,2309 'explor':357,374,436,2278 'extern':552 'extrem':1273 'face':257 'fact':114 'fail':655,1457,1748 'failur':1156,1228,2188 'fallaci':999,1412 'falsifi':950 'fast':2273 'fastest':782 'featur':2464 'feedback':1031 'feel':679,2098 'fenc':867 'feynman':1493 'figur':2443 'file':1886,2470,2512 'find':151,2387 'first':241,719,1349,1947,2171,2416 'fishbon':738 'five':828 'fix':2449 'flip':1116,2178 'flow':1087 'focus':2335 'forc':829 'formal':1936 'frame':433 'framework':125,1873 'free':770 'friend':2051 'front':1332 'full':1616,2285,2479 'fundament':727,1390 'futur':819,887,2201 'gambler':997 'game':700,1539,1552,1782 'gap':769 'gap-fre':768 'general':2142 'gentl':393 'genuin':173,258,356,2281,2428 'get':1130,1143 'give':617,1348,2221 'global':799 'goal':86 'good':75,710 'gotcha':2374 'growth':1491 'gt1':379 'gt2':421 'gt3':459 'gt4':500 'gt5':535 'guarante':601,1155 'guid':2477,2498 'guidanc':1626,2495,2530 'gut':2256 'gut-check':2255 'habitu':1206 'halo':1420 'happen':1414 'hard':2271 'hazard':1568 'healthi':353 'help':31,61,183,211,1865,2381 'hidden':107,1684 'high':1240,1277 'high-impact':1239 'high-upsid':1276 'hindsight':1378 'hold':145,485,529,1667 'horizon':295 'hormesi':1292 'hypothesi':776,2150 'hypothesis-driven':775 'hysteresi':1119 'idea':209,438 'ident':289 'ignor':1245,1602 'imagin':2187 'impact':1241,1249 'import':1831 'impress':1431 'inact':2160 'incent':908 'increas':1510 'influenc':691 'inform':305 'initi':1727 'insert':509 'insight':153,1828 'instead':138,1147,1594,2382 'interact':1048 'intern':1871 'interrog':165 'interv':1511 'introduc':551,1201 'invers':243,598,1146,1734,2173 'investig':1846 'ishikawa':739 'isn':757,1713 'jump':2419 'keep':1698,2386 'key':1658,1827,2488 'kill':787 'knew':1387 'know':724,1611 'knowledg':1363 'land':402,1715 'landscap':831 'larg':1060 'later':652 'law':917 'lead':1321 'learn':1489,2305 'leav':934 'lectur':69,1704,1959 'less':1473 'let':443,483,517 'leverag':1051 'like':398,1368,2398 'lindi':877 'line':588,1330 'list':2357 'listen':1672 'll':2226 'load':2510 'local':797,806 'lock':927 'lock-in':926 'logrol':1468 'long':148,880,1099 'look':493,973,1367,2397 'loop':1032 'loud':1984 'low':1237 'low-prob':1236 'm':232 'machin':160 'made':2348 'maintain':142 'mainten':1139 'make':526,559,2088 'maker':1524,1573 'man':1309,2205 'manag':1528 'map':853,2196 'margin':842,1253,2231 'mass':1108 'match':1935 'matrix':641 'matter':1679,1805 'maxim':708 'may':664 'mece':763 'mechan':983 'mental':13,44,58,117,568 'messag':1971 'messi':2429 'middl':1282 'might':859 'mine':911 'minim':620,623,2217 'minimum':1208 'minut':682,2104 'mirror':1556 'miss':42,195,993 'model':14,45,59,118,198,239,269,338,373,569,578,861,1620,1633,1640,1644,1664,1693,1712,1862,1899,1943,1961,2162,2163,2269,2292,2300,2308,2311,2355,2359,2363,2468,2473,2483,2522 'modifi':1161 'moment':491 'money':287,1792 'monitor':531,1851 'month':684,2106 'moral':1567 'mortem':246,647,1226,1744,1951,2112,2127,2182 'move':326,363,1586,1776 'much':1257,2237 'multipl':1967,2200 'name':199,238,1646,1897 'narrat':1350 'need':2016,2253,2441,2466,2518 'negativa':1284 'neglect':958 'negoti':1446 'newcom':1371 'next':1838 'nich':1587 'non':773 'non-overlap':772 'note':1686 'noth':2153 'notic':133,1910,2384 'null':2149 'number':1778 'obliqu':1199 'obvious':1483 'occurr':988 'offer':372,579,1879 'often':2133 'old':1504 'one':308,523,587,633,1020,1430,1548,1653,1705,1892,1970,2115 'one-lin':586 'one-shot':1547 'one-way':632 'open':147,358,488,666 'oper':2504 'opportun':612,824,2214 'oppos':1317 'opposit':1193,1739,2037 'optim':714 'optima':800 'option':487,534,658 'order':223,607,2185 'organ':2484 'orient':131,335,1814,2288,2407,2415,2501 'outcom':1014,1252 'output':2433 'outsid':1341,1932,2046 'overlap':774,1461 'own':893 'pain':930 'pair':2170 'part':1050 'partner':3,7,48,52,170,371,1888 'path':1120 'pattern':1913,2351 'paus':511 'peak':807,1434,1441 'peak-end':1433 'person':442 'perspect':1757 'persuas':1306 'philosophi':74 'pick':337 'pivot':1716 'place':1073 