` tags)\n- Preserve heading context (which H2/H3 section each paragraph belongs to)\n- Number each paragraph for reference\n- Count total words, sentences, and paragraphs\n\nPrint a brief summary:\n\n```\nContent Analysis: {title or domain}\n Words: {count}\n Paragraphs: {count}\n Headings: {count}\n Scanning for citability issues...\n```\n\n---\n\n## Phase 2: Paragraph-Level Diagnosis\n\nScan every paragraph for these 6 issue categories:\n\n### 2.1 Hedge Language\n\nHedge words reduce AI citation probability because AI engines prefer authoritative, confident statements.\n\n**Hedge word categories:**\n\n| Category | Examples | Severity |\n|----------|----------|----------|\n| Uncertainty | maybe, perhaps, possibly, might, could | High |\n| Qualification | somewhat, relatively, fairly, rather, quite | Medium |\n| Approximation | about, around, approximately, roughly, nearly | Medium |\n| Distancing | seems, appears, tends to, suggests, likely | High |\n| Generalization | generally, usually, often, sometimes, typically | Medium |\n| Weakening | a bit, sort of, kind of, in some ways | High |\n\n**Metrics:**\n- **Hedge Density** = (hedge word count / total word count) * 100\n- Target: < 0.5% for high-citability content\n- Critical: > 2.0% indicates systematically weak language\n\n### 2.2 Missing Data Support\n\nParagraphs that make claims without evidence:\n- Statements with \"better\", \"faster\", \"more\" without numbers\n- Comparisons without baselines\n- Claims about impact without metrics\n- Trends stated without timeframes or sources\n\n### 2.3 Missing Definitions\n\nTechnical terms or jargon used without explanation:\n- Acronyms not expanded at first use\n- Industry terms assumed known\n- Concepts referenced without context\n\n### 2.4 Poor Self-Containment\n\nParagraphs that cannot stand alone:\n- Starts with \"This\", \"It\", \"They\" without clear antecedent\n- Requires reading previous paragraphs to understand\n- References \"as mentioned above\" or \"as we discussed\"\n- Depends on surrounding context for meaning\n\n### 2.5 Structural Issues\n\n- Paragraphs longer than 4 sentences (AI prefers 2-3 sentence blocks)\n- Content that should be a list or table but is written as prose\n- Wall of text without visual breaks\n- Missing topic sentence (first sentence doesn't summarize the paragraph)\n\n### 2.6 Weak Answer Blocks\n\nContent that could serve as a direct AI answer but doesn't:\n- Questions in headings without direct answers in the first sentence\n- Definition opportunities missed (\"{Term} is...\" pattern absent)\n- FAQ content buried in prose instead of Q&A format\n\n### Diagnosis Output\n\nFor each paragraph with issues, record:\n\n```\nParagraph {n} (line {x}): {first 10 words}...\n Issues:\n - [HEDGE] 3 hedge words (density: 2.1%)\n - [DATA] Claim without metrics: \"significantly improves...\"\n - [SELF] Starts with \"This\" — unclear antecedent\n Severity: HIGH\n```\n\n---\n\n## Phase 3: Rewrite\n\nFor each paragraph with issues, generate a rewrite following these rules:\n\n### 3.1 Rewrite Principles\n\n1. **Preserve original meaning** — Never change what the author is saying, only how they say it\n2. **Replace hedge with certainty** — \"might help\" → \"reduces costs by X%\"\n3. **Add data placeholders** — If real data is unknown, use `[TODO: add specific metric]`\n4. **Front-load the answer** — Put the key claim in the first sentence\n5. **Make self-contained** — Each