{"id":"0e515ab9-f2a8-4ae8-bb69-243f8121f836","shortId":"Qh67Zt","kind":"skill","title":"fill-icmje-coi","tagline":"Batch-generate per-author ICMJE Conflict of Interest Disclosure Forms (`coi_disclosure.docx`) for manuscript submission. Pre-fills all 13 disclosure items as \"☒ None\" + final certification ☒ using a synthetic seed template shipped with the skill, then clones the seed per author w","description":"# Fill-ICMJE-COI Skill\n\nYou are helping a researcher prepare ICMJE Conflict of Interest Disclosure Forms\nfor every co-author on a manuscript about to be submitted to an ICMJE member\njournal (CHEST, NEJM, JAMA, Lancet, Radiology, etc.). This skill batch-generates\none personalized `.docx` per author from a synthetic all-None seed shipped with\nthe skill, avoiding 10–20 minutes of repetitive Word clicking per author.\n\n## Why This Skill Exists\n\nThe official ICMJE `coi_disclosure.docx` puts every field inside Word Content\nControls (Structured Document Tags, a.k.a. SDTs). Naive `python-docx`\nmanipulation of `cell.text` silently ignores SDT content, so the straightforward\nprogrammatic approach does not work. The historical workaround was to open the\ntemplate in Word and manually fill each author's form (21 authors × 13\ncheckboxes × 2 clicks = ~500 clicks). This skill replaces that by operating\ndirectly on `word/document.xml` inside the docx zip and doing literal-string\nreplacement — but that requires the target strings to already exist in the\nseed, so the skill ships a pre-filled synthetic seed.\n\n**Precedent:** a multi-author cohort manuscript submission — 6 authors\nauto-filled in ~5 seconds from the synthetic seed with zero Word clicks.\n\n## Core Principles (Do Not Violate)\n\n1. **Never author SDT XML from scratch.** Only replace existing strings in an\n   already-populated seed. Creating Content Controls programmatically is\n   fragile and Word-version-dependent.\n2. **Never ship a real author's filled form as the seed.** The template\n   directory contains `icmje_coi_seed_synthetic.docx` with all PII scrubbed\n   (synthetic name, title, date; metadata reset to `ICMJE` / `Anonymous`).\n   Real-person seeds leak PII through both document.xml and docProps.\n3. **Never modify the 13 disclosure items or certification checkbox.** The\n   script only replaces Date/Name/Title. If any author has a real disclosure,\n   they must edit in Word manually — the skill's purpose is the common\n   all-None case.\n4. **Always verify before circulation.** Each output must have 14 × ☒ and\n   13 × \"None\" in document.xml. The script runs this check implicitly by\n   preserving the seed structure; a post-generation grep is cheap insurance.\n\n## When to Use This Skill\n\n- Manuscript accepted for submission to an ICMJE member journal\n- 3+ co-authors with no real financial conflicts\n- Editorial Manager / submission portal requires per-author ICMJE disclosure docx\n- About to hand-fill the same form 6–21 times\n\nSkip this skill when:\n- Any author has a real financial disclosure to list (they fill their own form\n  in Word; this skill does not help)\n- Target journal uses its own declaration form (not ICMJE) — check author\n  guidelines first\n- Only 1 author (not worth the setup)\n\n## Execution\n\n### Phase 1 — Intake\n\nAsk the user (or extract from conversation):\n1. **Manuscript title** (exact, as it will appear on title page)\n2. **Submission date** (e.g., \"April 20, 2026\")\n3. **Author list** — ordered, one name per slot: `[(1, \"Author One\"), (2, \"Author Two\"), ...]