{"id":"c0b47fea-02dd-4401-9b4b-538bbc2aa5ef","shortId":"r3LLLd","kind":"skill","title":"resemble-detect","tagline":"Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using Resemble AI","description":"# Resemble Detect — Deepfake Detection & Media Safety\n\nAnalyze audio, image, video, and text for synthetic manipulation, AI-generated content, watermarks, speaker identity, and media intelligence using the Resemble AI platform.\n\n## Core Principle — THE IRON LAW\n\n**\"NEVER DECLARE MEDIA AS REAL OR FAKE WITHOUT A COMPLETED DETECTION RESULT.\"**\n\nDo not guess, infer, or speculate about media authenticity. Every authenticity claim must be backed by a completed Resemble detect job with a returned `label`, `score`, and `status: \"completed\"`. If the detection is still `processing`, wait. If it `failed`, say so — do not substitute your own judgment.\n\n## When to Use\n\nUse this skill whenever the user's request involves any of these:\n\n- Checking if audio, video, image, or text is AI-generated or manipulated\n- Detecting deepfakes in any media format\n- Verifying media authenticity or provenance\n- Identifying which AI platform synthesized audio (source tracing)\n- Applying or detecting watermarks on media\n- Analyzing media for speaker info, emotion, transcription, or misinformation\n- Asking natural-language questions about detection results\n- Matching or verifying speaker identity against known voice profiles\n- Detecting AI-generated or machine-written text\n- Any mention of: \"deepfake\", \"fake detection\", \"synthetic media\", \"voice verification\", \"watermark\", \"media forensics\", \"authenticity check\", \"source tracing\", \"is this real\", \"AI-written text\", \"text detection\"\n\n**Do NOT use** for text-to-speech generation, voice cloning, or speech-to-text transcription — those are separate Resemble capabilities.\n\n## Capability Decision Tree\n\n| User wants to...                                      | Use this                  | API endpoint                          |\n|-------------------------------------------------------|---------------------------|---------------------------------------|\n| Check if media is AI-generated / deepfake             | **Deepfake Detection**    | `POST /detect`                        |\n| Know *which AI platform* made fake audio              | **Audio Source Tracing**  | `POST /detect` with flag              |\n| Get speaker info, emotion, transcription from media   | **Intelligence**          | `POST /intelligence`                  |\n| Ask questions about a completed detection             | **Detect Intelligence**   | `POST /detects/{uuid}/intelligence`   |\n| Apply an invisible watermark to media                 | **Watermark Apply**       | `POST /watermark/apply`               |\n| Check if media contains a watermark                   | **Watermark Detect**      | `POST /watermark/detect`              |\n| Verify a speaker's identity against known profiles    | **Identity Search**       | `POST /identity/search`               |\n| Check if text is AI-generated                         | **Text Detection**        | `POST /text_detect`                   |\n| Create a voice identity profile for future matching   | **Identity Create**       | `POST /identity`                      |\n\nWhen multiple capabilities apply (e.g., user wants deepfake detection AND intelligence), combine them in a single `POST /detect` call using the `intelligence: true` flag rather than making separate requests.\n\n## Required Setup\n\n- **API Key**: Bearer token from the Resemble AI dashboard (set as `RESEMBLE_API_KEY`)\n- **Base URL**: `https://app.resemble.ai/api/v2`\n- **Auth Header**: `Authorization: Bearer <RESEMBLE_API_KEY>`\n- **Media Requirement**: All media must be at a publicly accessible HTTPS URL\n\nIf the user provides a local file path instead of a URL, inform them the file must be hosted at a public HTTPS URL first. Do not attempt to upload local files to the API. (Exception: `POST /text_detect` accepts text content inline.)