{"id":"7216d42e-dd22-4aae-a58b-fc4c62ba29fa","shortId":"4Wuq9Z","kind":"skill","title":"axiom","tagline":"First-principles assumption auditor. Classifies each hidden assumption (fact / convention / belief / interest-driven), ranks by fragility × impact, and rebuilds conclusions from verified premises. Bilingual: auto-detects Chinese or English.","description":"# Axiom — First-Principles Assumption Auditor / 第一性原理拆解器\n\nStrip any question down to its irreducible truths, then rebuild from there.\nThis is not framework fill-in-the-blank — it is assumption prosecution.\n\n把任何问题强制剥离到\"不可再拆的最小真相单元\"，再从那里重建。\n不是框架填空，是假设审判。\n\n## Language Rule / 语言规则\n\n> **Auto-detect the user's input language and respond entirely in that language throughout the session.**\n> If the user writes in Chinese, all phases, labels, and outputs must be in Chinese.\n> If the user writes in English, all phases, labels, and outputs must be in English.\n> Do NOT mix languages unless the user explicitly switches.\n\n---\n\n## When to Use This Skill / 何时使用\n\n- A major life or career decision is on the table (quitting a job, starting a company, buying a house)\n- You want to stress-test a business direction or product hypothesis\n- You suspect a belief you hold might be wrong but can't articulate why\n- You need to cut through complexity and find the real bottleneck\n- Someone asks you to \"think from first principles\" or \"break it down\"\n\n**Trigger phrases (中文):** 第一性原理 / 帮我想清楚 / 拆解一下 / 从底层分析 / 这个假设对吗 / 我在做一个决定 / 从根本上分析 / 底层逻辑 / 元问题 / 重新思考 / 有没有想错 / axiom\n\n**Trigger phrases (English):** first principles / break it down / question my assumptions / think from scratch / challenge this belief / audit my reasoning / what am I missing / help me think clearly / axiom\n\n---\n\n## What This Skill Does / 核心能力\n\n1. **Problem Reframing / 问题澄清** — Confirms the question itself is correctly defined before touching assumptions\n2. **Assumption Mining / 假设挖掘** — Systematically surfaces 8-12 hidden assumptions across three depth layers\n3. **Assumption Classification / 假设分类** — Force-labels every assumption into one of four types with different challenge strategies\n4. **Risk Ranking / 优先级排序** — Scores each assumption on Fragility × Impact and outputs a \"Most Dangerous Top 3\"\n5. **Reconstruction / 重建** — Rebuilds conclusions from verified premises only, explicitly comparing \"before vs after\" cognitive shift\n\n---\n\n## The 5-Phase Process / 拆解流程 — 5 阶段\n\n### Phase 1: Problem Reframing — What are you REALLY trying to solve?\n\n**阶段1：问题澄清 — 你真正想解决的是什么？**\n\nDo NOT start decomposing assumptions yet. First confirm the problem itself is correctly defined.\n\nMany people ask \"Should I quit my job?\" when the real question is \"Why can't I grow in my current role?\" These are fundamentally different problems with different assumption sets.\n\n**Ask:**\n- Who defined this problem? You, someone else's expectations, or a social narrative?\n- Is this the root problem, or a symptom of something deeper?\n- Restate the core question in one sentence.\n\n**Output:** A single reframed core question, presented to the user for confirmation before proceeding.\n\n> 先不拆假设，先确认问题本身没有被误定义。\n> 很多人问\"我该不该换工作\"，但真正的问题是\"我在当前工作里能不能成长\"。\n> Axiom 先问：这个问题是谁定义的？是你自己、他人期待、还是社会叙事？\n> **输出：一句重新表述的核心问题，供用户确认。**\n\n---\n\n### Phase 2: Assumption Mining — What are you believing without proof?\n\n**阶段2：假设挖掘 — 你在相信什么？