{"id":"64ffcfc7-1309-4113-9c71-6022d1888bee","shortId":"5ywqyq","kind":"skill","title":"canvas-peer-review-manager","tagline":"Educator peer review management for Canvas LMS. Tracks completion rates, analyzes comment quality, flags problematic reviews, sends targeted reminders, and generates instructor-ready reports. Trigger phrases include \"peer review status\", \"how are peer reviews going\", \"who hasn't ","description":"# Canvas Peer Review Manager\n\nA complete peer review management workflow for educators using Canvas LMS. Monitor completion, analyze quality, identify students who need follow-up, send reminders, and export data -- all through MCP tool calls against the Canvas API.\n\n## Prerequisites\n\n- **Canvas MCP server** must be running and connected to the agent's MCP client (e.g., Claude Code, Cursor, Codex, OpenCode).\n- The authenticated user must have an **educator or instructor role** in the target Canvas course.\n- The assignment must have **peer reviews enabled** in Canvas (either manual or automatic assignment).\n- **FERPA compliance**: Set `ENABLE_DATA_ANONYMIZATION=true` in the Canvas MCP server environment to anonymize student names. When enabled, names render as `Student_xxxxxxxx` hashes while preserving functional user IDs for messaging.\n\n## Steps\n\n### 1. Identify the Assignment\n\nAsk the user which course and assignment to manage peer reviews for. Accept a course code, Canvas ID, or course name, plus an assignment name or ID.\n\nIf the user does not specify, prompt:\n\n> Which course and assignment would you like to check peer reviews for?\n\nUse `list_courses` and `list_assignments` to help the user find the right identifiers.\n\n### 2. Check Peer Review Completion\n\nCall `get_peer_review_completion_analytics` with the course identifier and assignment ID. This returns:\n\n- Overall completion rate (percentage)\n- Number of students with all reviews complete, partial, and none complete\n- Per-student breakdown showing completed vs. assigned reviews\n\n**Key data points to surface:**\n\n| Metric | What It Tells You |\n|--------|-------------------|\n| Completion rate | Overall health of the peer review cycle |\n| \"None complete\" count | Students who haven't started -- highest priority for reminders |\n| \"Partial complete\" count | Students who started but didn't finish |\n| Per-student breakdown | Exactly who needs follow-up |\n\n### 3. Review the Assignment Mapping\n\nIf the user wants to understand who is reviewing whom, call `get_peer_review_assignments` with:\n\n- `include_names=true` for human-readable output\n- `include_submission_details=true` for submission context\n\nThis shows the full reviewer-to-reviewee mapping with completion status.\n\n### 4. Extract and Read Comments\n\nCall `get_peer_review_comments` to retrieve actual comment text. Parameters:\n\n- `include_reviewer_info=true` -- who wrote the comment\n- `include_reviewee_info=true` -- who received the comment\n- `anonymize_students=true` -- recommended when sharing results or working with sensitive data\n\nThis reveals what students actually wrote in their reviews.\n\n### 5. Analyze Comment Quality\n\nCall `analyze_peer_review_quality` to generate quality metrics across all reviews. The analysis includes:\n\n- **Average quality score** (1-5 scale)\n- **Word count statistics** (mean, median, range)\n- **Constructiveness analysis** (constructive feedback vs. generic comments vs. specific suggestions)\n- **Sentiment distribution** (positive, neutral, negative)\n- **Flagged reviews** that fall below quality thresholds\n\nOptionally pass `analysis_criteria` as a JSON string to customize what counts as high/low quality.