\n\n## MCP Tools Available\n\nWhen the Resemble MCP server is connected, use these tools instead of raw API calls:\n\n| Tool                      | Purpose                                           |\n|---------------------------|---------------------------------------------------|\n| `resemble_docs_lookup`    | Get comprehensive docs for any detect sub-topic   |\n| `resemble_search`         | Search across all documentation                   |\n| `resemble_api_endpoint`   | Get exact OpenAPI spec for any endpoint           |\n| `resemble_api_search`     | Find endpoints by keyword                         |\n| `resemble_get_page`       | Read specific documentation pages                 |\n| `resemble_list_topics`    | List all available topics                         |\n\n**Tool usage pattern**: Use `resemble_docs_lookup` with topic `\"detect\"` to get the full picture, then `resemble_api_endpoint` for exact request/response schemas before making API calls.\n\n## Full API Reference\n\nDetailed request/response schemas for every endpoint are in **[references/api-reference.md](references/api-reference.md)**. Consult it before making any API call to verify exact parameter names and response shapes. The sections below cover decision-making; the reference covers exact field formats.\n\n---\n\n## Phase 1: Deepfake Detection\n\nThe core capability. Submit audio, image, or video for AI-generated content analysis via `POST /detect`.\n\n**Key flags to consider:**\n- `visualize: true` — generate heatmap/visualization artifacts\n- `intelligence: true` — run multimodal intelligence alongside detection (saves a round-trip)\n- `audio_source_tracing: true` — identify which AI platform synthesized fake audio (only fires on `\"fake\"` audio)\n- `use_reverse_search: true` — enable reverse image search (image only)\n- `zero_retention_mode: true` — auto-delete media after analysis (for sensitive content)\n\nDetection is asynchronous. Poll `GET /detect/{uuid}` at 2s → 5s → 10s intervals until `status` is `\"completed\"` or `\"failed\"`. Most complete in 10–60 seconds.\n\n**Supported formats:** Audio (WAV, MP3, OGG, M4A, FLAC) · Video (MP4, MOV, AVI, WMV) · Image (JPG, PNG, GIF, WEBP)\n\n### Reading Results\n\n- **Audio** — verdict in `metrics` — use `label` and `aggregated_score`\n- **Image** — verdict in `image_metrics` — use `label` and `score`; `ifl` has an Invisible Frequency Layer heatmap\n- **Video** — verdict in `video_metrics` — hierarchical tree of frame/segment results; video-with-audio returns both `metrics` and `video_metrics`\n\nSee [references/api-reference.md](references/api-reference.md#reading-results-by-media-type) for full response schemas.\n\n### Interpreting Scores\n\n| Score Range | Interpretation                                      |\n|-------------|-----------------------------------------------------|\n| 0.0 – 0.3  | Strong indication of authentic/real media            |\n| 0.3 – 0.5  | Inconclusive — recommend additional analysis         |\n| 0.5 – 0.7  | Likely synthetic — flag for review                   |\n| 0.7 – 1.0  | High confidence synthetic/AI-generated               |\n\n**Always present scores with context.** Say \"The detection returned a score of 0.87, indicating high confidence that this audio is AI-generated\" — never just \"it's fake.\"\n\n---\n\n## Phase 2: Intelligence — Media Analysis\n\nRich structured insights about media: speaker info, emotion, transcription, translation, misinformation, abnormalities.\n\nTwo ways to run Intelligence:\n1. **Combined with detection** — add `intelligence: true` to `POST /detect` (preferred; one call)\n2. **Standalone** — `POST /intelligence` with a URL (when you only need analysis, not a deepfake verdict)\n\n**Audio/video structured fields include:** `speaker_info`, `language`, `dialect`, `emotion`, `speaking_style`, `context`, `message`, `abnormalities`, `transcription`, `translation`, `misinformation`.\n\n**Image structured fields include:** `scene_description`, `subjects`, `authenticity_analysis`, `context_and_setting`, `abnormalities`, `misinformation`.\n\n### Detect Intelligence — Ask Questions About Results\n\nAfter a detection completes, ask natural-language questions via `POST /detects/{detect_uuid}/intelligence` with `{ \"query\": \"...\" }`. Returns a question UUID — poll `GET /detects/{detect_uuid}/intelligence/{question_uuid}` until `completed`.