paragraph should be quotable in isolation\n6. **Keep it concise** — 2-3 sentences per paragraph, maximum 4\n\n### 3.2 Rewrite Format\n\nFor each rewritten paragraph:\n\n```markdown\n### Paragraph {n} (line {x})\n\n**Issues**: {comma-separated issue list}\n\n**Before**:\n> {Original paragraph text}\n\n**After**:\n> {Rewritten paragraph text}\n\n**Changes**:\n- {What was changed and why}\n- {What was changed and why}\n\n**Platform impact**: {Which AI platform benefits most from this rewrite and why}\n```\n\n### 3.3 AI Platform Citation Preferences\n\nDifferent AI platforms have different citation biases. When generating rewrites, tag each rewrite with the platform that benefits most:\n\n| Platform | Favors | Rewrite Implication |\n|----------|--------|-------------------|\n| **ChatGPT** | Authority, named sources, expert quotes | Rewrites adding expert attribution or named citations → tag \"ChatGPT\" |\n| **Perplexity** | Freshness, data recency, community signals | Rewrites adding dates, \"as of [year]\", recent statistics → tag \"Perplexity\" |\n| **Gemini** | Brand-site content, structured data context | Rewrites improving brand name consistency and self-containment → tag \"Gemini\" |\n| **Google AI Overviews** | Structured answers, tables, lists, FAQ patterns | Rewrites converting prose to tables/lists or adding Q&A format → tag \"Google AIO\" |\n| **Claude** | Primary sources, original data, cited statistics | Rewrites adding first-party data or specific research citations → tag \"Claude\" |\n\nWhen a rewrite benefits multiple platforms, list the primary one. Example:\n\n```\n**Platform impact**: Perplexity (added 2025 data with source — strong freshness signal)\n```\n\n### 3.4 Rewrite Patterns\n\n**Hedge → Confident:**\n- \"might help\" → \"helps\" or \"reduces X by Y%\"\n- \"seems to indicate\" → \"indicates\" or \"shows that\"\n- \"could potentially improve\" → \"improves\"\n- \"is generally considered\" → \"is\"\n- \"in some cases\" → \"[specific condition]\"\n\n**Vague → Specific:**\n- \"significantly improves\" → \"improves by 34%\"\n- \"many customers\" → \"2,500+ customers\" or \"[TODO: customer count]\"\n- \"recently\" → \"in Q1 2026\" or \"[TODO: specific date]\"\n- \"industry-leading\" → \"[TODO: specific benchmark or ranking]\"\n\n**Dependent → Self-Contained:**\n- \"This helps...\" → \"{Product Name} helps...\"\n- \"It works by...\" → \"{Feature Name} works by...\"\n- \"As mentioned above...\" → Remove, restate the key fact\n\n**Prose → Structure:**\n- Lists of 3+ items → Bullet list or table\n- Comparisons → Table with columns\n- Sequential steps → Numbered list\n- Features with details → Table (Feature | Description | Benefit)\n\n### 3.5 Skip Rules\n\nDo NOT rewrite paragraphs that:\n- Already score well on all dimensions\n- Are legal disclaimers or regulatory text\n- Are direct quotes from named sources\n- Are code blocks or technical specifications\n\n---\n\n## Phase 4: Output\n\n### 4.1 Generate Fix File\n\nCreate a file named `content-fix-{domain}-{YYYY-MM-DD}.md` (or `content-fix-{YYYY-MM-DD}.md` if input was pasted text).