\n\n### 6. Flag Problematic Reviews\n\nCall `identify_problematic_peer_reviews` to automatically flag reviews needing instructor attention. Flagging criteria include:\n\n- Very short or empty comments\n- Generic responses (e.g., \"looks good\", \"nice work\")\n- Lack of constructive feedback\n- Potential copy-paste or identical reviews\n\nPass custom `criteria` as a JSON string to override default thresholds.\n\n### 7. Get the Follow-up List\n\nCall `get_peer_review_followup_list` to get a prioritized list of students requiring action:\n\n- `priority_filter=\"urgent\"` -- students with zero reviews completed\n- `priority_filter=\"medium\"` -- students with partial completion\n- `priority_filter=\"all\"` -- everyone who needs follow-up\n- `days_threshold=3` -- adjusts urgency calculation based on days since assignment\n\n### 8. Send Reminders\n\n**Always use a dry run or review step before sending messages.**\n\nFor targeted reminders, call `send_peer_review_reminders` with:\n\n- `recipient_ids` -- list of Canvas user IDs from the analytics results\n- `custom_message` -- optional custom text (a default template is used if omitted)\n- `subject_prefix` -- defaults to \"Peer Review Reminder\"\n\nExample flow:\n\n1. Get incomplete reviewers from step 2\n2. Extract their user IDs\n3. Review the recipient list with the user\n4. Send reminders after confirmation\n\nFor a fully automated pipeline, call `send_peer_review_followup_campaign` with just the course identifier and assignment ID. This tool:\n\n1. Runs completion analytics automatically\n2. Segments students into \"urgent\" (none complete) and \"partial\" groups\n3. Sends appropriately toned reminders to each group\n4. Returns combined analytics and messaging results\n\n**Warning:** The campaign tool sends real messages. Always confirm with the instructor before running it.\n\n### 9. Export Data\n\nCall `extract_peer_review_dataset` to export all peer review data for external analysis:\n\n- `output_format=\"csv\"` or `output_format=\"json\"`\n- `include_analytics=true` -- appends quality metrics to the export\n- `anonymize_data=true` -- recommended for sharing or archival\n- `save_locally=true` -- saves to a local file; set to `false` to return data inline\n\n### 10. Generate Instructor Reports\n\nCall `generate_peer_review_feedback_report` for a formatted, shareable report:\n\n- `report_type=\"comprehensive\"` -- full analysis with samples of low-quality reviews\n- `report_type=\"summary\"` -- executive overview only\n- `report_type=\"individual\"` -- per-student breakdown\n- `include_student_names=false` -- recommended for FERPA compliance\n\nFor a completion-focused report (rather than quality-focused), use `generate_peer_review_report` with options for executive summary, student details, action items, and timeline analysis. This report can be saved to a file with `save_to_file=true`.\n\n## Use Cases\n\n**\"How are peer reviews going?\"**\nRun steps 1-2. Present completion rate, highlight any concerning patterns (e.g., \"Only 60% complete, 8 students haven't started\").\n\n**\"Who hasn't done their reviews?\"**\nRun steps 1-2, then step 7 with `priority_filter=\"urgent\"`. List the students who need follow-up.\n\n**\"Are the reviews any good?\"**\nRun steps 4-6. Present quality scores, flag generic or low-effort reviews, and surface recommendations.\n\n**\"Send reminders to stragglers\"**\nRun steps 1-2 to identify incomplete reviewers, then step 8. Always confirm the recipient list before sending.\n\n**\"Give me a full report\"**\nRun steps 2, 5, 6, and 10. Combine completion analytics with quality analysis into a comprehensive instructor report.