\n\n**Good questions to suggest:**\n- \"Summarize the detection results in plain language\"\n- \"What specific indicators suggest this is AI-generated?\"\n- \"How do the audio and video detection results differ?\"\n- \"What is the confidence level and what does it mean?\"\n- \"Are there any inconsistencies in the analysis?\"\n\n**Prerequisite:** The detection must have `status: \"completed\"`. Submitting a question against a processing or failed detection returns 422.\n\nSee [references/api-reference.md](references/api-reference.md#intelligence) for full parameters.\n\n---\n\n## Phase 3: Audio Source Tracing\n\nWhen audio is labeled `\"fake\"`, identify which AI platform generated it.\n\n**Enable it** by setting `audio_source_tracing: true` in the `POST /detect` request. Result appears in the detection response under `audio_source_tracing.label`.\n\nKnown labels: `resemble_ai`, `elevenlabs`, `real`, and others as the model expands.\n\n**Important:** Source tracing only runs on audio labeled `\"fake\"`. Real audio produces no source tracing result.\n\nStandalone queries: `GET /audio_source_tracings` and `GET /audio_source_tracings/{uuid}`.\n\n---\n\n## Phase 4: Watermarking\n\nApply invisible watermarks to media for provenance tracking, or detect existing watermarks.\n\n- **Apply**: `POST /watermark/apply` with `url`, optional `strength` (0.0–1.0), optional `custom_message`. Add `Prefer: wait` for synchronous response, or poll `GET /watermark/apply/{uuid}/result`. Response includes `watermarked_media` URL.\n- **Detect**: `POST /watermark/detect` with `url`. Audio returns `{ has_watermark, confidence }`; image/video returns `{ has_watermark }`.\n\nSee [references/api-reference.md](references/api-reference.md#watermarking) for exact parameter rules.\n\n---\n\n## Phase 5: Identity — Speaker Verification (Beta)\n\nCreate voice identity profiles and match incoming audio against them.\n\n> **Beta feature** — requires joining the preview program. Inform the user if they encounter access errors.\n\n- **Create profile**: `POST /identity` with `{ audio_url, name }`\n- **Search**: `POST /identity/search` with `{ audio_url, top_k }`\n\nResponse returns ranked matches with `confidence` (higher = stronger) and `distance` (lower = closer match).\n\nSee [references/api-reference.md](references/api-reference.md#identity--speaker-verification-beta) for full schemas.\n\n---\n\n## Phase 6: Text Detection\n\nDetect whether text content is AI-generated or human-written via `POST /text_detect`.\n\n> **Beta feature** — requires the `detect_beta_user` role or a billing plan that includes the `dfd_text` product.\n\n**Key parameters:**\n- `text` (required, max 100,000 chars)\n- `threshold` (default 0.5)\n- `privacy_mode: true` — text content not stored after analysis\n- `callback_url` — async notification webhook\n\nAdd `Prefer: wait` for synchronous response, or poll `GET /text_detect/{uuid}`. Response includes `prediction` (`\"ai\"` or `\"human\"`) and `confidence` (0.0–1.0).\n\nSee [references/api-reference.md](references/api-reference.md#text-detection) for full schema and callback format.\n\n---\n\n## Recommended Workflows\n\n### Full Media Forensics (Most Thorough)\n\nFor a comprehensive analysis, combine all capabilities:\n\n1. Submit detection with all flags enabled:\n   ```json\n   {\n     \"url\": \"https://example.com/suspect.mp4\",\n     \"visualize\": true,\n     \"intelligence\": true,\n     \"audio_source_tracing\": true,\n     \"use_reverse_search\": true\n   }\n   ```\n2. Poll until `status: \"completed\"`\n3. Read `metrics` / `image_metrics` / `video_metrics` for the verdict\n4. Read `intelligence.description` for structured media analysis\n5. If audio labeled `\"fake\"`, check `audio_source_tracing.label` for the source platform\n6. Ask follow-up questions via Detect Intelligence if anything needs clarification\n7. Check for watermarks via `POST /watermark/detect` if provenance is relevant\n\n### Quick Authenticity Check (Fastest)\n\n1. Submit minimal detection: `{ \"url\": \"...