\n\nStructure:\n\n```markdown\n# Content Citability Fix: {title}\n\n**Source**: {url or \"pasted text\"}\n**Date**: {YYYY-MM-DD}\n**Paragraphs analyzed**: {total}\n**Issues found**: {count}\n**Paragraphs rewritten**: {count}\n\n## Citability Score\n\nThe Overall Citability score uses a simplified version of the geo-audit Content Citability dimension (see `../geo-audit/references/scoring-guide.md` for the full rubric). Each metric maps to a sub-dimension:\n\n| Metric | Max Points | Scoring Basis | Before | After (est.) |\n|--------|-----------|---------------|--------|-------------|\n| Hedge Density | 20 | < 0.5% = 20, 0.5-1% = 15, 1-2% = 10, > 2% = 5 | {x} | {y} |\n| Data-Supported Claims | 20 | % of claim paragraphs with quantitative evidence | {x} | {y} |\n| Self-Contained Paragraphs | 20 | % of paragraphs understandable in isolation | {x} | {y} |\n| Structural Clarity | 15 | Avg 2-4 sentences/para = 15, >6 = 5; lists/tables used = +bonus | {x} | {y} |\n| Answer Block Quality | 15 | Count of Q+A, definition, FAQ patterns (0=0, 1-2=8, 3+=15) | {x} | {y} |\n| Term Definitions | 10 | % of technical terms defined at first use | {x} | {y} |\n| **Overall Citability** | **100** | **Sum of above** | **{x}/100** | **{y}/100** |\n\n**GEO Score impact**: Content Citability carries a 35% weight in the composite GEO Score. Improving this score directly impacts the largest single dimension.\n\n## Issue Summary\n\n| Category | Count | Severity |\n|----------|-------|----------|\n| Hedge Language | {n} | {avg severity} |\n| Missing Data | {n} | {avg severity} |\n| Missing Definitions | {n} | {avg severity} |\n| Poor Self-Containment | {n} | {avg severity} |\n| Structural Issues | {n} | {avg severity} |\n| Weak Answer Blocks | {n} | {avg severity} |\n\n## Rewrites\n\n{All paragraph rewrites from Phase 3}\n\n## Full Rewritten Content\n\n{Complete content with all rewrites applied, ready to copy-paste}\n```\n\n### 4.2 Print Summary\n\n```\nContent Fix: {title or domain}\n\nParagraphs: {total} analyzed, {n} rewritten\nHedge Density: {before}% → {after}% (target: < 0.5%)\nCitability Score: {before}/100 → {after}/100 (estimated)\n\nTop issues:\n 1. {issue description} ({n} instances)\n 2. {issue description} ({n} instances)\n 3. {issue description} ({n} instances)\n\nOutput: content-fix-{domain}-{date}.md\n```\n\n---\n\n## Phase 5: Post-Optimization Validation\n\nAfter generating all rewrites, run a final self-check on the rewritten content. This catches issues that paragraph-level analysis may miss.\n\n### 5.1 Citability Self-Check\n\nVerify the rewritten content against these criteria:\n\n| # | Check | Pass Criteria | Status |\n|---|-------|--------------|--------|\n| 1 | **Direct answer in first 150 words** | The opening paragraph directly answers the page's primary question or states the core value proposition — no preamble | Pass/Fail |\n| 2 | **Data density** | At least 1 specific statistic or quantitative claim per 300 words (or `[TODO]` placeholder) | Pass/Fail |\n| 3 | **Citation frequency** | At least 1 named source per 500 words | Pass/Fail |\n| 4 | **Definition coverage** | All key terms defined at first use (acronyms expanded, jargon explained) | Pass/Fail |\n| 5 | **Self-containment** | No paragraph starts with unresolved \"This\", \"It\", \"They\" | Pass/Fail |\n| 6 | **Hedge-free zones** | Zero hedge words in definition blocks, lead paragraphs, and FAQ answers | Pass/Fail |\n| 7 | **Structural variety** | At least 1 table or comparison list, 1 numbered process, and 1 Q&A block in the full content (where applicable) | Pass/Fail |\n| 8 | **Freshness signals** | Dates, timeframes, or \"as of [year]\" present for statistical claims | Pass/Fail |\n| 9 | **Quotable passages** | At least 3 passages that are self-contained, factual, and