{"id":"a69ddd7f-70f1-4314-831b-3592c50e5752","shortId":"gXyFuw","kind":"skill","title":"Arize Experiment","tagline":"Awesome Copilot skill by Github","description":"# Arize Experiment Skill\n\n## Concepts\n\n- **Experiment** = a named evaluation run against a specific dataset version, containing one run per example\n- **Experiment Run** = the result of processing one dataset example -- includes the model output, optional evaluations, and optional metadata\n- **Dataset** = a versioned collection of examples; every experiment is tied to a dataset and a specific dataset version\n- **Evaluation** = a named metric attached to a run (e.g., `correctness`, `relevance`), with optional label, score, and explanation\n\nThe typical flow: export a dataset → process each example → collect outputs and evaluations → create an experiment with the runs.\n\n## Prerequisites\n\nProceed directly with the task — run the `ax` command you need. Do NOT check versions, env vars, or profiles upfront.\n\nIf an `ax` command fails, troubleshoot based on the error:\n- `command not found` or version error → see references/ax-setup.md\n- `401 Unauthorized` / missing API key → run `ax profiles show` to inspect the current profile. If the profile is missing or the API key is wrong: check `.env` for `ARIZE_API_KEY` and use it to create/update the profile via references/ax-profiles.md. If `.env` has no key either, ask the user for their Arize API key (https://app.arize.com/admin > API Keys)\n- Space ID unknown → check `.env` for `ARIZE_SPACE_ID`, or run `ax spaces list -o json`, or ask the user\n- Project unclear → check `.env` for `ARIZE_DEFAULT_PROJECT`, or ask, or run `ax projects list -o json --limit 100` and present as selectable options\n\n## List Experiments: `ax experiments list`\n\nBrowse experiments, optionally filtered by dataset. Output goes to stdout.\n\n```bash\nax experiments list\nax experiments list --dataset-id DATASET_ID --limit 20\nax experiments list --cursor CURSOR_TOKEN\nax experiments list -o json\n```\n\n### Flags\n\n| Flag | Type | Default | Description |\n|------|------|---------|-------------|\n| `--dataset-id` | string | none | Filter by dataset |\n| `--limit, -l` | int | 15 | Max results (1-100) |\n| `--cursor` | string | none | Pagination cursor from previous response |\n| `-o, --output` | string | table | Output format: table, json, csv, parquet, or file path |\n| `-p, --profile` | string | default | Configuration profile |\n\n## Get Experiment: `ax experiments get`\n\nQuick metadata lookup -- returns experiment name, linked dataset/version, and timestamps.\n\n```bash\nax experiments get EXPERIMENT_ID\nax experiments get EXPERIMENT_ID -o json\n```\n\n### Flags\n\n| Flag | Type | Default | Description |\n|------|------|---------|-------------|\n| `EXPERIMENT_ID` | string | required | Positional argument |\n| `-o, --output` | string | table | Output format |\n| `-p, --profile` | string | default | Configuration profile |\n\n### Response fields\n\n| Field | Type | Description |\n|-------|------|-------------|\n| `id` | string | Experiment ID |\n| `name` | string | Experiment name |\n| `dataset_id` | string | Linked dataset ID |\n| `dataset_version_id` | string | Specific dataset version used |\n| `experiment_traces_project_id` | string | Project where experiment traces are stored |\n| `created_at` | datetime | When the experiment was created |\n| `updated_at` | datetime | Last modification time |\n\n## Export Experiment: `ax experiments export`\n\nDownload all runs to a file. By default uses the REST API; pass `--all` to use Arrow Flight for bulk transfer.