\n\n**\"Export everything for my records\"**\nRun step 9 with `output_format=\"csv\"` and `anonymize_data=true` for a FERPA-safe dataset.\n\n## MCP Tools Used\n\n| Tool | Purpose |\n|------|---------|\n| `list_courses` | Discover active courses |\n| `list_assignments` | Find assignments with peer reviews enabled |\n| `get_peer_review_assignments` | Full reviewer-to-reviewee mapping |\n| `get_peer_review_completion_analytics` | Completion rates and per-student breakdown |\n| `get_peer_review_comments` | Extract actual comment text |\n| `analyze_peer_review_quality` | Quality metrics (scores, word counts, constructiveness) |\n| `identify_problematic_peer_reviews` | Flag low-quality or empty reviews |\n| `get_peer_review_followup_list` | Prioritized list of students needing follow-up |\n| `send_peer_review_reminders` | Send targeted reminder messages |\n| `send_peer_review_followup_campaign` | Automated analytics-to-messaging pipeline |\n| `extract_peer_review_dataset` | Export data as CSV or JSON |\n| `generate_peer_review_feedback_report` | Quality-focused instructor report |\n| `generate_peer_review_report` | Completion-focused instructor report |\n\n## Example\n\n**User:** \"How are peer reviews going for Assignment 3 in BADM 350?\"\n\n**Agent:** Calls `get_peer_review_completion_analytics` and presents:\n\n```\n## Peer Review Status: Assignment 3\n\n- **Completion rate:** 72% (23/32 students fully complete)\n- **Partial:** 5 students (started but not finished)\n- **Not started:** 4 students\n\n### Students Needing Follow-up\n**Not started (urgent):**\n- Student_a8f7e23 (0 of 3 reviews done)\n- Student_b2c91d4 (0 of 3 reviews done)\n- Student_f5e67a1 (0 of 3 reviews done)\n- Student_d9c34b2 (0 of 3 reviews done)\n\n**Partial (needs nudge):**\n- Student_c1d82e5 (1 of 3 reviews done)\n- Student_e4f03a9 (2 of 3 reviews done)\n```\n\n**User:** \"Send reminders to the ones who haven't started\"\n\n**Agent:** Confirms the 4 recipients, then calls `send_peer_review_reminders` with their user IDs.\n\n**User:** \"Now check if the completed reviews are any good\"\n\n**Agent:** Calls `analyze_peer_review_quality` and presents quality scores, flags 3 reviews as too short, and recommends the instructor follow up with specific students.\n\n## Safety Guidelines\n\n- **Confirm before sending** -- Always present the recipient list and message content to the instructor before calling any messaging tool.\n- **Use dry runs** -- When testing workflows, start with a single recipient or confirm the output of analytics tools before acting on the data.\n- **Anonymize by default** -- Use `anonymize_students=true` or `anonymize_data=true` when reviewing data in shared contexts.\n- **Respect rate limits** -- The Canvas API allows roughly 700 requests per 10 minutes. For large courses, the messaging tools send messages sequentially with built-in delays.\n- **FERPA compliance** -- Never display student names in logs, shared screens, or exported files unless the instructor has explicitly confirmed the context is appropriate.\n\n## Notes\n\n- Peer reviews must be enabled on the assignment in Canvas before any of these tools return data.\n- The `send_peer_review_followup_campaign` tool combines analytics and messaging into one call -- powerful but sends real messages. Use it only after confirming intent with the instructor.\n- Quality analysis uses heuristics (word count, keyword matching, sentiment). It identifies likely low-quality reviews but is not a substitute for instructor judgment.