**\n\nSystematically mine hidden assumptions in three layers:\n\n| Layer | Description | Example |\n|-------|-------------|---------|\n| **Surface** | Obvious, often stated aloud | \"I need more money\" |\n| **Middle** | Industry conventions, common wisdom | \"A degree is required for good jobs\" |\n| **Deep** | Never questioned, feels like gravity | \"Success means financial independence\" |\n\n**Goal:** Find 8-12 assumptions. The more concrete, the better. Reject vague statements like \"I think this is right\" — force specificity.\n\n**When detecting the user's scenario type**, reference the appropriate scenario checklist from `references/scenarios.md` to ensure thorough mining.\n\n> 系统性挖掘隐含假设，分三层：\n> - **表层假设**（显而易见的）\n> - **中层假设**（行业惯例或常识）\n> - **深层假设**（你从未质疑过、觉得\"天经地义\"的信念）\n>\n> 深层假设才是最有价值的。\n> **目标：找到 8-12 个假设，越具体越好，不接受模糊的\"我以为这样更好\"。**\n\n---\n\n### Phase 3: Assumption Classification — What is the nature of this belief?\n\n**阶段3：假设分类 — 这个信念的本质是什么？**\n\nLabel every assumption with one of four types. Each type has a fundamentally different challenge strategy:\n\n| Type | Label | Definition | Challenge Strategy |\n|------|-------|------------|--------------------|\n| 🔵 | **Physical Fact / 物理事实** | Laws of nature, mathematical truths. Cannot be changed. | Accept it. Do not waste energy questioning gravity. |\n| 🟡 | **Historical Convention / 历史惯例** | Once valid, widely practiced. | Check if the environment has changed. What was true in 2010 may not be true now. |\n| 🔴 | **Subjective Belief / 主观信念** | Personal experience projected as universal truth. | Who told you this? Have you personally verified it? Seek counter-evidence. |\n| ⚫ | **Interest-Driven / 利益驱动** | Someone benefits from you believing this. | Trace the incentive chain. Who profits from this narrative? |\n\n**The classification itself is the insight.** Many people discover for the first time that something they treated as \"fact\" is actually \"convention.\"\n\nFor detailed identification methods, examples, and edge cases, reference `references/assumption-types.md`.\n\n> 对每个假设打标签。不同性质的假设有不同的质疑方式，处理策略也不同。\n> **分类本身就是洞见** — 很多人第一次发现某个\"事实\"其实是\"惯例\"。\n\n---\n\n### Phase 4: Risk Ranking — Which assumptions to investigate first?\n\n**阶段4：优先级排序 — 先查哪个？**\n\nScore every assumption on two dimensions:\n\n**Fragility / 脆弱性 (1-5):** How easily can this assumption be disproven?\n- 1 = Nearly impossible to overturn (e.g., physical laws)\n- 5 = Extremely easy to disprove (e.g., untested market intuition, personal feeling)\n\n**Impact / 影响力 (1-5):** If this assumption is wrong, how much does your conclusion collapse?\n- 1 = Barely affects the final conclusion\n- 5 = Foundational pillar — if wrong, everything falls apart\n\n```\nRisk Score = Fragility × Impact\n\nOutput: Top 3 assumptions with highest risk scores, as priority investigation targets.\nEach Top 3 entry MUST include a specific, actionable verification question.\n```\n\n> 给每个假设打两个维度的分：\n> - **脆弱性**（1-5，这个假设有多容易被证伪）\n> - **影响力**（1-5，如果它是错的，你的结论会垮多少）\n>\n> 两者相乘得到\"危险值\"，输出危险值最高的 **Top 3** 假设作为优先调查对象。\n> **这是现有竞品全部缺失的功能。**\n\n---\n\n### Phase 5: Reconstruction — Rebuild from verified ground truth\n\n**阶段5：重建 — 从真相出发，你会怎么做？**\n\nKeep ONLY the assumptions that survived scrutiny. Rebuild the conclusion from scratch using only verified premises.