under 60 words — ideal for AI extraction | Pass/Fail |\n| 10 | **No invented data** | All statistics are from the original content or marked `[TODO: add source]` — nothing fabricated | Pass/Fail |\n\n### 5.2 Validation Output\n\nAppend the check results to the fix report:\n\n```markdown\n## Post-Optimization Validation\n\n| # | Check | Status |\n|---|-------|--------|\n| 1 | Direct answer in first 150 words | {Pass/Fail} |\n| 2 | Data density (≥1 stat per 300 words) | {Pass/Fail} |\n| 3 | Citation frequency (≥1 source per 500 words) | {Pass/Fail} |\n| 4 | Definition coverage | {Pass/Fail} |\n| 5 | Self-containment (no unresolved pronouns) | {Pass/Fail} |\n| 6 | Hedge-free zones | {Pass/Fail} |\n| 7 | Structural variety | {Pass/Fail} |\n| 8 | Freshness signals | {Pass/Fail} |\n| 9 | Quotable passages (≥3) | {Pass/Fail} |\n| 10 | No invented data | {Pass/Fail} |\n\n**Result**: {n}/10 passed\n{If any Fail: list specific items that need attention}\n```\n\nIf fewer than 7 checks pass, flag the content as **needs additional work** and list the specific failures with fix suggestions.\n\n---\n\n## Error Handling\n\n- **URL unreachable**: Report the error and ask user to provide the content as pasted text instead\n- **No main content extracted**: If the page is mostly navigation/JS with no readable content, report as error and suggest the user paste the text directly\n- **Content too long (>50 paragraphs)**: Analyze the first 50 paragraphs and suggest the user split the remaining content into a second run\n- **Non-text content**: Skip images, videos, embedded widgets — only analyze text paragraphs\n- **Rate limiting**: Wait 1 second between requests when fetching multiple pages\n- **Timeout**: 30 seconds per URL fetch\n\n---\n\n## Quality Gates\n\n1. **Meaning preservation** — Rewrites must not change the author's intent or claims\n2. **Data integrity** — Never invent statistics; use `[TODO: ...]` placeholders for missing data\n3. **Tone consistency** — Match the original content's tone (formal/casual/technical)\n4. **Language matching** — Rewrite in the same language as the original content\n5. **No over-optimization** — Content should still read naturally, not like keyword stuffing\n6. **Rate limiting** — 1 second between requests when fetching URLs\n7. **Maximum scope** — Analyze up to 50 paragraphs per run; suggest splitting for longer content","tags":["geo","fix","content","geoskills","cognitic-labs","agent-skills","agentskills","ai-citability","ai-search","ai-visibility","chatgpt","claude-code"],"capabilities":["skill","source-cognitic-labs","skill-geo-fix-content","topic-agent-skills","topic-agentskills","topic-ai-citability","topic-ai-search","topic-ai-visibility","topic-chatgpt","topic-claude-code","topic-codex","topic-cursor","topic-geo","topic-json-ld","topic-llm"],"categories":["geoskills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/Cognitic-Labs/geoskills/geo-fix-content","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add Cognitic-Labs/geoskills","source_repo":"https://github.com/Cognitic-Labs/geoskills","install_from":"skills.sh"}},"qualityScore":"0.454","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 8 github stars · SKILL.md body (14,102 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":"2026-05-18T19:08:51.376Z","embedding":null,"createdAt":"2026-05-18T13:14:31.232Z","updatedAt":"2026-05-18T19:08:51.376Z","lastSeenAt":"2026-05-18T19:08:51.376Z","tsv":"'-1':1188 '-2':1191,1251 '-3':541,741 '-4':1227 '/10':1720 '/100':1276,1278,1383,1385 '/geo-audit/references/scoring-guide.md':1161 '0':1248,1249 '0.5':425,1185,1187,1379 '1':216,669,1190,1250,1389,1457,1488,1506,1563,1568,1572,1656,1667,1676,1833,1849,1913 '1.1':218 '1.2':273 '10':629,1192,1259,1619,1713 '100':423,1271 '15':1189,1224,1229,1240,1254 '150':1462,1661 '2':332,540,685,740,979,1193,1226,1394,1483,1664,1862 '2.0':432 '2.1':345,637 '2.2':437 '2.3':468 '2.4':492 '2.5':530 '2.6':573 '20':1184,1186,1201,1214 '2025':930 '2026':989 '3':633,653,696,1030,1253,1346,1399,1501,1602,1673,1711,1874 '3.1':666 '3.2':747 '3.3':796 '3.4':937 '3.5':1051 '30':1842 '300':1495,1670 '34':976 '35':1286 '4':536,710,746,1084,1513,1682,1884 '4.1':1086 '4.2':1361 '5':724,1194,1231,1412,1528,1686,1896 '5.1':1441 '5.2':1638 '50':1798,1803,1926 '500':980,1510,1679 '6':342,736,1230,1541,1694,1910 '60':1612 '7':1558,1700,1734,1920 '8':1252,1583,1704 '9':1597,1708 'absent':605 'accept':221 'acronym':478,1523 'ad':257,831,846,889,904,929 'add':15,697,707,1633 'addit':1742 'agent':184 'ai':10,26,37,42,69,74,351,355,538,584,787,797,802,875,1616 'aio':895 'alon':501 'alreadi':1059 'analysi':213,317,1438 'analyz':56,153,169,237,280,1134,1371,1800,1827,1923 'answer':575,585,594,715,878,1237,1335,1459,1468,1556,1658 'anteced':509,649 'appear':390 'append':1641 'appli':1355 'applic':1581 'approxim':381,384 'around':383 'ask':32,1760 'assum':486 'attempt':199,207 'attent':1730 'attribut':833 'audit':1156 'author':677,825,1857 'authorit':358 'avg':1225,1310,1315,1320,1327,1332,1338 'back':97 'banner':259 'baselin':456 'basi':1178 'before/after':123 'belong':299 'benchmark':999 'benefit':789,818,918,1050 'better':449 'bias':807 'bit':405 'blank':287 'block':265,543,576,1079,1238,1336,1551,1575 'bodi':251 'bonus':1234 'brand':857,865 'brand-sit':856 'break':276,562 'brief':314 'build':130 'bullet':1032 'buri':608 'cannot':499 'carri':1284 'case':967 'catch':1432 'categori':344,363,364,1304 'certainti':689 'chang':674,773,776,781,1855 'chatgpt':824,838 'check':1426,1445,1453,1643,1654,1735 'citabl':11,39,70,127,329,429,1120,1142,1146,1158,1270,1283,1380,1442 'citat':352,799,806,836,912,1502,1674 'cite':78,901 'claim':444,457,639,719,1200,1203,1493,1595,1861 'clariti':1223 'claud':896,914 'clear':508 'code':264,1078 'column':1039 'comma':761 'comma-separ':760 'communiti':843 'comparison':454,1036,1566 'complet':1350 'composit':1290 'concept':488 'concis':739 'condit':969 'confid':359,941 'consid':963 'consist':867,1876 'contain':21,101,181,496,728,871,1005,1212,1325,1531,1608,1689 'content':4,7,35,48,53,58,82,128,132,135,138,168,180,234,250,274,278,316,430,544,577,607,859,1095,1105,1119,1157,1282,1349,1351,1364,1406,1430,1449,1579,1629,1739,1765,1772,1783,1795,1812,1820,1880,1895,1901,1934 'content-fix':1094,1104,1405 'context':293,491,527,862 'continu':211 'convert':884 'cooki':258 'copi':1359 'copy-past':1358 'core':1477 'cost':693 'could':372,579,957 'count':306,322,324,326,419,422,985,1138,1141,1241,1305 'coverag':1515,1684 'creat':1090 'criteria':1452,1455 'critic':431 'custom':978,981,984 'data':16,96,147,151,439,638,698,702,841,861,900,908,931,1198,1313,1484,1622,1665,1716,1863,1873 'data-back':95 'data-support':1197 'date':847,993,1128,1409,1586 'dd':1101,1110,1132 'defin':1263,1519 'definit':470,599,1245,1258,1318,1514,1550,1683 'densiti':416,636,1183,1375,1485,1666 'depend':524,1002 