\n\n```bash\nax experiments export EXPERIMENT_ID\n# -> experiment_abc123_20260305_141500/runs.json\n\nax experiments export EXPERIMENT_ID --all\nax experiments export EXPERIMENT_ID --output-dir ./results\nax experiments export EXPERIMENT_ID --stdout\nax experiments export EXPERIMENT_ID --stdout | jq '.[0]'\n```\n\n### Flags\n\n| Flag | Type | Default | Description |\n|------|------|---------|-------------|\n| `EXPERIMENT_ID` | string | required | Positional argument |\n| `--all` | bool | false | Use Arrow Flight for bulk export (see below) |\n| `--output-dir` | string | `.` | Output directory |\n| `--stdout` | bool | false | Print JSON to stdout instead of file |\n| `-p, --profile` | string | default | Configuration profile |\n\n### REST vs Flight (`--all`)\n\n- **REST** (default): Lower friction -- no Arrow/Flight dependency, standard HTTPS ports, works through any corporate proxy or firewall. Limited to 500 runs per page.\n- **Flight** (`--all`): Required for experiments with more than 500 runs. Uses gRPC+TLS on a separate host/port (`flight.arize.com:443`) which some corporate networks may block.\n\n**Agent auto-escalation rule:** If a REST export returns exactly 500 runs, the result is likely truncated. Re-run with `--all` to get the full dataset.\n\nOutput is a JSON array of run objects:\n\n```json\n[\n  {\n    \"id\": \"run_001\",\n    \"example_id\": \"ex_001\",\n    \"output\": \"The answer is 4.\",\n    \"evaluations\": {\n      \"correctness\": { \"label\": \"correct\", \"score\": 1.0 },\n      \"relevance\": { \"score\": 0.95, \"explanation\": \"Directly answers the question\" }\n    },\n    \"metadata\": { \"model\": \"gpt-4o\", \"latency_ms\": 1234 }\n  }\n]\n```\n\n## Create Experiment: `ax experiments create`\n\nCreate a new experiment with runs from a data file.\n\n```bash\nax experiments create --name \"gpt-4o-baseline\" --dataset-id DATASET_ID --file runs.json\nax experiments create --name \"claude-test\" --dataset-id DATASET_ID --file runs.csv\n```\n\n### Flags\n\n| Flag | Type | Required | Description |\n|------|------|----------|-------------|\n| `--name, -n` | string | yes | Experiment name |\n| `--dataset-id` | string | yes | Dataset to run the experiment against |\n| `--file, -f` | path | yes | Data file with runs: CSV, JSON, JSONL, or Parquet |\n| `-o, --output` | string | no | Output format |\n| `-p, --profile` | string | no | Configuration profile |\n\n### Passing data via stdin\n\nUse `--file -` to pipe data directly — no temp file needed:\n\n```bash\necho '[{\"example_id\": \"ex_001\", \"output\": \"Paris\"}]' | ax experiments create --name \"my-experiment\" --dataset-id DATASET_ID --file -\n\n# Or with a heredoc\nax experiments create --name \"my-experiment\" --dataset-id DATASET_ID --file - << 'EOF'\n[{\"example_id\": \"ex_001\", \"output\": \"Paris\"}]\nEOF\n```\n\n### Required columns in the runs file\n\n| Column | Type | Required | Description |\n|--------|------|----------|-------------|\n| `example_id` | string | yes | ID of the dataset example this run corresponds to |\n| `output` | string | yes | The model/system output for this example |\n\nAdditional columns are passed through as `additionalProperties` on the run.