`\n4. **Output directory** — typically `submission/{journal}/icmje_forms/`\n\nPresent the intake back to the user for confirmation (**Gate 1 — user approval**)\nbefore generating anything. Explicitly name which authors will get all-None\nforms and remind that anyone with a real disclosure must instead fill their own\nform in Word.\n\n### Phase 2 — Generate\n\nInvoke the script with the synthetic seed that ships with this skill:\n\n```bash\npython3 ${SKILL_DIR}/scripts/fill_icmje_coi.py \\\n  --seed ${SKILL_DIR}/templates/icmje_coi_seed_synthetic.docx \\\n  --seed-name \"Placeholder Author\" \\\n  --seed-title \"Placeholder Manuscript Title\" \\\n  --seed-date \"January 1, 2000\" \\\n  --new-title \"{exact manuscript title}\" \\\n  --new-date \"{submission date}\" \\\n  --out-dir {out_dir} \\\n  --authors '[[1,\"Author One\"],[2,\"Author Two\"],...]'\n```\n\nThe script exits nonzero if any seed string is not found, preventing silent\nfailures.\n\n### Phase 3 — Verify\n\nFor each generated docx, confirm:\n- ☒ count = 14 (13 disclosure items + 1 final certification)\n- \"None\" count = 13\n- Correct name appears after \"Your Name:\"\n- Correct title appears after \"Manuscript Title:\"\n- No leakage of seed placeholder strings (`Placeholder Author`, `Placeholder Manuscript Title`, `January 1, 2000`)\n\nVerification one-liner:\n```bash\nfor f in {out_dir}/*.docx; do\n  python3 -c \"\nimport zipfile, sys\nxml = zipfile.ZipFile('$f').read('word/document.xml').decode()\nassert xml.count('☒') == 14, 'bad ☒ count'\nassert xml.count('None') == 13, 'bad None count'\nassert 'Placeholder' not in xml, 'seed leak'\nprint('✓ $f')\n\"\ndone\n```\n\nPresent verification results to user (**Gate 2 — user review**) before handing\noff files.\n\n### Phase 4 — Circulation Guidance\n\nProvide the user with circulation copy to send with each personalized form:\n\n> 첨부된 ICMJE COI 폼을 검토 부탁드립니다.\n> - 내용이 맞으면 서명 후 PDF로 회신\n> - 수정이 필요하면 해당 항목을 고쳐서 체크 + 서명 후 회신\n> - 전체가 변경 없음이면 \"변경 없음\" 회신 + 서명본 PDF 별도 회신\n\nAll 6–21 authors can be emailed in one `gws gmail draft` batch (**Gate 3 — user\napproves batch send** before actually dispatching).\n\n## Custom Seeds\n\nIf the user wants a custom seed (e.g., different default wording, pre-filled\nitems 2/3 with a common grant), generate it once as follows:\n\n1. Open `templates/icmje_coi_seed_synthetic.docx` in Word\n2. Edit the desired fields\n3. Save as a new file under `{project}/submission/{journal}/` or\n   `~/.claude/private-seeds/`\n4. Pass `--seed /path/to/custom.docx` to the script along with the new seed\n   values for `--seed-name`, `--seed-title`, `--seed-date`\n\nDo NOT commit custom seeds that contain real author names to the public\nmedsci-skills repo. Keep them in private per-project directories or under\n`~/.claude/private-seeds/`.\n\n## Seed Provenance (how the shipped synthetic seed was created)\n\nThe shipped `templates/icmje_coi_seed_synthetic.docx` was derived from the\nofficial ICMJE `coi_disclosure.docx` through the following steps:\n\n1. Downloaded the official ICMJE template (`https://www.icmje.org/downloads/coi_disclosure.docx`)\n2. Opened in Word, typed placeholder values:\n   - Date: `January 1, 2000`\n   - Your Name: `Placeholder Author`\n   - Manuscript Title: `Placeholder Manuscript Title`\n3. Checked each of the 13 disclosure items' \"None\" option (14 checkboxes total including final certification)\n4. Typed \"None\" in the \"Name all entities\" column for each item\n5. Scrubbed `docProps/core.xml` metadata: creator=`ICMJE`, lastModifiedBy=`Anonymous`, dates=`2000-01-01`\n6. Scrubbed `docProps/app.xml` Company/Manager fields\n\nNo real author's disclosure data is embedded. The file is safe to redistribute.