'descript':272,1049,1391,1396,1401 'detail':1046 'detect':208 'diagnosi':336,616 'dictionari':115 'differ':801,805 'dimens':1064,1159,1173,1301 'direct':238,583,593,1072,1296,1458,1467,1657,1794 'directori':111 'disclaim':1067 'discoveri':217 'discuss':523 'distanc':388 'doesn':568,587 'domain':320,1097,1368,1408 'e.g':186 'elimin':119 'embed':1824 'engin':27,356 'error':1752,1758,1786 'est':1181 'estim':1386 'everi':83,338 'evid':446,1207 'exampl':124,365,925 'execut':173 'expand':480,1524 'expert':828,832 'explain':1526 'explan':477 'extract':231,248,1617,1773 'fabric':1636 'fact':1025 'factual':1609 'fail':1724 'failur':1748 'fair':377 'faq':606,881,1246,1555 'faster':450 'favor':821 'featur':1014,1044,1048 'fetch':139,161,167,179,227,244,1838,1846,1918 'fewer':1732 'file':106,1089,1092 'final':1423 'first':482,566,597,628,722,906,1265,1461,1521,1660,1802 'first-parti':905 'fix':3,38,52,1088,1096,1106,1121,1365,1407,1647,1750 'flag':1737 'follow':158,195,663 'footer':255 'form':225 'formal/casual/technical':1883 'format':615,749,892 'found':176,1137 'free':1544,1697 'frequenc':1503,1675 'fresh':840,935,1584,1705 'front':712 'front-load':711 'full':1164,1347,1578 'gate':1848 'gemini':855,873 'general':396,397,962 'generat':660,809,1087,1418 'geo':2,51,1155,1279,1291 'geo-audit':1154 'geo-fix-cont':1,50 'googl':874,894 'h2/h3':295 'handl':136,1753 'head':261,292,325,591 'header':254 'hedg':13,44,113,346,348,361,415,417,632,634,687,940,1182,1307,1374,1543,1547,1696 'hedge-fre':1542,1695 'help':691,943,944,1007,1010 'high':373,395,413,428,651 'high-cit':427 'html':162,247 'ideal':1614 'ignor':187 'imag':1822 'impact':459,785,927,1281,1297 'implic':823 'improv':18,34,643,864,959,960,973,974,1293 'indic':433,952,953 'industri':484,995 'industry-lead':994 'inject':206 'input':220,222,1113 'instanc':1393,1398,1403 'instead':611,1769 'instruct':156,175,185,189 'integr':1864 'intent':1859 'invent':1621,1715,1866 'inventori':275 'isol':735,1219 'issu':330,343,532,622,631,659,759,763,1136,1302,1330,1388,1390,1395,1400,1433 'item':1031,1727 'jargon':474,1525 'keep':737 'key':718,1024,1517 'keyword':1908 'kind':408 'known':487 'languag':14,114,121,347,436,1308,1885,1891 'largest':1299 'lead':996,1552 'least':1487,1505,1562,1601 'legal':1066 'level':62,335,1437 'like':394,1907 'likelihood':72 'limit':1831,1912 'line':288,626,757 'list':262,549,764,880,921,1028,1033,1043,1567,1725,1745 'lists/tables':1232 'load':713 'long':1797 'longer':534,1933 'main':233,249,1771 'make':47,90,443,725 'mani':977 'map':1168 'mark':1631 'markdown':754,1118,1649 'match':1877,1886 'max':1175 'maxim':9,68 'maximum':745,1921 'may':1439 'mayb':368 'md':1102,1111,1410 'mean':88,529,672,1850 'medium':380,387,402 'mental':163 'mention':518,1019 'meta':271 'metric':414,461,641,709,1167,1174 'might':371,690,942 'miss':438,469,563,601,1312,1317,1440,1872 'mm':1100,1109,1131 'most':1778 'multipl':919,1839 'must':1853 'n':625,756,1309,1314,1319,1326,1331,1337,1372,1392,1397,1402,1719 'name':826,835,866,1009,1015,1075,1093,1507 'natur':1905 'navig':253 'navigation/js':1779 'near':386 'need':1729,1741 'never':154,673,1865 'non':1818 'non-text':1817 'normal':214 'note':197,266 'noth':1635 'number':301,453,1042,1569 'often':399 'one':924 'open':1465 'opportun':600 'optim':23,1415,1652,1900 'origin':87,671,766,899,1628,1879,1894 'output':202,617,1085,1404,1640 'over-optim':1898 'overal':1145,1269 'overview':876 'page':229,246,268,1470,1776,1840 