\n\n## Delete Experiment: `ax experiments delete`\n\n```bash\nax experiments delete EXPERIMENT_ID\nax experiments delete EXPERIMENT_ID --force   # skip confirmation prompt\n```\n\n### Flags\n\n| Flag | Type | Default | Description |\n|------|------|---------|-------------|\n| `EXPERIMENT_ID` | string | required | Positional argument |\n| `--force, -f` | bool | false | Skip confirmation prompt |\n| `-p, --profile` | string | default | Configuration profile |\n\n## Experiment Run Schema\n\nEach run corresponds to one dataset example:\n\n```json\n{\n  \"example_id\": \"required -- links to dataset example\",\n  \"output\": \"required -- the model/system output for this example\",\n  \"evaluations\": {\n    \"metric_name\": {\n      \"label\": \"optional string label (e.g., 'correct', 'incorrect')\",\n      \"score\": \"optional numeric score (e.g., 0.95)\",\n      \"explanation\": \"optional freeform text\"\n    }\n  },\n  \"metadata\": {\n    \"model\": \"gpt-4o\",\n    \"temperature\": 0.7,\n    \"latency_ms\": 1234\n  }\n}\n```\n\n### Evaluation fields\n\n| Field | Type | Required | Description |\n|-------|------|----------|-------------|\n| `label` | string | no | Categorical classification (e.g., `correct`, `incorrect`, `partial`) |\n| `score` | number | no | Numeric quality score (e.g., 0.0 - 1.0) |\n| `explanation` | string | no | Freeform reasoning for the evaluation |\n\nAt least one of `label`, `score`, or `explanation` should be present per evaluation.\n\n## Workflows\n\n### Run an experiment against a dataset\n\n1. Find or create a dataset:\n   ```bash\n   ax datasets list\n   ax datasets export DATASET_ID --stdout | jq 'length'\n   ```\n2. Export the dataset examples:\n   ```bash\n   ax datasets export DATASET_ID\n   ```\n3. Process each example through your system, collecting outputs and evaluations\n4. Build a runs file (JSON array) with `example_id`, `output`, and optional `evaluations`:\n   ```json\n   [\n     {\"example_id\": \"ex_001\", \"output\": \"4\", \"evaluations\": {\"correctness\": {\"label\": \"correct\", \"score\": 1.0}}},\n     {\"example_id\": \"ex_002\", \"output\": \"Paris\", \"evaluations\": {\"correctness\": {\"label\": \"correct\", \"score\": 1.0}}}\n   ]\n   ```\n5. Create the experiment:\n   ```bash\n   ax experiments create --name \"gpt-4o-baseline\" --dataset-id DATASET_ID --file runs.json\n   ```\n6. Verify: `ax experiments get EXPERIMENT_ID`\n\n### Compare two experiments\n\n1. Export both experiments:\n   ```bash\n   ax experiments export EXPERIMENT_ID_A --stdout > a.json\n   ax experiments export EXPERIMENT_ID_B --stdout > b.json\n   ```\n2. Compare evaluation scores by `example_id`:\n   ```bash\n   # Average correctness score for experiment A\n   jq '[.[] | .evaluations.correctness.score] | add / length' a.json\n\n   # Same for experiment B\n   jq '[.[] | .evaluations.correctness.score] | add / length' b.json\n   ```\n3. Find examples where results differ:\n   ```bash\n   jq -s '.[0] as $a | .[1][] | . as $run |\n     {\n       example_id: $run.example_id,\n       b_score: $run.evaluations.correctness.score,\n       a_score: ($a[] | select(.example_id == $run.example_id) | .evaluations.correctness.score)\n     }' a.json b.json\n   ```\n4. Score distribution per evaluator (pass/fail/partial counts):\n   ```bash\n   # Count by label for experiment A\n   jq '[.