\n\n## Anti-Hallucination\n\n- **Never invent author names, email addresses, or ORCIDs.** Pull them\n  verbatim from the manuscript's title page or the user's author list.\n- **Never claim to have filled the 13 disclosure items** — they come from the\n  seed unchanged. If the user asks whether the script \"handled the\n  disclosures,\" the honest answer is \"it cloned the seed's ☒ None entries;\n  no author-specific disclosure reasoning happened.\"\n- **Never promise the script works on a blank ICMJE template.** It does not —\n  the seed must be pre-filled with all-None ☒ + text.\n- **Never edit seed XML by authoring new SDT elements.** If an error requires\n  altering the seed structure, stop and escalate to the user; Word-generated\n  SDT XML is the ground truth.\n- **Never push private seed files to public repos.** If the user asks to\n  promote a custom seed, verify by `unzip -p seed.docx docProps/core.xml` that\n  no real names remain in metadata before committing.\n\n## References\n\n- ICMJE Disclosure of Interest page: https://www.icmje.org/disclosure-of-interest/\n- ICMJE COI form download: https://www.icmje.org/downloads/coi_disclosure.docx\n- ICMJE FAQ on disclosure forms: https://www.icmje.org/about-icmje/faqs/conflict-of-interest-disclosure-forms/\n- ${SKILL_DIR}/scripts/fill_icmje_coi.py — generator CLI + Python API\n- ${SKILL_DIR}/templates/icmje_coi_seed_synthetic.docx — shipped synthetic seed (PII-free)\n\n## Related Skills\n\n| Skill | Relationship |\n|---|---|\n| `write-paper` | Completes the manuscript whose title is used as input |\n| `find-journal` | Identifies whether the target journal requires ICMJE form |\n| `add-journal` | Journal profile records whether ICMJE form is required |\n| `revise` | After revision, updated title may require re-generating forms |\n\n## Non-Goals\n\n- Filling journal-specific disclosure forms (Elsevier Declaration of Interest,\n  BMJ ICMJE derivative, etc.) — only the canonical ICMJE form\n- Handling authors with real disclosures — those authors fill their own forms\n- Signing the forms — authors sign manually after receiving their personalized docx\n- Uploading to Editorial Manager — that remains manual, post-signature","tags":["fill","icmje","coi","medsci","skills","aperivue","agent-skills","biostatistics","claude-code","claude-skills","clinical-research","diagnostic-accuracy"],"capabilities":["skill","source-aperivue","skill-fill-icmje-coi","topic-agent-skills","topic-biostatistics","topic-claude-code","topic-claude-skills","topic-clinical-research","topic-diagnostic-accuracy","topic-irb-protocol","topic-literature-review","topic-manuscript","topic-medical-ai","topic-medical-research","topic-meta-analysis"],"categories":["medsci-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/Aperivue/medsci-skills/fill-icmje-coi","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add Aperivue/medsci-skills","source_repo":"https://github.com/Aperivue/medsci-skills","install_from":"skills.sh"}},"qualityScore":"0.499","qualityRationale":"deterministic score 0.50 from registry signals: · indexed on github topic:agent-skills · 98 github stars · SKILL.md body (8,809 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T18:56:29.461Z","embedding":null,"createdAt":"2026-05-13T12:57:44.536Z","updatedAt":"2026-05-18T18:56:29.461Z","lastSeenAt":"2026-05-18T18:56:29.461Z","tsv":"'-01':1017,1018 '/.claude/private-seeds':875,926 '/about-icmje/faqs/conflict-of-interest-disclosure-forms/':1219 '/disclosure-of-interest/':1204 '/downloads/coi_disclosure.docx':958,1211 '/icmje_forms':534 '/path/to/custom.docx':879 '/scripts/fill_icmje_coi.py':596,1222 '/submission':872 '/templates/icmje_coi_seed_synthetic.docx':600,1229 '1':253,479,487,496,522,545,616,635,668,698,854,950,968 '10':110 '13':25,177,326,372,665,673,731,984,1070 '14':370,664,725,989 '2':179,281,507,525,578,638,751,859,959 '2/3':844 '20':111,512 '2000':617,699,969,1016 '2026':513 '21':175,438,807 '3':322,409,514,656,819,864,979 '4':361,528,759,876,995 '5':238,1007 '500':181 '6':232,437,806,1019 'a.k.a':137 'accept':401 'actual':825 'add':1264 'add-journ':1263 'address':1046 'all-non':101,357,557,1128 'along':883 'alreadi':209,267 'already-popul':266 'alter':1145 'alway':362 'anonym':310,1014 'answer':1091 'anti':1039 'anti-hallucin':1038 'anyon':564 'anyth':550 'api':1226 'appear':503,676,682 'approach':154 'approv':547,821 'april':511 'ask':489,1082,1175 'assert':723,728,735 'author':10,46,69,97,118,172,176,228,233,255,286,339,412,425,445,475,480,515,523,526,554,605,634,636,639,693,808,907,973,1026,1043,1062,1102,1137,1308,1313,1321 'author-specif':1101 'auto':235 'auto-fil':234 'avoid':109 'back':538 'bad':726,732 'bash':592,704 'batch':6,91,817,822 'batch-gener':5,90 'blank':1114 'bmj':1298 'c':713 'canon':1304 'case':360 'cell.text':145 'certif':31,330,670,994 'cheap':393 'check':380,474,980 'checkbox':178,331,990 'chest':82 'circul':365,760,766 'claim':1065 'cli':1224 'click':116,180,182,247 'clone':42,1094 'co':68,411 'co-author':67,410 'cohort':229 'coi':4,51,776,1206 'coi_disclosure.docx':17,126,945 'column':1003 'come':1074 'commit':901,1195 'common':356,847 'company/manager':1022 'complet':1243 'confirm':543,662 'conflict':12,60,417 'contain':296,905 'content':132,149,271 'control':133,272 'convers':495 'copi':767 'core':248 'correct':674,680 'count':663,672,727,734 'creat':270,935 'creator':1011 'custom':827,834,902,1179 'data':1029 'date':305,509,614,626,628,898,966,1015 'date/name/title':336 'declar':470,1295 'decod':722 'default':838 'depend':280 'deriv':940,1300 'desir':862 'differ':837 'dir':595,599,631,633,709,1221,1228 'direct':189 'directori':295,530,923 'disclosur':15,26,63,327,343,427,450,568,666,985,1028,1071,1088,1104,1198,1215,1292,1311 'dispatch':826 'docprop':321 'docprops/app.xml':1021 'docprops/core.xml':1009,1186 'document':135 'document.xml':319,375 'docx':95,142,194,428,661,710,1328 'done':744 'download':951,1208 'draft':816 'e.g':510,836 'edit':346,860,1133 'editori':418,1331 'element':1140 'elsevi':1294 'email':811,1045 'embed':1031 'entiti':1002 'entri':1099 'error':1143 'escal':1151 'etc':87,1301 'everi':66,128 'exact':499,621 'execut':485 'exist':122,210,262 'exit':643 'explicit':551 'extract':493 'f':706,719,743 'failur':654 'faq':1213 'field':129,863,1023 'file':757,869,1033,1168 'fill':2,23,49,170,221,236,288,433,454,571,842,1068,1126,1288,1314 'fill-icmje-coi':1,48 'final':30,669,993 'financi':416,449 'find':1253 'find-journ':1252 'first':477 'follow':853,948 'form':16,64,174,289,436,457,471,560,574,773,1207,1216,1262,1271,1284,1293,1306,1317,1320 'found':651 'fragil':275 'free':1235 'gate':544,750,818 'generat':7,92,390,549,579,660,849,1157,1223,1283 'get':556 'gmail':815 'goal':1287 'grant':848 'grep':391 'ground':1162 'guidanc':761 'guidelin':476 'gws':814 'hallucin':1040 'hand':432,755 'hand-fil':431 'handl':1086,1307 'happen':1106 'help':55,464 'histor':159 'honest':1090 'icmj':3,11,50,59,79,125,309,406,426,473,775,944,954,1012,1115,1197,1205,1212,1261,1270,1299,1305 'icmje_coi_seed_synthetic.docx':297 'identifi':1255 'ignor':147 'implicit':381 'import':714 