'paragraph':61,284,298,303,311,323,334,339,441,497,513,533,572,620,624,657,730,744,753,755,767,771,1057,1133,1139,1204,1213,1216,1342,1369,1436,1466,1533,1553,1799,1804,1829,1927 'paragraph-level':333,1435 'parti':907 'pass':1454,1721,1736 'pass/fail':1482,1500,1512,1527,1540,1557,1582,1596,1618,1637,1663,1672,1681,1685,1693,1699,1703,1707,1712,1717 'passag':1599,1603,1710 'past':235,1115,1126,1360,1767,1791 'pattern':118,129,604,882,939,1247 'per':743,1494,1509,1669,1678,1844,1928 'perhap':369 'perplex':839,854,928 'phase':215,331,652,1083,1345,1411 'placehold':699,1499,1870 'platform':784,788,798,803,816,820,920,926 'point':1176 'poor':493,1322 'possibl':370 'post':1414,1651 'post-optim':1413,1650 'potenti':958 'preambl':1481 'prefer':357,539,800 'present':1592 'preserv':85,260,291,670,1851 'previous':188,512 'primari':897,923,1472 'principl':668 'print':312,1362 'probabl':353 'process':160,1570 'product':1008 'prompt':205 'pronoun':1692 'proposit':1479 'prose':556,610,885,1026 'provid':64,243,1763 'put':716 'q':613,890,1243,1573 'q1':988 'qualif':374 'qualiti':1239,1847 'quantit':1206,1492 'question':589,1473 'quit':379 'quot':77,829,1073 'quotabl':94,131,733,1598,1709 'rank':1001 'rate':1830,1911 'rather':378 'read':511,1904 'readabl':1782 'readi':1356 'real':701 'recenc':842 'recent':851,986 'recommend':80 'record':623 'reduc':350,692,946 'refer':102,105,305,516 'referenc':489 'references/hedge-words.md':112 'references/quotable-content-examples.md':122 'regulatori':1069 'relat':376 'remain':1811 'remov':12,43,1021 'replac':686 'report':1648,1756,1784 'request':1836,1916 'requir':510 'research':911 'resembl':183 'restat':1022 'result':1644,1718 'rewrit':5,40,66,117,654,662,667,748,793,810,813,822,830,845,863,883,903,917,938,1056,1340,1343,1354,1420,1852,1887 'rewritten':752,770,1140,1348,1373,1429,1448 'rough':385 'rubric':1165 'rule':665,1053 'run':1421,1816,1929 'say':679,683 'scan':327,337 'scope':1922 'score':1060,1143,1147,1177,1280,1292,1295,1381 'second':1815,1834,1843,1914 'section':296 'secur':133 'see':1160 'seem':389,950 'self':20,100,495,644,727,870,1004,1211,1324,1425,1444,1530,1607,1688 'self-check':1424,1443 'self-contain':19,99,494,726,869,1003,1210,1323,1529,1606,1687 'sentenc':309,537,542,565,567,598,723,742 'sentences/para':1228 'separ':285,762 'sequenti':1040 'serv':580 'sever':366,650,1306,1311,1316,1321,1328,1333,1339 'show':955 'sidebar':256 'signal':844,936,1585,1706 'signific':642,972 'simplifi':1150 'singl':1300 'site':858 'skill':54,109 'skill-geo-fix-content' 'skip':1052,1821 'sometim':400 'somewhat':375 'sort':406 'sourc':467,827,898,933,1076,1123,1508,1634,1677 'source-cognitic-labs' 'specif':65,708,910,968,971,992,998,1082,1489,1726,1747 'split':282,1809,1931 'stand':500 'start':502,645,1534 'stat':1668 'state':463,1475 'statement':360,447 'statist':852,902,1490,1594,1624,1867 'status':1456,1655 'step':1041 'still':1903 'strip':252 'strong':126,934 'structur':24,531,860,877,1027,1117,1222,1329,1559,1701 'stuf':1909 'sub':1172 'sub-dimens':1171 'suggest':84,393,1751,1788,1806,1930 'sum':1272 'summar':570 'summari':315,1303,1363 'suppli':143 'support':17,440,1199 'surround':526 'system':75 'systemat':434 'tabl':263,551,879,1035,1037,1047,1564 'tables/lists':887 'tag':290,811,837,853,872,893,913 'target':424,1378 'technic':471,1081,1261 'tend':391 'term':472,485,602,1257,1262,1518 'text':92,182,236,559,768,772,1070,1116,1127,1768,1793,1819,1828 