\n- This skill pairs well with `canvas-morning-check` for a full course health overview that includes peer review status alongside submission rates and grade distribution.","tags":["canvas","peer","review","manager","mcp","vishalsachdev","agent-skills","skills-sh"],"capabilities":["skill","source-vishalsachdev","skill-canvas-peer-review-manager","topic-agent-skills","topic-skills-sh"],"categories":["canvas-mcp"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/vishalsachdev/canvas-mcp/canvas-peer-review-manager","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add vishalsachdev/canvas-mcp","source_repo":"https://github.com/vishalsachdev/canvas-mcp","install_from":"skills.sh"}},"qualityScore":"0.509","qualityRationale":"deterministic score 0.51 from registry signals: · indexed on github topic:agent-skills · 118 github stars · SKILL.md body (10,340 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":"2026-05-02T12:55:01.598Z","embedding":null,"createdAt":"2026-04-18T22:12:05.935Z","updatedAt":"2026-05-02T12:55:01.598Z","lastSeenAt":"2026-05-02T12:55:01.598Z","tsv":"'-2':907,933,978 '-5':451 '-6':957 '0':1223,1230,1237,1244 '1':168,450,661,707,906,932,977,1254 '10':808,1004,1398 '2':232,667,668,712,1000,1261 '23/32':1198 '3':327,597,673,722,1177,1194,1225,1232,1239,1246,1256,1263,1312 '350':1180 '4':375,681,730,956,1211,1279 '5':428,1001,1203 '6':496,1002 '60':917 '7':549,936 '700':1395 '72':1197 '8':606,919,985 '9':752,1023 'a8f7e23':1222 'accept':184 'across':441 'act':1366 'action':570,879 'activ':1046 'actual':387,423,1083 'adjust':598 'agent':96,1181,1276,1301 'allow':1393 'alongsid':1527 'alway':609,744,986,1331 'analysi':445,460,483,768,827,883,1010,1484 'analyt':242,638,710,733,777,1007,1070,1135,1187,1363,1463 'analytics-to-messag':1134 'analyz':16,62,429,433,1086,1303 'anonym':140,149,407,785,1029,1370,1374,1378 'api':84,1392 'append':779 'appropri':724,1436 'archiv':792 'ask':172 'assign':122,134,171,178,195,209,223,248,274,330,346,605,703,1049,1051,1059,1176,1193,1445 'attent':511 'authent':107 'autom':689,1133 'automat':133,506,711 'averag':447 'b2c91d4':1229 'badm':1179 'base':601 'breakdown':270,320,847,1077 'built':1411 'built-in':1410 'c1d82e5':1253 'calcul':600 'call':80,237,342,380,432,500,556,623,691,755,812,1182,1282,1302,1343,1468 'campaign':696,739,1132,1460 'canva':2,11,45,58,83,86,119,129,144,188,633,1391,1447,1513 'canvas-morning-check':1512 'canvas-peer-review-manag':1 'case':898 'check':214,233,1293,1515 'claud':101 'client':99 'code':102,187 'codex':104 'combin':732,1005,1462 'comment':17,379,384,388,398,406,430,465,519,1081,1084 'complet':14,50,61,236,241,253,262,266,272,286,296,308,373,578,585,709,718,859,909,918,1006,1069,1071,1164,1186,1195,1201,1296 'completion-focus':858,1163 'complianc':136,855,1415 'comprehens':825,1013 'concern':913 'confirm':685,745,987,1277,1328,1359,1432,1478 'connect':93 'construct':459,461,529,1095 'content':1338 'context':362,1386,1434 'copi':533 'copy-past':532 'count':297,309,454,492,1094,1488 'cours':120,176,186,191,207,220,245,700,1044,1047,1402,1519 'criteria':484,513,540 'csv':771,1027,1146 'cursor':103 'custom':490,539,640,643 'cycl':294 'd9c34b2':1243 'data':75,139,277,418,754,765,786,806,1030,1144,1369,1379,1383,1454 'dataset':759,1037,1142 'day':595,603 'default':547,646,654,1372 'delay':1413 'detail':358,878 'didn':314 'discov':1045 'display':1417 'distribut':470,1532 'done':927,1227,1234,1241,1248,1258,1265 'dri':612,1348 'e.g':100,522,915 'e4f03a9':1260 'educ':6,56,112 'effort':966 'either':130 'empti':518,1105 'enabl':127,138,153,1055,1442 'environ':147 'everyon':589 'everyth':1017 'exact':321 'exampl':659,1168 'execut':838,875 'explicit':1431 'export':74,753,761,784,1016,1143,1425 'extern':767 'extract':376,669,756,1082,1139 'f5e67a1':1236 'fall':477 'fals':803,851 'feedback':462,530,816,1152 'ferpa':135,854,1035,1414 