\n\n**Critical requirements:**\n- Explicitly compare \"Original Thinking\" vs \"Rebuilt Thinking\" side by side\n- If the rebuilt conclusion is identical to the original, explain WHY — the analysis must demonstrate that either a genuine shift occurred, or provide specific reasons why the original reasoning was already sound\n- Highlight the cognitive shift so the user can see what changed and why\n\n**If the user doesn't have time for a full reconstruction:**\nOutput the single most important thing to verify: \"你最该验证的一件事\" / \"The one thing you should verify first.\"\n\n> 只保留被验证的真实前提，从零重建结论。\n> **重要的是：新结论必须和原来的直觉有所不同** — 如果完全一样，说明拆解不够深。\n> Axiom 会主动对比\"原来的想法\"和\"重建后的想法\"，让用户看到认知位移。\n>\n> 如果用户没有时间做完整重建，至少输出\"你最该验证的一件事\"。\n\n---\n\n## Anti-Sycophancy Rules / 反谄媚核心规则\n\nThese rules are **hard constraints** — they override all other behavioral tendencies. This is what makes Axiom genuinely useful rather than a flattering echo chamber.\n\n| Rule | Description |\n|------|-------------|\n| 🚫 **No agreement** | Do NOT agree with the user's original conclusion during the decomposition phases, even if they insist repeatedly. |\n| 🚫 **No flattery openers** | Do NOT start with \"That's a great question\" or any similar validating phrase. Get straight to work. |\n| 🚫 **No identical reconstruction** | The Phase 5 reconstruction MUST NOT produce an identical conclusion to the original without explicitly explaining why no shift occurred, with specific evidence. |\n| ✅ **At least one uncomfortable truth** | Phase 4 MUST output at least one assumption the user probably doesn't want to hear challenged. |\n| ✅ **Devil's advocate persistence** | If the user rejects a classification or pushback, hold firm like a devil's advocate. Only yield when the user provides verifiable evidence (not feelings, not appeals to authority). |\n\n> 这是让 axiom 真正有用的关键。Claude 天生倾向于认同用户，必须写入明确规则对抗这个倾向：\n> - 🚫 禁止在拆解阶段认同用户的原始结论\n> - 🚫 禁止用\"这是个好问题\"或类似话语开头\n> - 🚫 禁止重建阶段给出和原始想法完全一致的结论\n> - ✅ 必须在阶段4输出至少一个用户可能不喜欢听的\"危险假设\"\n> - ✅ 必须像 devil's advocate 一样坚持，直到用户提供真实证据\n\n---\n\n## Scenario Reference / 场景引用\n\nWhen the user's question matches one of these scenario types, reference the corresponding assumption mining checklist from `references/scenarios.md`:\n\n| # | 中文场景 | English Scenario |\n|---|---------|-----------------|\n| 1 | 职业决策（换工作、创业方向） | Career Decisions (job change, career pivot) |\n| 2 | 产品方向验证（创业、新功能） | Business & Product Validation |\n| 3 | 消费选择（买房、投资、重大消费） | Financial & Life Decisions |\n| 4 | 认知信念质疑（人生观、方法论） | Belief & Worldview Audit |\n\nEach scenario contains 10-15 \"high-frequency hidden assumptions\" specific to that domain and culture, plus tailored probing questions.\n\n---\n\n## Quick Output Mode / 快捷输出\n\nIf the user explicitly requests a quick analysis or is short on time:\n- Skip the full 5-phase walkthrough\n- Output directly: the **Top 3 most dangerous assumptions** with risk scores and one actionable verification question each\n- End with: \"你最该验证的一件事是…\" / \"The single most important thing to verify is…\"\n\n---\n\n## Example / 示例\n\n### Chinese Example / 中文示例\nSee `examples/walkthrough-zh.md` for a complete 5-phase walkthrough using: \"我觉得我应该辞职去创业\"\n\n### English Example\nSee `examples/walkthrough-en.md` for a complete 5-phase walkthrough using: \"I'm thinking about dropping out of my CS degree to join a startup\"\n\n---\n\n## Tips / 使用建议\n\n- The deeper the assumption layer you can reach, the more valuable the analysis\n- Don't accept \"I just feel it\" as evidence — push for specifics\n- The most powerful insight often comes from reclassifying what you thought was a \"fact\" as a \"convention\"\n- Use