'includ':992 'input':1251 'insid':130,192 'instead':570 'insur':394 'intak':488,537 'interest':14,62,1200,1297 'invent':1042 'invok':580 'item':27,328,667,843,986,1006,1072 'jama':84 'januari':615,697,967 'journal':81,408,466,533,873,1254,1259,1265,1266,1290 'journal-specif':1289 'keep':916 'lancet':85 'lastmodifiedbi':1013 'leak':315,741 'leakag':687 'liner':703 'list':452,516,1063 'liter':199 'literal-str':198 'manag':419,1332 'manipul':143 'manual':169,349,1323,1335 'manuscript':19,72,230,400,497,610,622,684,695,974,977,1054,1245 'may':1279 'medsci':913 'medsci-skil':912 'member':80,407 'metadata':306,1010,1193 'minut':112 'modifi':324 'multi':227 'multi-author':226 'must':345,368,569,1122 'naiv':139 'name':303,519,552,603,675,679,892,908,971,1000,1044,1190 'nejm':83 'never':254,282,323,1041,1064,1107,1132,1164 'new':619,625,868,886,1138 'new-dat':624 'new-titl':618 'non':1286 'non-goal':1285 'none':29,103,359,373,559,671,730,733,987,997,1098,1130 'nonzero':644 'offici':124,943,953 'one':93,518,524,637,702,813 'one-lin':701 'open':163,855,960 'oper':188 'option':988 'orcid':1048 'order':517 'out-dir':629 'output':367,529 'p':1184 'page':506,1057,1201 'paper':1242 'pass':877 'pdf':802 'pdf로':784 'per':9,45,96,117,424,520,921 'per-author':8,423 'per-project':920 'person':94,313,772,1327 'phase':486,577,655,758 'pii':300,316,1234 'pii-fre':1233 'placehold':604,609,690,692,694,736,964,972,976 'popul':268 'portal':421 'post':389,1337 'post-gener':388 'post-signatur':1336 'pre':22,220,841,1125 'pre-fil':21,219,840,1124 'preced':224 'prepar':58 'present':535,745 'preserv':383 'prevent':652 'principl':249 'print':742 'privat':919,1166 'profil':1267 'programmat':153,273 'project':871,922 'promis':1108 'promot':1177 'proven':928 'provid':762 'public':911,1170 'pull':1049 'purpos':353 'push':1165 'put':127 'python':141,1225 'python-docx':140 'python3':593,712 'radiolog':86 're':1282 're-gener':1281 'read':720 'real':285,312,342,415,448,567,906,1025,1189,1310 'real-person':311 'reason':1105 'receiv':1325 'record':1268 'redistribut':1037 'refer':1196 'relat':1236 'relationship':1239 'remain':1191,1334 'remind':562 'repetit':114 'replac':185,201,261,335 'repo':915,1171 'requir':204,422,1144,1260,1273,1280 'research':57 'reset':307 'result':747 'review':753 'revis':1274,1276 'run':378 'safe':1035 'save':865 'scratch':259 'script':333,377,582,642,882,1085,1110 'scrub':301,1008,1020 'sdt':148,256,1139,1158 'sdts':138 'second':239 'seed':35,44,104,213,223,243,269,292,314,385,586,597,602,607,613,647,689,740,828,835,878,887,891,894,897,903,927,933,1077,1096,1121,1134,1147,1167,1180,1232 'seed-dat':612,896 'seed-nam':601,890 'seed-titl':606,893 'seed.docx':1185 'send':769,823 'setup':484 'ship':37,105,217,283,588,931,937,1230 'sign':1318,1322 'signatur':1338 'silent':146,653 'skill':40,52,89,108,121,184,216,351,399,442,461,591,594,598,914,1220,1227,1237,1238 'skill-fill-icmje-coi' 'skip':440 'slot':521 'source-aperivue' 'specif':1103,1291 'step':949 'stop':1149 'straightforward':152 'string':200,207,263,648,691 'structur':134,386,1148 'submiss':20,231,403,420,508,532,627 'submit':76 'synthet':34,100,222,242,302,585,932,1231 'sys':716 'tag':136 'target':206,465,1258 'templat':36,165,294,955,1116 'templates/icmje_coi_seed_synthetic.docx':856,938 'text':1131 'time':439 'titl':304,498,505,608,611,620,623,681,685,696,895,975,978,1056,1247,1278 'topic-agent-skills' 'topic-biostatistics' 'topic-claude-code' 'topic-claude-skills' 'topic-clinical-research' 'topic-diagnostic-accuracy' 'topic-irb-protocol' 'topic-literature-review' 'topic-manuscript' 