'plan':210,811,814,841,1411,2195 'plausibl':818 'play':202 'point':1052,1110,1479 'porter':826 'posit':2085,2198 'post':2126 'post-mortem':2125 'power':916,2166 'pre':245,646,1225,1743,1950,2111,2181 'pre-mortem':244,645,1224,1742,1949,2110,2180 'predict':555,885 'prematur':2417 'prescrib':1988 'preserv':378,420,657 'pressur':478,1395 'primari':2027 'princip':901 'principal-ag':900 'principl':242,720,1320,1948,2172 'prior':962 'prison':1544 'probabl':963,1238,1248 'probe':1735,1745,1755 'problem':19,717,760,903,1176,2426 'proceed':368 'process':351,1010 'process-sovereign':350 'produc':1058,2408 'product':143,2463 'project':1417 'prompt':1203 'protagonist':1360 'protect':1533 'protocol':2509 'prove':1564 'provid':2528 'proxim':1516 'psycholog':1373,1982 'pull':1694 'punish':1558 'push':178,519,1674,1676,2030 'put':1162 'pyramid':1319 'quarter':298 'queen':1064 'question':310,320,1659,1662,1706,1893,1930,1968,2262,2489 'quick':2254 'rais':1665 'random':1202 'rapid':2264 'rate':957,1096,1424,2130 'rather':1289 'ratio':1270 'ration':255 're':1901,2004,2220 'real':152,751,2321 'realiti':864 'realli':2074 'reason':1169,1682,1810 'reciproc':1344 'recommend':594 'red':832,1063,2333 'red-team':2332 'reduc':458 'refer':2469,2511 'references/model-catalog.md':1628,2478 'references/thinking-diagnostics.md':2496 'refram':753,1189,1926 'regardless':1012,2454 'regret':619,624,2216 'reinforc':1037 'relationship':288 'remov':875,1178,1288 'repeat':1551 'repetit':1507 'request':1877 'reshap':1591 'resolut':2012,2418 'resolv':466 'resourc':304,899 'respect':171 'respond':1084 'result':1389 'retent':1513 'revers':306,627,1125,1167,2033 'review':1508 'revisit':1860 'right':123,230,432,481,507,1296,2432 'risk':668,1221,1263,2242 'role':1613 'root':729 'rule':675,1436 'run':1068 'rush':464,2010 'safeti':844,1255,1274,2233 'sake':1977 'satisf':706 'save':1881 'say':30,1908 'scale':1766 'scamper':1157 'scenario':813,2194 'schedul':1526,1530 'schell':1478 'second':222,606,2184 'second-ord':221,605,2183 'see':1627 'seek':386,499 'seem':253 'select':119,567,575,989,1639,2289 'self':1036,1040,2507 'self-correct':1039,2506 'self-reinforc':1035 'sentenc':1654 'serious':2209 'serv':136 'session':72,2243,2533 'settl':514 'share':898 'sharpen':16,98,1992 'shift':947,2094 'shock':1133 'shot':1549 'show':2005 'side':1465,1582 'signal':1560 'silent':339 'similar':1175,1416 'sit':2018 'situat':128,250,265,313,573,1394,2055,2284,2322,2457 'skill':26 'skill-thinking-partner' 'skill.md':2527 'skin':697,1779 'slow':472 'small':919,1056,1275 'smart':2050 'solv':18,279,778,1173 'someon':454 'sometim':2430 'sophist':2400 'sound':397,1011 'source-mattnowdev' 'sovereign':352 'space':1506,1668 'spar':71 'speak':1338 'specif':966,2065,2261,2307,2521 'spectacular':1749 'spot':790,1754 'stack':1966 'stake':285 'state':84,345,2525 'stay':1071 'steel':1308,2204 'steelman':2076 'step':261,329,331,565,1629,1719,1816,1839,2337 'stock':1085 'stori':1355 'storytel':1351 'strategi':809,1200,1272 'strength':822 'stress':206,446,1299,1724,2343 'stress-test':445,1723,2342 'strong':2070 'stronger':1131 'strongest':1313,2080,2212 'stuck':233,254,803 'substitut':1158 'succeed':1151 'suffici':2529 'support':1325,1523,2067,2390 'sure':527 'surfac':106,394,1683,1912 'surviv':883 'survivorship':968 'swan':1233,2235 'switch':924 'swot':240,820,2193 'synthes':1689,1818,2272,2296 'synthesi':1825 'system':1027,1118 'systemat':742 'tail':2241 'take':914 'tat':1555 'team':833,2334 'techniqu':1494,2023 'tell':90,2059 'tension':144 'term':1987 'territori':857 'test':207,447,628,783,1215,1725,1783,2047,2344 'theori':745,1540 'thing':473,1832,2138,2439 'think':2,6,21,33,38,47,51,63,76,95,101,124,135,169,185,190,227,334,344,608,1005,1016,1075,1207,1887,1991,1995,2186 'thinking-partn':1 'thorough':2294 'thread':1696 'threat':457,825 'threat-reduc':456 'threshold':1114 'time':290,294,1709,1896,2093 'tip':1109 'tit':1553 'today':296 'togeth':375,1697 'tone':1941 'tool':2028,2365 'toolkit':1907 'topic-agent-skills' 'topic-claude-code' 