the Risk Matrix to focus your limited verification energy on what matters most\n- If reconstruction matches the original conclusion exactly, the decomposition wasn't deep enough\n\n---\n\n## Common Use Cases / 常见场景\n\n- Major career decisions (quit, pivot, negotiate)\n- Startup idea validation before investing time/money\n- Challenging \"obvious\" beliefs that might be holding you back\n- Pre-mortem analysis on important life choices\n- Auditing investment or financial decisions\n- Breaking through analysis paralysis by identifying what actually matters\n\n---\n\n## Related Resources / 参考文件\n\n- `references/scenarios.md` — 8 scenario-specific assumption mining checklists (4 Chinese + 4 English)\n- `references/assumption-types.md` — Detailed handbook for the 4-type classification system\n- `examples/walkthrough-zh.md` — Complete Chinese example (辞职创业)\n- `examples/walkthrough-en.md` — Complete English example (dropping out for startup)\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.","tags":["axiom","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows","antigravity-skills"],"capabilities":["skill","source-sickn33","skill-axiom","topic-agent-skills","topic-agentic-skills","topic-ai-agent-skills","topic-ai-agents","topic-ai-coding","topic-ai-workflows","topic-antigravity","topic-antigravity-skills","topic-claude-code","topic-claude-code-skills","topic-codex-cli","topic-codex-skills"],"categories":["antigravity-awesome-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/sickn33/antigravity-awesome-skills/axiom","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add sickn33/antigravity-awesome-skills","source_repo":"https://github.com/sickn33/antigravity-awesome-skills","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 34964 github stars · SKILL.md body (10,955 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":"2026-04-25T00:50:30.180Z","embedding":null,"createdAt":"2026-04-18T21:31:47.209Z","updatedAt":"2026-04-25T00:50:30.180Z","lastSeenAt":"2026-04-25T00:50:30.180Z","tsv":"'-12':274,516,567 '-15':1211 '-5':751,781,837,841 '1':253,340,750,759,780,793,836,840,1175 '10':1210 '2':267,460,1185 '2010':643 '3':281,315,573,813,825,848,1192,1254 '4':299,731,1082,1200,1447,1449,1456 '5':316,333,337,767,799,852,1055,1247,1288,1300 '8':273,515,566,1440 'accept':618,1335 'across':277 'action':831,1263 'actual':710,1434 'advoc':1100,1116,1147 'affect':795 'agre':1013 'agreement':1010 'aloud':486 'alreadi':921 'analysi':903,1238,1332,1417,1429 'anti':979 'anti-sycoph':978 'apart':806 'appeal':1128 'appropri':543 'articul':179 'ask':193,369,398,1506 'assumpt':5,10,38,64,229,266,268,276,282,289,305,357,396,461,475,517,574,588,735,744,756,784,814,866,1088,1167,1216,1257,1323,1444 'audit':236,1206,1422 'auditor':6,39 'author':1130 'auto':29,75 'auto-detect':28,74 'axiom':1,34,218,247,450,969,998,1132 'back':1413 'bare':794 'behavior':992 'belief':13,170,235,582,650,1204,1407 'believ':466,679 'benefit':676 'better':522 'bilingu':27 'blank':61 'bottleneck':191 'boundari':1514 'break':201,224,1427 'busi':162,1189 'buy':152 'cannot':615 'career':140,1179,1183,1394 'case':719,1391 'chain':684 'challeng':233,297,600,605,1097,1405 'chamber':1006 'chang':617,638,933,1182 'check':633 'checklist':545,1169,1446 'chines':31,96,105,1280,1448,1462 'choic':1421 'clarif':1508 'classif':283,575,691,1107,1458 'classifi':7 'claud':1134 'clear':246,1481 'cognit':330,925 'collaps':792 'come':1350 