'topic-medical-ai' 'topic-medical-research' 'topic-meta-analysis' 'total':991 'truth':1163 'two':527,640 'type':963,996 'typic':531 'unchang':1078 'unzip':1183 'updat':1277 'upload':1329 'use':32,397,467,1249 'user':491,541,546,749,752,764,820,831,1060,1081,1154,1174 'valu':888,965 'verbatim':1051 'verif':700,746 'verifi':363,657,1181 'version':279 'violat':252 'w':47 'want':832 'whether':1083,1256,1269 'whose':1246 'word':115,131,167,246,278,348,459,576,839,858,962,1156 'word-gener':1155 'word-version-depend':277 'word/document.xml':191,721 'work':157,1111 'workaround':160 'worth':482 'write':1241 'write-pap':1240 'www.icmje.org':957,1203,1210,1218 'www.icmje.org/about-icmje/faqs/conflict-of-interest-disclosure-forms/':1217 'www.icmje.org/disclosure-of-interest/':1202 'www.icmje.org/downloads/coi_disclosure.docx':956,1209 'xml':257,717,739,1135,1159 'xml.count':724,729 'zero':245 'zip':195 'zipfil':715 'zipfile.zipfile':718 '검토':778 '고쳐서':790 '내용이':780 '맞으면':781 '변경':796,798 '별도':803 '부탁드립니다':779 '서명':782,792 '서명본':801 '수정이':786 '없음':799 '없음이면':797 '전체가':795 '첨부된':774 '체크':791 '폼을':777 '필요하면':787 '항목을':789 '해당':788 '회신':785,794,800,804 '후':783,793","prices":[{"id":"1516e630-c274-4cf2-920b-d4b30eca0dff","listingId":"0e515ab9-f2a8-4ae8-bb69-243f8121f836","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"Aperivue","category":"medsci-skills","install_from":"skills.sh"},"createdAt":"2026-05-13T12:57:44.536Z"}],"sources":[{"listingId":"0e515ab9-f2a8-4ae8-bb69-243f8121f836","source":"github","sourceId":"Aperivue/medsci-skills/fill-icmje-coi","sourceUrl":"https://github.com/Aperivue/medsci-skills/tree/main/skills/fill-icmje-coi","isPrimary":false,"firstSeenAt":"2026-05-13T12:57:44.536Z","lastSeenAt":"2026-05-18T18:56:29.461Z"}],"details":{"listingId":"0e515ab9-f2a8-4ae8-bb69-243f8121f836","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"Aperivue","slug":"fill-icmje-coi","github":{"repo":"Aperivue/medsci-skills","stars":98,"topics":["agent-skills","biostatistics","claude-code","claude-skills","clinical-research","diagnostic-accuracy","irb-protocol","literature-review","manuscript","medical-ai","medical-research","meta-analysis","physician-researcher","prisma","pubmed","radiology","reporting-guidelines","strobe","systematic-review","tripod-ai"],"license":"other","html_url":"https://github.com/Aperivue/medsci-skills","pushed_at":"2026-05-17T20:50:52Z","description":"Claude Code skills for medical research — literature search, reporting guidelines, statistical analysis, publication figures. Built by a physician-researcher, tested on real publications. MIT licensed.","skill_md_sha":"a98304ce5a62f1d871375d3b502ab48462cfb5b2","skill_md_path":"skills/fill-icmje-coi/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/Aperivue/medsci-skills/tree/main/skills/fill-icmje-coi"},"layout":"multi","source":"github","category":"medsci-skills","frontmatter":{"name":"fill-icmje-coi","description":"Batch-generate per-author ICMJE Conflict of Interest Disclosure Forms (`coi_disclosure.docx`) for manuscript submission. Pre-fills all 13 disclosure items as \"☒ None\" + final certification ☒ using a synthetic seed template shipped with the skill, then clones the seed per author with Date, Name, and Manuscript Title replaced. Designed for the common case of hospital-based observational research where no author has real financial conflicts; the circulated forms become \"reply 변경 없음 + sign\" for most authors and only flag those who need to amend."},"skills_sh_url":"https://skills.sh/Aperivue/medsci-skills/fill-icmje-coi"},"updatedAt":"2026-05-18T18:56:29.461Z"}}