[] | .evaluations.correctness.label] | group_by(.) | map({label: .[0], count: length})' a.json\n   ```\n5. Find regressions (examples that passed in A but fail in B):\n   ```bash\n   jq -s '\n     [.[0][] | select(.evaluations.correctness.label == \"correct\")] as $passed_a |\n     [.[1][] | select(.evaluations.correctness.label != \"correct\") |\n       select(.example_id as $id | $passed_a | any(.example_id == $id))\n     ]\n   ' a.json b.json\n   ```\n\n**Statistical significance note:** Score comparisons are most reliable with ≥ 30 examples per evaluator. With fewer examples, treat the delta as directional only — a 5% difference on n=10 may be noise. Report sample size alongside scores: `jq 'length' a.json`.\n\n### Download experiment results for analysis\n\n1. `ax experiments list --dataset-id DATASET_ID` -- find experiments\n2. `ax experiments export EXPERIMENT_ID` -- download to file\n3. Parse: `jq '.[] | {example_id, score: .evaluations.correctness.score}' experiment_*/runs.json`\n\n### Pipe export to other tools\n\n```bash\n# Count runs\nax experiments export EXPERIMENT_ID --stdout | jq 'length'\n\n# Extract all outputs\nax experiments export EXPERIMENT_ID --stdout | jq '.[].output'\n\n# Get runs with low scores\nax experiments export EXPERIMENT_ID --stdout | jq '[.[] | select(.evaluations.correctness.score < 0.5)]'\n\n# Convert to CSV\nax experiments export EXPERIMENT_ID --stdout | jq -r '.[] | [.example_id, .output, .evaluations.correctness.score] | @csv'\n```\n\n## Related Skills\n\n- **arize-dataset**: Create or export the dataset this experiment runs against → use `arize-dataset` first\n- **arize-prompt-optimization**: Use experiment results to improve prompts → next step is `arize-prompt-optimization`\n- **arize-trace**: Inspect individual span traces for failing experiment runs → use `arize-trace`\n- **arize-link**: Generate clickable UI links to traces from experiment runs → use `arize-link`\n\n## Troubleshooting\n\n| Problem | Solution |\n|---------|----------|\n| `ax: command not found` | See references/ax-setup.md |\n| `401 Unauthorized` | API key is wrong, expired, or doesn't have access to this space. Fix the profile using references/ax-profiles.md. |\n| `No profile found` | No profile is configured. See references/ax-profiles.md to create one. |\n| `Experiment not found` | Verify experiment ID with `ax experiments list` |\n| `Invalid runs file` | Each run must have `example_id` and `output` fields |\n| `example_id mismatch` | Ensure `example_id` values match IDs from the dataset (export dataset to verify) |\n| `No runs found` | Export returned empty -- verify experiment has runs via `ax experiments get` |\n| `Dataset not found` | The linked dataset may have been deleted; check with `ax datasets list` |\n\n## Save Credentials for Future Use\n\nSee references/ax-profiles.md § Save Credentials for Future Use.","tags":["arize","experiment","awesome","copilot","github"],"capabilities":["skill","source-github","category-awesome-copilot"],"categories":["awesome-copilot"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/github/awesome-copilot/arize-experiment","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"install_from":"skills.sh"}},"qualityScore":"0.300","qualityRationale":"deterministic score 0.30 from registry signals: · indexed on skills.sh · published under