'common':494,1389 'compani':151 'compar':326,882 'complet':1287,1299,1461,1466 'complex':186 'conclus':23,320,791,798,872,894,1019,1062,1381 'concret':520 'confirm':257,360,441 'constraint':987 'contain':1209 'convent':12,493,627,711,1361 'core':425,434 'correct':262,365 'correspond':1166 'counter':669 'counter-evid':668 'criteria':1517 'critic':879 'cs':1312 'cultur':1222 'current':387 'cut':184 'danger':313,1256 'decis':141,1180,1199,1395,1426 'decompos':356 'decomposit':1022,1384 'deep':503,1387 'deeper':422,1321 'defin':263,366,400 'definit':604 'degre':497,1313 'demonstr':905 'depth':279 'describ':1485 'descript':480,1008 'detail':713,1452 'detect':30,76,535 'devil':1098,1114,1145 'differ':296,392,395,599 'dimens':747 'direct':163,1251 'discov':698 'disprov':771 'disproven':758 'doesn':939,1092 'domain':1220 'driven':16,673 'drop':1308,1469 'e.g':764,772 'easi':769 'easili':753 'echo':1005 'edg':718 'either':907 'els':405 'end':1267 'energi':623,1371 'english':33,111,120,221,1173,1293,1450,1467 'enough':1388 'ensur':549 'entir':84 'entri':826 'environ':636,1497 'environment-specif':1496 'even':1024 'everi':288,587,743 'everyth':804 'evid':670,1075,1124,1341 'exact':1382 'exampl':481,716,1278,1281,1294,1463,1468 'examples/walkthrough-en.md':1296,1465 'examples/walkthrough-zh.md':1284,1460 'expect':407 'experi':653 'expert':1502 'explain':900,1068 'explicit':128,325,881,1067,1234 'extrem':768 'fact':11,608,708,1358 'fall':805 'feel':506,777,1126,1338 'fill':58 'fill-in-the-blank':57 'final':797 'financi':511,1197,1425 'find':188,514 'firm':1111 'first':3,36,198,222,359,701,738,962 'first-principl':2,35 'flatter':1004 'flatteri':1030 'focus':1367 'forc':286,532 'force-label':285 'foundat':800 'four':293,592 'fragil':19,307,748,809 'framework':56 'frequenc':1214 'full':945,1246 'fundament':391,598 'genuin':909,999 'get':1046 'goal':513 'good':501 'graviti':508,625 'great':1039 'ground':857 'grow':384 'handbook':1453 'hard':986 'hear':1096 'help':243 'hidden':9,275,474,1215 'high':1213 'high-frequ':1212 'highest':816 'highlight':923 'histor':626 'hold':172,1110,1411 'hous':154 'hypothesi':166 'idea':1400 'ident':896,1051,1061 'identif':714 'identifi':1432 'impact':20,308,778,810 'import':951,1273,1419 'imposs':761 'incent':683 'includ':828 'independ':512 'industri':492 'input':80,1511 'insight':695,1348 'insist':1027 'interest':15,672 'interest-driven':14,671 'intuit':775 'invest':1403,1423 'investig':737,821 'irreduc':47 'job':148,374,502,1181 'join':1315 'keep':863 'label':99,114,287,586,603 'languag':71,81,87,124 'law':610,766 'layer':280,478,479,1324 'least':1077,1086 'life':138,1198,1420 'like':507,526,1112 'limit':1369,1473 'm':1305 'major':137,1393 'make':997 'mani':367,696 'market':774 'match':1158,1378,1482 'mathemat':613 'matrix':1365 'matter':1374,1435 'may':644 'mean':510 'method':715 'middl':491 'might':173,1409 'mine':269,462,473,551,1168,1445 'miss':242,1519 'mix':123 'mode':1229 'money':490 'mortem':1416 'much':788 'must':102,117,827,904,1057,1083 'narrat':411,689 'natur':579,612 'near':760 'need':182,488 'negoti':1398 'never':504 'obvious':483,1406 'occur':911,1072 'often':484,1349 'one':291,428,590,957,1078,1087,1159,1262 'open':1031 'origin':883,899,918,1018,1065,1380 'output':101,116,310,430,811,947,1084,1228,1250,1491 'overrid':989 'overturn':763 'paralysi':1430 'peopl':368,697 'permiss':1512 'persist':1101 'person':652,664,776 'phase':98,113,334,339,459,572,730,851,1023,1054,1081,1248,1289,1301 