\" }`\n2. Poll until complete\n3. Check `label` and `aggregated_score` (audio) or `label` and `score` (image/video)\n4. Report result with score context\n\n### Provenance Pipeline (Content Creators)\n\n1. Apply watermark to original content: `POST /watermark/apply`\n2. Distribute watermarked media\n3. Later, verify provenance: `POST /watermark/detect` against any copy\n\n---\n\n## Red Flags — Stop and Reassess\n\n- **Declaring authenticity without a detection result** — Never say media is real or fake based on visual/auditory inspection alone\n- **Ignoring the score and reporting only the label** — A `\"fake\"` label with score 0.51 means something very different from score 0.95\n- **Submitting local file paths to the API** — The API requires publicly accessible HTTPS URLs (does not apply to text detection)\n- **Sending text longer than 100,000 characters to text detection** — Split into chunks or inform the user of the limit\n- **Polling too aggressively** — Start at 2s intervals, back off exponentially; do not loop at <1s\n- **Asking Detect Intelligence questions before detection completes** — Results in 422 error\n- **Expecting source tracing on \"real\" audio** — Source tracing only runs on audio labeled `\"fake\"`\n- **Treating beta features (Identity, Text Detection) as production-ready** — Warn users about beta status\n- **Ignoring `zero_retention_mode` for sensitive media** — Always suggest this flag when the user indicates the media is sensitive or private\n- **Making multiple separate API calls when flags can combine** — Use `intelligence: true` and `audio_source_tracing: true` on the detection call instead of separate requests\n\n## Response Presentation Guidelines\n\nWhen presenting results to users:\n\n1. **Lead with the verdict** — \"The detection indicates this audio is likely AI-generated (score: 0.87)\"\n2. **Provide score context** — Use the score interpretation table above\n3. **Mention limitations** — Detection is probabilistic, not absolute proof\n4. **Include actionable next steps** — Suggest intelligence queries, source tracing, or watermark checks as appropriate\n5. **For inconclusive results (0.3–0.5)** — Explicitly state the result is inconclusive and recommend additional analysis with different parameters or manual review\n6. **Never present detection as legal evidence** — Detection results are analytical tools, not forensic certifications\n\n## Error Handling\n\n| Error     | Cause                                      | Resolution                                      |\n|-----------|--------------------------------------------|-------------------------------------------------|\n| 400       | Invalid request body or missing `url`      | Check required parameters                       |\n| 401       | Invalid or missing API key                 | Verify `RESEMBLE_API_KEY`                       |\n| 404       | Detection UUID not found                   | Verify the UUID from the creation response     |\n| 422       | Detection not completed (for Intelligence) | Wait for detection to reach `completed` status |\n| 429       | Rate limited                               | Back off and retry with exponential delay       |\n| 500       | Server error                               | Retry once, then report to user                  |\n\n## Privacy & Compliance Notes\n\n- **Zero retention mode**: Set `zero_retention_mode: true` to auto-delete media after analysis. The URL is redacted and `media_deleted` is set to true post-completion.\n- **Text privacy mode**: Set `privacy_mode: true` on text detection to prevent text content from being stored after analysis.\n- **Data handling**: Media URLs and text content are stored by default. For GDPR/compliance-sensitive workflows, enable zero retention (media) or privacy mode (text).\n- **Callback security**: If using `callback_url`, ensure the endpoint is HTTPS and authenticated on the receiving end.","tags":["resemble","detect","awesome","copilot","github","agent-skills","agents","custom-agents","github-copilot","hacktoberfest","prompt-engineering"],"capabilities":["skill","source-github","skill-resemble-detect","topic-agent-skills","topic-agents","topic-awesome","topic-custom-agents","topic-github-copilot","topic-hacktoberfest","topic-prompt-engineering"],"categories":["awesome-copilot"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/github/awesome-copilot/resemble-detect","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add