'topic-critical-thinking' 'topic-cursor' 'topic-decision-making' 'topic-mental-models' 'topic-thinking' 'trace':2189 'tragedi':888 'trait':1432 'trap':2401 'treat':112 'tri':276 'trigger':182,1301 'true':410,728,1198,1741,2041 'truth':140 'tutori':2301 'two':637 'two-way':636 'type':574,2136,2244 'uncap':672 'uncertain':2282 'understand':263,270,281,870,1026,1505 'unexamin':1811 'unhelp':2009 'uniform':2448 'unstuck':1144 'updat':942,2203,2206 'upsid':673,1267,1278 'usag':1625 'use':24,1165,1916,1952,1996,2366,2494 'user':29,62,92,110,252,274,342,354,380,422,460,501,536,583,1636,1869,1876,1905,1918,1939,1980,2015,2252,2258,2279,2302,2325 'valid':387,2330 'valu':1247,1472,1476 'variabl':1021 've':400 'veil':1600 'verifi':564 'version':1314 'via':1283 'viabl':1209 'view':558,1318 'visibl':1106 'vs':690,707,798,977,1268,1527,2223 'walk':1634,2312 'want':502,665,2263,2303,2329 'wasn':1181 'way':634,638 'weak':823,1681,1809 'weapon':2002 'weight':642 'went':1751,2121 'when-to-us':2491 'whenev':27 'whys':248,732 'will':176 'winner':913,975 'winner-take-al':912 'wish':2227 'within':1339 'without':1137,1428,1963,2360 'word':1921,1998 'work':796,1536,1691,2139 'workflow':260,2286 'would':406,556,600,836,953,1153,1186,1365,1422,1466,1603,1775,1784,2043,2057,2393 'wrap':1821 'write':2123 'wrong':361,603,851,1752,2412 'x':35,187,215,404,1180,2391,2396 'y':217,412 'year':300,651,686,1503,2108,2116 'year-old':1502 'yes':159 'yes-machin':158 'zone':1514 'zopa':1458","prices":[{"id":"29603d06-c0dc-436f-948b-cdc10e0df8d4","listingId":"ec9a0796-035d-4f1a-93e6-409d3b76b9b3","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"mattnowdev","category":"thinking-partner","install_from":"skills.sh"},"createdAt":"2026-04-18T22:09:57.129Z"}],"sources":[{"listingId":"ec9a0796-035d-4f1a-93e6-409d3b76b9b3","source":"github","sourceId":"mattnowdev/thinking-partner/thinking-partner","sourceUrl":"https://github.com/mattnowdev/thinking-partner/tree/main/skills/thinking-partner","isPrimary":false,"firstSeenAt":"2026-04-18T22:09:57.129Z","lastSeenAt":"2026-05-02T12:54:46.909Z"}],"details":{"listingId":"ec9a0796-035d-4f1a-93e6-409d3b76b9b3","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"mattnowdev","slug":"thinking-partner","github":{"repo":"mattnowdev/thinking-partner","stars":134,"topics":["agent-skills","claude-code","critical-thinking","cursor","decision-making","mental-models","thinking"],"license":"mit","html_url":"https://github.com/mattnowdev/thinking-partner","pushed_at":"2026-03-31T17:19:54Z","description":"Thinking partner skill for AI agents — 150+ mental models, orientation detection, cognitive operations. Works with Claude Code, Cursor, Windsurf, Cline, GitHub Copilot.","skill_md_sha":"d251587628994314c0553979e205f308c49b42e4","skill_md_path":"skills/thinking-partner/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/mattnowdev/thinking-partner/tree/main/skills/thinking-partner"},"layout":"multi","source":"github","category":"thinking-partner","frontmatter":{"name":"thinking-partner","description":"A deterministic thinking partner that challenges assumptions and applies mental models to sharpen decisions, solve problems, and think more clearly. Use this skill whenever a user says \"help me think through X\", \"challenge my thinking\", \"what am I missing\", \"apply mental models to this\", \"play devil's advocate\", \"stress test this idea\", \"poke holes in my plan\", \"help me decide between X and Y\", \"what are the second-order effects\", \"I'm stuck on a decision\", names any specific model (SWOT, first principles, inversion, pre-mortem, etc.), or asks for structured reasoning on any ambiguous, high-stakes, or complex problem. Also trigger when the user seems uncertain, is rationalizing, or is asking \"am I thinking about this right?\" Even casual phrases like \"what do you think about...\" on non-trivial topics should trigger this skill."},"skills_sh_url":"https://skills.sh/mattnowdev/thinking-partner/thinking-partner"},"updatedAt":"2026-05-02T12:54:46.909Z"}}