'phrase':205,220,1045 'physic':607,765 'pillar':801 'pivot':1184,1397 'plus':1223 'power':1347 'practic':632 'pre':1415 'pre-mortem':1414 'premis':26,323,878 'present':436 'principl':4,37,199,223 'prioriti':820 'probabl':1091 'probe':1225 'problem':254,341,362,393,402,416 'proceed':443 'process':335 'produc':1059 'product':165,1190 'profit':686 'project':654 'proof':468 'prosecut':65 'provid':913,1122 'push':1342 'pushback':1109 'question':43,227,259,378,426,435,505,624,833,1040,1157,1226,1265 'quick':1227,1237 'quit':146,372,1396 'rank':17,301,733 'rather':1001 'reach':1327 'real':190,377 'realli':346 'reason':238,915,919 'rebuild':22,50,319,854,870 'rebuilt':886,893 'reclassifi':1352 'reconstruct':317,853,946,1052,1056,1377 'refer':541,720,1151,1164 'references/assumption-types.md':721,1451 'references/scenarios.md':547,1171,1439 'refram':255,342,433 'reject':523,1105 'relat':1436 'repeat':1028 'request':1235 'requir':499,880,1510 'resourc':1437 'respond':83 'restat':423 'review':1503 'right':531 'risk':300,732,807,817,1259,1364 'role':388 'root':415 'rule':72,981,984,1007 'safeti':1513 'scenario':539,544,1150,1162,1174,1208,1442 'scenario-specif':1441 'scope':1484 'score':303,742,808,818,1260 'scratch':232,874 'scrutini':869 'see':931,1283,1295 'seek':667 'sentenc':429 'session':90 'set':397 'shift':331,910,926,1071 'short':1241 'side':888,890 'similar':1043 'singl':432,949,1271 'skill':134,250,1476 'skill-axiom' 'skip':1244 'social':410 'solv':349 'someon':192,404,675 'someth':421,704 'sound':922 'source-sickn33' 'specif':533,830,914,1074,1217,1344,1443,1498 'start':149,355,1034 'startup':1317,1399,1472 'state':485 'statement':525 'stop':1504 'straight':1047 'strategi':298,601,606 'stress':159 'stress-test':158 'strip':41 'subject':649 'substitut':1494 'success':509,1516 'surfac':272,482 'surviv':868 'suspect':168 'switch':129 'sycoph':980 'symptom':419 'system':1459 'systemat':271,472 'tabl':145 'tailor':1224 'target':822 'task':1480 'tendenc':993 'test':160,1500 'thing':952,958,1274 'think':196,230,245,528,884,887,1306 'thorough':550 'thought':1355 'three':278,477 'throughout':88 'time':702,942,1243 'time/money':1404 'tip':1318 'told':659 'top':314,812,824,847,1253 'topic-agent-skills' 'topic-agentic-skills' 'topic-ai-agent-skills' 'topic-ai-agents' 'topic-ai-coding' 'topic-ai-workflows' 'topic-antigravity' 'topic-antigravity-skills' 'topic-claude-code' 'topic-claude-code-skills' 'topic-codex-cli' 'topic-codex-skills' 'touch':265 'trace':681 'treat':706,1489 'tri':347 'trigger':204,219 'true':641,647 'truth':48,614,657,858,1080 'two':746 'type':294,540,593,595,602,1163,1457 'uncomfort':1079 'univers':656 'unless':125 'untest':773 'use':132,875,1000,1291,1303,1362,1390,1474 'user':78,93,108,127,439,537,929,938,1016,1090,1104,1121,1155,1233 'vagu':524 'valid':630,1044,1191,1401,1499 'valuabl':1330 'verif':832,1264,1370 'verifi':25,322,665,856,877,954,961,1123,1276 'vs':328,885 'walkthrough':1249,1290,1302 'want':156,1094 'wasn':1385 'wast':622 'wide':631 'wisdom':495 'without':467,1066 'work':1049 'worldview':1205 'write':94,109 'wrong':175,786,803 'yet':358 'yield':1118 '一句重新表述的核心问题':457 '一样坚持':1148 '不可再拆的最小真相单元':67 '不同性质的假设有不同的质疑方式':723 '不接受模糊的':570 '不是框架填空':69 '两者相乘得到':844 '个假设':568 '中层假设':556 '中文':206 '中文场景':1172 '中文示例':1282 '主观信念':651 '买房':1194 '事实':727 '产品方向验证':1186 '人生观':1202 '从底层分析':210 '从根本上分析':213 '从真相出发':861 '从零重建结论':964 '他人期待':454 '优先级排序':302,740 '会主动对比':970 '但真正的问题是':448 '何时使用':135 '你从未质疑过':559 '你会怎么做':862 '你在相信什么':471 '你最该验证的一件事':955,977 '你最该验证的一件事是':1269 '你的结论会垮多少':843 '你真正想解决的是什么':352 '使用建议':1319 '供用户确认':458 '假设作为优先调查对象':849 '假设分类':284,584 '假设挖掘':270,470 '元问题':215 '先不拆假设':444 '先查哪个':741 '先确认问题本身没有被误定义':445 '先问':451 '其实是':728 '再从那里重建':68 '分三层':553 '分类本身就是洞见':725 '创业':1187 '创业方向':1178 '利益驱动':674 '危险值':845 '危险假设':1143 '历史惯例':628 '原来的想法':971 '参考文件':1438 '反谄媚核心规则':982 '只保留被验证的真实前提':963 '和':972 '场景引用':1152 '处理策略也不同':724 '天生倾向于认同用户':1135 '天经地义':561 '如果它是错的':842 '如果完全一样':967 '如果用户没有时间做完整重建':975 '对每个假设打标签':722 '帮我想清楚':208 '常见场景':1392 '底层逻辑':214 '影响力':779,839 '很多人第一次发现某个':726 '很多人问':446 '必须像':1144 '必须写入明确规则对抗这个倾向':1136 '必须在阶段4输出至少一个用户可能不喜欢听的':1142 '快捷输出':1230 '惯例':729 '我以为这样更好':571 '我在做一个决定':212 '我在当前工作里能不能成长':449 '我觉得我应该辞职去创业':1292 '我该不该换工作':447 '或类似话语开头':1140 '找到':565 '把任何问题强制剥离到':66 '投资':1195 '拆解一下':209 '拆解流程':336 '换工作':1177 '新功能':1188 '新结论必须和原来的直觉有所不同':966 '方法论':1203 '是你自己':453 '是假设审判':70 '显而易见的':555 '有没有想错':217 '核心能力':252 '消费选择':1193 '深层假设':558 '深层假设才是最有价值的':563 '物理事实':609 '的信念':562 '目标':564 '直到用户提供真实证据':1149 '真正有用的关键':1133 '示例':1279 '禁止在拆解阶段认同用户的原始结论':1137 '禁止用':1138 '禁止重建阶段给出和原始想法完全一致的结论':1141 '第一性原理':207 '第一性原理拆解器':40 '系统性挖掘隐含假设':552 '给每个假设打两个维度的分':834 '职业决策':1176 '脆弱性':749,835 '至少输出':976 '行业惯例或常识':557 '表层假设':554 '觉得':560 '认知信念质疑':1201 '让用户看到认知位移':974 '语言规则':73 '说明拆解不够深':968 '越具体越好':569 '输出':456 '输出危险值最高的':846 '辞职创业':1464 '还是社会叙事':455 '这个信念的本质是什么':585 '这个假设对吗':211 '这个假设有多容易被证伪':838 '这个问题是谁定义的':452 '这是个好问题':1139 '这是现有竞品全部缺失的功能':850 '这是让':1131 '重大消费':1196 '重建':318,860 '重建后的想法':973 '重新思考':216 '重要的是':965 '问题澄清':256,351 '阶段':338 '阶段1':350 '阶段2':469 '阶段3':583 '阶段4':739 '阶段5':859","prices":[{"id":"e043469c-8e83-480b-92e3-cd8ae6e6e16e","listingId":"7216d42e-dd22-4aae-a58b-fc4c62ba29fa","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"sickn33","category":"antigravity-awesome-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T21:31:47.209Z"}],"sources":[{"listingId":"7216d42e-dd22-4aae-a58b-fc4c62ba29fa","source":"github","sourceId":"sickn33/antigravity-awesome-skills/axiom","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/axiom","isPrimary":false,"firstSeenAt":"2026-04-18T21:31:47.209Z","lastSeenAt":"2026-04-25T00:50:30.180Z"}],"details":{"listingId":"7216d42e-dd22-4aae-a58b-fc4c62ba29fa","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"axiom","github":{"repo":"sickn33/antigravity-awesome-skills","stars":34964,"topics":["agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows","antigravity","antigravity-skills","claude-code","claude-code-skills","codex-cli","codex-skills","cursor","cursor-skills","developer-tools","gemini-cli","gemini-skills","kiro","mcp","skill-library"],"license":"mit","html_url":"https://github.com/sickn33/antigravity-awesome-skills","pushed_at":"2026-04-24T06:41:17Z","description":"Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.","skill_md_sha":"caaf89a0c9384363f24cb7d60a75dd51eb4e3044","skill_md_path":"skills/axiom/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/axiom"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"axiom","description":"First-principles assumption auditor. Classifies each hidden assumption (fact / convention / belief / interest-driven), ranks by fragility × impact, and rebuilds conclusions from verified premises. Bilingual: auto-detects Chinese or English."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/axiom"},"updatedAt":"2026-04-25T00:50:30.180Z"}}