github/awesome-copilot","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:v1","enrichmentVersion":1,"enrichedAt":"2026-04-22T03:40:38.175Z","embedding":null,"createdAt":"2026-04-18T20:36:12.855Z","updatedAt":"2026-04-22T03:40:38.175Z","lastSeenAt":"2026-04-22T03:40:38.175Z","tsv":"'-100':301 '/admin':194 '/results':482 '/runs.json':1335 '0':496,1176,1220,1239 '0.0':979 '0.5':1377 '0.7':953 '0.95':649,942 '001':631,635,774,811,1067 '002':1079 '1':300,1009,1118,1179,1246,1307 '1.0':646,980,1075,1087 '10':1290 '100':235 '1234':662,956 '141500/runs.json':467 '15':297 '2':1027,1139,1318 '20':269 '20260305':466 '3':1038,1167,1327 '30':1272 '4':640,1049,1069,1200 '401':138,1470 '4o':659,685,951,1099 '5':1088,1224,1286 '500':564,576,603 '6':1108 'a.json':1130,1157,1198,1223,1261,1301 'abc123':465 'access':1481 'add':1155,1164 'addit':847 'additionalproperti':853 'agent':592 'alongsid':1297 'analysi':1306 'answer':638,652 'api':141,159,167,190,195,448,1472 'app.arize.com':193 'app.arize.com/admin':192 'argument':367,507,887 'ariz':1,8,166,189,203,222,1397,1410,1414,1427,1431,1443,1446,1459 'arize-dataset':1396,1409 'arize-link':1445,1458 'arize-prompt-optim':1413,1426 'arize-trac':1430,1442 'array':624,1055 'arrow':453,512 'arrow/flight':550 'ask':184,214,226 'attach':67 'auto':594 'auto-escal':593 'averag':1147 'awesom':3 'ax':107,122,144,208,229,243,257,260,270,276,331,345,350,434,459,468,474,483,489,665,679,694,777,794,859,863,868,1016,1019,1033,1093,1110,1123,1131,1308,1319,1344,1355,1368,1381,1464,1509,1551,1566 'b':1136,1161,1186,1235 'b.json':1138,1166,1199,1262 'base':126 'baselin':686,1100 'bash':256,344,458,678,769,862,1015,1032,1092,1122,1146,1173,1207,1236,1341 'block':591 'bool':509,526,890 'brows':246 'build':1050 'bulk':456,515 'categor':966 'category-awesome-copilot' 'check':113,163,200,219,1564 'classif':967 'claud':699 'claude-test':698 'clickabl':1449 'collect':48,89,1045 'column':816,821,848 'command':108,123,130,1465 'compar':1115,1140 'comparison':1267 'concept':11 'configur':327,378,539,753,899,1496 'confirm':875,893 'contain':22 'convert':1378 'copilot':4 'corpor':558,588 'correct':72,642,644,935,969,1071,1073,1083,1085,1148,1242,1249 'correspond':836,906 'count':1206,1208,1221,1342 'creat':93,418,425,663,667,668,681,696,779,796,1012,1089,1095,1399,1500 'create/update':173 'credenti':1570,1577 'csv':318,738,1380,1393 'current':150 'cursor':273,274,302,306 'data':676,734,756,763 'dataset':20,34,45,57,61,85,251,264,266,287,293,393,397,399,404,619,688,690,702,704,720,724,785,787,802,804,832,909,917,1008,1014,1017,1020,1022,1030,1034,1036,1102,1104,1312,1314,1398,1403,1411,1535,1537,1554,1559,1567 'dataset-id':263,286,687,701,719,784,801,1101,1311 'dataset/version':341 'datetim':420,428 'default':223,284,326,360,377,444,500,538,546,880,898 'delet':857,861,865,870,1563 'delta':1281 'depend':551 'descript':285,361,384,501,712,824,881,962 'differ':1172,1287 'dir':481,521 'direct':101,651,764,1283 'directori':524 'distribut':1202 'doesn':1478 'download':437,1302,1324 'e.g':71,934,941,968,978 'echo':770 'either':183 'empti':1545 'ensur':1527 'env':115,164,179,201,220 'eof':807,814 'error':129,135 'escal':595 'evalu':15,41,63,92,641,927,957,988,1001,1048,1062,1070,1082,1141,1204,1275 'evaluations.correctness.label':1215,1241,1248 'evaluations.correctness.score':1154,1163,1197,1333,1376,1392 'everi':51 'ex':634,773,810,1066,1078 'exact':602 