'ferpa-saf':1034 'file':800,891,895,1426 'filter':572,580,587,939 'find':228,1050 'finish':316,1208 'flag':19,474,497,507,512,961,1100,1311 'flow':660 'focus':860,866,1156,1165 'follow':69,325,553,593,947,1118,1216,1321 'follow-up':68,324,552,592,946,1117,1215 'followup':560,695,1110,1131,1459 'format':770,774,820,1026 'full':366,826,996,1060,1518 'fulli':688,1200 'function':162 'generat':26,438,809,813,868,1149,1159 'generic':464,520,962 'get':238,343,381,550,557,563,662,1056,1066,1078,1107,1183 'give':993 'go':41,903,1174 'good':524,953,1300 'grade':1531 'group':721,729 'guidelin':1327 'hash':159 'hasn':43,925 'haven':300,921,1273 'health':289,1520 'help':225 'heurist':1486 'high/low':494 'highest':303 'highlight':911 'human':353 'human-read':352 'id':164,189,198,249,630,635,672,704,1290 'ident':536 'identifi':64,169,231,246,501,701,980,1096,1493 'includ':33,348,356,391,399,446,514,776,848,1523 'incomplet':663,981 'individu':843 'info':393,401 'inlin':807 'instructor':28,114,510,748,810,1014,1157,1166,1320,1341,1429,1482,1505 'instructor-readi':27 'intent':1479 'item':880 'json':487,543,775,1148 'judgment':1506 'key':276 'keyword':1489 'lack':527 'larg':1401 'like':212,1494 'limit':1389 'list':219,222,555,561,566,631,677,941,990,1043,1048,1111,1113,1335 'lms':12,59 'local':794,799 'log':1421 'look':523 'low':832,965,1102,1496 'low-effort':964 'low-qual':831,1101,1495 'manag':5,9,48,53,180 'manual':131 'map':331,371,1065 'match':1490 'mcp':78,87,98,145,1038 'mean':456 'median':457 'medium':581 'messag':166,619,641,735,743,1127,1137,1337,1345,1404,1407,1465,1473 'metric':281,440,781,1091 'minut':1399 'monitor':60 'morn':1514 'must':89,109,123,1440 'name':151,154,192,196,349,850,1419 'need':67,323,509,591,945,1116,1214,1250 'negat':473 'neutral':472 'never':1416 'nice':525 'none':265,295,717 'note':1437 'nudg':1251 'number':256 'omit':651 'one':1271,1467 'opencod':105 'option':481,642,873 'output':355,769,773,1025,1361 'overal':252,288 'overrid':546 'overview':839,1521 'pair':1509 'paramet':390 'partial':263,307,584,720,1202,1249 'pass':482,538 'past':534 'pattern':914 'peer':3,7,34,39,46,51,125,181,215,234,239,292,344,382,434,503,558,625,656,693,757,763,814,869,901,1053,1057,1067,1079,1087,1098,1108,1121,1129,1140,1150,1160,1172,1184,1190,1284,1304,1438,1457,1524 'per':268,318,845,1075,1397 'per-stud':267,317,844,1074 'percentag':255 'phrase':32 'pipelin':690,1138 'plus':193 'point':278 'posit':471 'potenti':531 'power':1469 'prefix':653 'prerequisit':85 'present':908,958,1189,1308,1332 'preserv':161 'priorit':565,1112 'prioriti':304,571,579,586,938 'problemat':20,498,502,1097 'prompt':205 'purpos':1042 'qualiti':18,63,431,436,439,448,479,495,780,833,865,959,1009,1089,1090,1103,1155,1306,1309,1483,1497 'quality-focus':864,1154 'rang':458 'rate':15,254,287,910,1072,1196,1388,1529 'rather':862 'read':378 'readabl':354 'readi':29 'real':742,1472 'receiv':404 'recipi':629,676,989,1280,1334,1357 'recommend':410,788,852,970,1318 'record':1020 'remind':24,72,306,608,622,627,658,683,726,972,1123,1126,1268,1286 'render':155 'report':30,811,817,822,823,835,841,861,871,885,997,1015,1153,1158,1162,1167 'request':1396 'requir':569 'respect':1387 'respons':521 'result':413,639,736 'retriev':386 'return':251,731,805,1453 'reveal':420 'review':4,8,21,35,40,47,52,126,182,216,235,240,261,275,293,328,340,345,368,383,392,427,435,443,475,499,504,508,537,559,577,615,626,657,664,674,694,758,764,815,834,870,902,929,951,967,982,1054,1058,1062,1068,1080,1088,1099,1106,1109,1122,1130,1141,1151,1161,1173,1185,1191,1226,1233,1240,1247,1257,1264,1285,1297,1305,1313,1382,1439,1458,1498,1525 'reviewe':370,400,1064 'reviewer-to-reviewe':367,1061 