'timefram':465,1587 'timeout':1841 'titl':269,318,1122,1366 'todo':706,983,991,997,1498,1632,1869 'tone':1875,1882 'top':1387 'topic':564 'topic-agent-skills' 'topic-agentskills' 'topic-ai-citability' 'topic-ai-search' 'topic-ai-visibility' 'topic-chatgpt' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-geo' 'topic-json-ld' 'topic-llm' 'total':307,420,1135,1370 'treat':148 'trend':462 'two':224 'typic':401 'uncertainti':367 'unclear':648 'understand':515,1217 'unit':281 'unknown':704 'unreach':1755 'unresolv':1536,1691 'untrust':134,146 'url':144,226,241,1124,1754,1845,1919 'use':28,475,483,705,1148,1233,1266,1522,1868 'user':31,142,1761,1790,1808 'user-suppli':141 'usual':398 'vagu':970 'valid':219,1416,1639,1653 'valu':1478 'varieti':1560,1702 'verifi':1446 'version':1151 'video':1823 'visual':561 'wait':1832 'wall':557 'warn':209 'way':412 'weak':120,435,574,1334 'weaken':403 'websit':6,57 'weight':1287 'well':1061 'widget':1825 'within':177 'without':445,452,455,460,464,476,490,507,560,592,640 'word':45,308,321,349,362,418,421,630,635,1463,1496,1511,1548,1613,1662,1671,1680 'work':1012,1016,1743 'wrap':164 'written':554 'x':627,695,758,947,1195,1208,1220,1235,1255,1267,1275 'y':949,1196,1209,1221,1236,1256,1268,1277 'year':850,1591 'yyyi':1099,1108,1130 'yyyy-mm-dd':1098,1107,1129 'zero':1546 'zone':1545,1698","prices":[{"id":"65458e41-1dfb-44e9-bd88-46dcbd8bda2e","listingId":"32286c5f-1329-406c-9c99-41efb70479af","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"Cognitic-Labs","category":"geoskills","install_from":"skills.sh"},"createdAt":"2026-05-18T13:14:31.232Z"}],"sources":[{"listingId":"32286c5f-1329-406c-9c99-41efb70479af","source":"github","sourceId":"Cognitic-Labs/geoskills/geo-fix-content","sourceUrl":"https://github.com/Cognitic-Labs/geoskills/tree/main/skills/geo-fix-content","isPrimary":false,"firstSeenAt":"2026-05-18T13:14:31.232Z","lastSeenAt":"2026-05-18T19:08:51.376Z"}],"details":{"listingId":"32286c5f-1329-406c-9c99-41efb70479af","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"Cognitic-Labs","slug":"geo-fix-content","github":{"repo":"Cognitic-Labs/geoskills","stars":8,"topics":["agent-skills","agentskills","ai-citability","ai-search","ai-visibility","chatgpt","claude-code","codex","cursor","generative-engine-optimization","geo","json-ld","llm","llms-txt","openclaw","opencode","perplexity","schema-markup","seo","structured-data"],"license":"apache-2.0","html_url":"https://github.com/Cognitic-Labs/geoskills","pushed_at":"2026-04-05T17:45:25Z","description":"Open-source Agent Skills for GEO — 6 skills to diagnose, fix, and monitor AI visibility for your website. Works with Claude Code, OpenCode, OpenClaw, Codex, Cursor.","skill_md_sha":"c48b34befcb55441dc70d5c52735ea99d4c14818","skill_md_path":"skills/geo-fix-content/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/Cognitic-Labs/geoskills/tree/main/skills/geo-fix-content"},"layout":"multi","source":"github","category":"geoskills","frontmatter":{"name":"geo-fix-content","description":"Rewrite website content to maximize AI citability — remove hedge language, add data support, improve self-containment, and optimize structure for AI engines. Use when the user asks to improve content for AI, fix citability, rewrite for AI, remove hedge words, or make content more citable."},"skills_sh_url":"https://skills.sh/Cognitic-Labs/geoskills/geo-fix-content"},"updatedAt":"2026-05-18T19:08:51.376Z"}}