'exampl':26,35,50,88,632,771,808,825,833,846,910,912,918,926,1031,1041,1057,1064,1076,1144,1169,1182,1193,1227,1251,1258,1273,1278,1330,1389,1519,1524,1528 'experi':2,9,12,27,52,95,242,244,247,258,261,271,277,330,332,338,346,348,351,353,362,387,391,407,414,423,433,435,460,462,464,469,471,475,477,484,486,490,492,502,572,664,666,671,680,695,717,728,778,783,795,800,858,860,864,866,869,871,882,901,1005,1091,1094,1111,1113,1117,1121,1124,1126,1132,1134,1151,1160,1212,1303,1309,1317,1320,1322,1334,1345,1347,1356,1358,1369,1371,1382,1384,1405,1418,1439,1455,1502,1506,1510,1547,1552 'expir':1476 'explan':79,650,943,981,996 'export':83,432,436,461,470,476,485,491,516,600,1021,1028,1035,1119,1125,1133,1321,1337,1346,1357,1370,1383,1401,1536,1543 'extract':1352 'f':731,889 'fail':124,1233,1438 'fals':510,527,891 'fewer':1277 'field':381,382,958,959,1523 'file':321,442,534,677,692,706,730,735,760,767,789,806,820,1053,1106,1326,1514 'filter':249,291 'find':1010,1168,1225,1316 'firewal':561 'first':1412 'fix':1485 'flag':281,282,357,358,497,498,708,709,877,878 'flight':454,513,543,568 'flight.arize.com:443':585 'flow':82 'forc':873,888 'format':315,373,748 'found':132,1467,1492,1504,1542,1556 'freeform':945,984 'friction':548 'full':618 'futur':1572,1579 'generat':1448 'get':329,333,347,352,616,1112,1363,1553 'github':7 'goe':253 'gpt':658,684,950,1098 'gpt-4o':657,949 'gpt-4o-baseline':683,1097 'group':1216 'grpc':579 'heredoc':793 'host/port':584 'https':553 'id':198,205,265,267,288,349,354,363,385,388,394,398,401,410,463,472,478,487,493,503,629,633,689,691,703,705,721,772,786,788,803,805,809,826,829,867,872,883,913,1023,1037,1058,1065,1077,1103,1105,1114,1127,1135,1145,1183,1185,1194,1196,1252,1254,1259,1260,1313,1315,1323,1331,1348,1359,1372,1385,1390,1507,1520,1525,1529,1532 'improv':1421 'includ':36 'incorrect':936,970 'individu':1434 'inspect':148,1433 'instead':532 'int':296 'invalid':1512 'jq':495,1025,1153,1162,1174,1214,1237,1299,1329,1350,1361,1374,1387 'json':212,233,280,317,356,529,623,628,739,911,1054,1063 'jsonl':740 'key':142,160,168,182,191,196,1473 'l':295 'label':76,643,930,933,963,993,1072,1084,1210,1219 'last':429 'latenc':660,954 'least':990 'length':1026,1156,1165,1222,1300,1351 'like':608 'limit':234,268,294,562 'link':340,396,915,1447,1451,1460,1558 'list':210,231,241,245,259,262,272,278,1018,1310,1511,1568 'lookup':336 'low':1366 'lower':547 'map':1218 'match':1531 'max':298 'may':590,1291,1560 'metadata':44,335,655,947 'metric':66,928 'mismatch':1526 'miss':140,156 'model':38,656,948 'model/system':842,922 'modif':430 'ms':661,955 'must':1517 'my-experi':781,798 'n':714,1289 'name':14,65,339,389,392,682,697,713,718,780,797,929,1096 'need':110,768 'network':589 'new':670 'next':1423 'nois':1293 'none':290,304 'note':1265 'number':973 'numer':939,975 'o':211,232,279,310,355,368,743 'object':627 'one':23,33,908,991,1501 'optim':1416,1429 'option':40,43,75,240,248,931,938,944,1061 'output':39,90,252,311,314,369,372,480,520,523,620,636,744,747,775,812,838,843,919,923,1046,1059,1068,1080,1354,1362,1391,1522 'output-dir':479,519 'p':323,374,535,749,895 'page':567 'pagin':305 'pari':776,813,1081 'parquet':319,742 'pars':1328 'partial':971 'pass':449,755,850,1229,1244,1255 'pass/fail/partial':1205 'path':322,732 'per':25,566,1000,1203,1274 'pipe':762,1336 'port':554 'posit':366,506,886 'prerequisit':99 'present':237,999 