'right':230 'role':115 'rough':1394 'run':91,613,708,750,904,930,954,975,998,1021,1349 'safe':1036 'safeti':1326 'sampl':829 'save':793,796,888,893 'scale':452 'score':449,960,1092,1310 'screen':1423 'segment':713 'send':22,71,607,618,624,682,692,723,741,971,992,1120,1124,1128,1267,1283,1330,1406,1456,1471 'sensit':417 'sentiment':469,1491 'sequenti':1408 'server':88,146 'set':137,801 'share':412,790,1385,1422 'shareabl':821 'short':516,1316 'show':271,364 'sinc':604 'singl':1356 'skill':1508 'skill-canvas-peer-review-manager' 'source-vishalsachdev' 'specif':467,1324 'specifi':204 'start':302,312,923,1205,1210,1219,1275,1353 'statist':455 'status':36,374,1192,1526 'step':167,616,666,905,931,935,955,976,984,999,1022 'straggler':974 'string':488,544 'student':65,150,157,258,269,298,310,319,408,422,568,574,582,714,846,849,877,920,943,1076,1115,1199,1204,1212,1213,1221,1228,1235,1242,1252,1259,1325,1375,1418 'subject':652 'submiss':357,361,1528 'substitut':1503 'suggest':468 'summari':837,876 'surfac':280,969 'target':23,118,621,1125 'tell':284 'templat':647 'test':1351 'text':389,644,1085 'threshold':480,548,596 'timelin':882 'tone':725 'tool':79,706,740,1039,1041,1346,1364,1405,1452,1461 'topic-agent-skills' 'topic-skills-sh' 'track':13 'trigger':31 'true':141,350,359,394,402,409,778,787,795,896,1031,1376,1380 'type':824,836,842 'understand':337 'unless':1427 'urgenc':599 'urgent':573,716,940,1220 'use':57,218,610,649,867,897,1040,1347,1373,1474,1485 'user':108,163,174,201,227,334,634,671,680,1169,1266,1289,1291 'vs':273,463,466 'want':335 'warn':737 'well':1510 'word':453,1093,1487 'work':415,526 'workflow':54,1352 'would':210 'wrote':396,424 'xxxxxxxx':158 'zero':576","prices":[{"id":"765a927c-c58f-47b2-80b7-8137763db54e","listingId":"64ffcfc7-1309-4113-9c71-6022d1888bee","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"vishalsachdev","category":"canvas-mcp","install_from":"skills.sh"},"createdAt":"2026-04-18T22:12:05.935Z"}],"sources":[{"listingId":"64ffcfc7-1309-4113-9c71-6022d1888bee","source":"github","sourceId":"vishalsachdev/canvas-mcp/canvas-peer-review-manager","sourceUrl":"https://github.com/vishalsachdev/canvas-mcp/tree/main/skills/canvas-peer-review-manager","isPrimary":false,"firstSeenAt":"2026-04-18T22:12:05.935Z","lastSeenAt":"2026-05-02T12:55:01.598Z"}],"details":{"listingId":"64ffcfc7-1309-4113-9c71-6022d1888bee","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"vishalsachdev","slug":"canvas-peer-review-manager","github":{"repo":"vishalsachdev/canvas-mcp","stars":118,"topics":["agent-skills","skills-sh"],"license":"mit","html_url":"https://github.com/vishalsachdev/canvas-mcp","pushed_at":"2026-04-27T16:16:22Z","description":"Canvas LMS MCP server — 80+ tools and 5 agent skills for students & educators. Works with Claude, Cursor, Codex, and 40+ agents. v1.1.0","skill_md_sha":"68d26c6f7eb5899f9c93289c67bbab3388725062","skill_md_path":"skills/canvas-peer-review-manager/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/vishalsachdev/canvas-mcp/tree/main/skills/canvas-peer-review-manager"},"layout":"multi","source":"github","category":"canvas-mcp","frontmatter":{"name":"canvas-peer-review-manager","description":"Educator peer review management for Canvas LMS. Tracks completion rates, analyzes comment quality, flags problematic reviews, sends targeted reminders, and generates instructor-ready reports. Trigger phrases include \"peer review status\", \"how are peer reviews going\", \"who hasn't reviewed\", \"review quality\", or any peer review follow-up task."},"skills_sh_url":"https://skills.sh/vishalsachdev/canvas-mcp/canvas-peer-review-manager"},"updatedAt":"2026-05-02T12:55:01.598Z"}}