'previous':308 'print':528 'problem':1462 'proceed':100 'process':32,86,1039 'profil':118,145,151,154,175,324,328,375,379,536,540,750,754,896,900,1487,1491,1494 'project':217,224,230,409,412 'prompt':876,894,1415,1422,1428 'proxi':559 'qualiti':976 'question':654 'quick':334 'r':1388 're':611 're-run':610 'reason':985 'references/ax-profiles.md':177,1489,1498,1575 'references/ax-setup.md':137,1469 'regress':1226 'relat':1394 'relev':73,647 'reliabl':1270 'report':1294 'requir':365,505,570,711,815,823,885,914,920,961 'respons':309,380 'rest':447,541,545,599 'result':30,299,606,1171,1304,1419 'return':337,601,1544 'rule':596 'run':16,24,28,70,98,105,143,207,228,439,565,577,604,612,626,630,673,726,737,819,835,856,902,905,1003,1052,1181,1343,1364,1406,1440,1456,1513,1516,1541,1549 'run.evaluations.correctness.score':1188 'run.example':1184,1195 'runs.csv':707 'runs.json':693,1107 'sampl':1295 'save':1569,1576 'schema':903 'score':77,645,648,937,940,972,977,994,1074,1086,1142,1149,1187,1190,1201,1266,1298,1332,1367 'see':136,517,1468,1497,1574 'select':239,1192,1240,1247,1250,1375 'separ':583 'show':146 'signific':1264 'size':1296 'skill':5,10,1395 'skip':874,892 'solut':1463 'source-github' 'space':197,204,209,1484 'span':1435 'specif':19,60,403 'standard':552 'statist':1263 'stdin':758 'stdout':255,488,494,525,531,1024,1129,1137,1349,1360,1373,1386 'step':1424 'store':417 'string':289,303,312,325,364,370,376,386,390,395,402,411,504,522,537,715,722,745,751,827,839,884,897,932,964,982 'system':1044 'tabl':313,316,371 'task':104 'temp':766 'temperatur':952 'test':700 'text':946 'tie':54 'time':431 'timestamp':343 'tls':580 'token':275 'tool':1340 'trace':408,415,1432,1436,1444,1453 'transfer':457 'treat':1279 'troubleshoot':125,1461 'truncat':609 'two':1116 'type':283,359,383,499,710,822,879,960 'typic':81 'ui':1450 'unauthor':139,1471 'unclear':218 'unknown':199 'updat':426 'upfront':119 'use':170,406,445,452,511,578,759,1408,1417,1441,1457,1488,1573,1580 'user':186,216 'valu':1530 'var':116 'verifi':1109,1505,1539,1546 'version':21,47,62,114,134,400,405 'via':176,757,1550 'vs':542 'work':555 'workflow':1002 'wrong':162,1475 'yes':716,723,733,828,840","prices":[{"id":"4091a094-ead3-4aea-8997-7ddbce1475a3","listingId":"a69ddd7f-70f1-4314-831b-3592c50e5752","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"github","category":"awesome-copilot","install_from":"skills.sh"},"createdAt":"2026-04-18T20:36:12.855Z"}],"sources":[{"listingId":"a69ddd7f-70f1-4314-831b-3592c50e5752","source":"github","sourceId":"github/awesome-copilot/arize-experiment","sourceUrl":"https://github.com/github/awesome-copilot/tree/main/skills/arize-experiment","isPrimary":false,"firstSeenAt":"2026-04-18T21:48:15.334Z","lastSeenAt":"2026-04-22T00:52:03.771Z"},{"listingId":"a69ddd7f-70f1-4314-831b-3592c50e5752","source":"skills_sh","sourceId":"github/awesome-copilot/arize-experiment","sourceUrl":"https://skills.sh/github/awesome-copilot/arize-experiment","isPrimary":true,"firstSeenAt":"2026-04-18T20:36:12.855Z","lastSeenAt":"2026-04-22T03:40:38.175Z"}],"details":{"listingId":"a69ddd7f-70f1-4314-831b-3592c50e5752","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"github","slug":"arize-experiment","source":"skills_sh","category":"awesome-copilot","skills_sh_url":"https://skills.sh/github/awesome-copilot/arize-experiment"},"updatedAt":"2026-04-22T03:40:38.175Z"}}