github/awesome-copilot","source_repo":"https://github.com/github/awesome-copilot","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 33270 github stars · SKILL.md body (15,850 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":"2026-05-18T18:52:23.995Z","embedding":null,"createdAt":"2026-04-28T06:52:09.834Z","updatedAt":"2026-05-18T18:52:23.995Z","lastSeenAt":"2026-05-18T18:52:23.995Z","tsv":"'/api/v2':425 '/audio_source_tracings':1120,1123 '/detect':284,296,393,641,707,893,1079 '/detects':318,961,973 '/identity':375,1225 '/identity/search':352,1232 '/intelligence':308,320,900,964,976 '/result':1163 '/suspect.mp4':1382 '/text_detect':363,479,1280,1333 '/watermark/apply':330,1142,1161,1494 '/watermark/detect':340,1171,1447,1504 '0.0':809,1147,1343 '0.3':810,816,1756 '0.5':817,822,1309,1757 '0.51':1544 '0.7':823,829 '0.87':846,1717 '0.95':1551 '000':1305,1577 '1':622,884,1371,1456,1487,1701 '1.0':830,1148,1344 '10':723 '100':1304,1576 '10s':712 '1s':1606 '2':863,897,1395,1461,1495,1718 '2s':710,1597 '3':1053,1400,1465,1499,1728 '4':1126,1410,1477,1737 '400':1794 '401':1804 '404':1814 '422':1044,1616,1826 '429':1839 '5':1192,1417,1752 '500':1849 '5s':711 '6':1263,1428,1774 '60':724 '7':1441 'abnorm':878,926,942 'absolut':1735 'accept':480 'access':439,1220,1563 'across':519 'action':1739 'add':888,1152,1324 'addit':820,1766 'aggreg':753,1469 'aggress':1594 'ai':11,32,49,61,151,168,208,236,278,287,358,414,635,669,855,999,1064,1092,1272,1338,1714 'ai-gener':10,48,150,207,277,357,634,854,998,1271,1713 'ai-written':235 'alon':1530 'alongsid':656 'alway':834,1654 'analysi':638,698,821,866,908,938,1026,1318,1367,1416,1767,1875,1908 'analyt':1784 'analyz':27,39,180 'anyth':1438 'api':271,407,419,476,500,523,533,570,578,581,598,1558,1560,1671,1808,1812 'app.resemble.ai':424 'app.resemble.ai/api/v2':423 'appear':1082 'appli':21,174,321,328,379,1128,1140,1488,1568 'appropri':1751 'artifact':650 'ask':189,309,946,954,1429,1607 'async':1321 'asynchron':704 'attempt':469 'audio':13,40,144,171,291,292,629,663,673,678,728,746,784,852,1004,1054,1058,1072,1107,1111,1174,1204,1227,1234,1387,1419,1471,1623,1629,1681,1710 'audio/video':913 'audio_source_tracing.label':1088,1423 'auth':426 'authent':88,90,163,228,937,1453,1514,1943 'authentic/real':814 'author':428 'auto':694,1871 'auto-delet':693,1870 'avail':486,551 'avi':737 'back':94,1599,1842 'base':421,1526 'bearer':409,429 'beta':1196,1207,1258,1281,1286,1633,1645 'bill':1291 'bodi':1797 'call':394,501,579,599,896,1672,1688 'callback':1319,1355,1931,1935 'capabl':262,263,378,627,1370 'caus':1792 'certif':1788 'char':1306 'charact':1578 'check':142,229,273,331,353,1422,1442,1454,1466,1749,1801 'chunk':1584 'claim':91 'clarif':1440 'clone':251 'closer':1249 'combin':387,885,1368,1676 'complet':77,97,108,313,717,721,953,980,1033,1399,1464,1613,1829,1837,1889 'complianc':1859 'comprehens':508,1366 'confid':832,849,1013,1178,1243,1342 'connect':493 'consid':645 'consult':593 'contain':334 'content':51,482,637,701,1269,1314,1485,1492,1903,1915 'context':838,924,939,1482,1721 'copi':1507 'core':63,626 'cover':611,617 'creat':364,373,1197,1222 'creation':1824 'creator':1486 'custom':1150 'dashboard':415 'data':1909 'decis':264,613 'decision-mak':612 'declar':69,1513 'deepfak':4,35,156,218,280,281,383,623,911 'default':1308,1919 'delay':1848 'delet':695,1872,1882 'descript':935 'detail':583 'detect':3,5,9,34,36,78,99,111,155,176,195,206,220,240,282,314,315,338,361,384,512,562,624,657,702,841,887,944,952,962,974,987,1007,1029,1042,1085,1137,1169,1265,1266,1285,1350,1373,1435,1459,1517,1571,1581,1608,1612,1637,1687,1707,1731,1777,1781,1815,1827,1834,1899 'dfd':1296 'dialect':920 'differ':1009,1548,1769 'distanc':1247 'distribut':1496 'doc':505,509,558 'document':521,544 'e.g':380 'elevenlab':1093 'emot':185,302,874,921 'enabl':683,1068,1377,1923 'encount':1219 'end':1947 'endpoint':272,524,531,536,571,588,1939 'ensur':1937 'error':1221,1617,1789,1791,1851 'everi':89,587 'evid':1780 'exact':526,573,602,618,1188 'example.com':1381 'example.com/suspect.mp4':1380 'except':477 'exist':1138 'expand':1100 'expect':1618 'explicit':1758 'exponenti':1601,1847 'fail':118,719,1041 'fake':74,219,290,672,677,861,1061,1109,1421,1525,1540,1631 'fastest':1455 'featur':1208,1282,1634 'field':619,915,932 'file':448,457,473,1554 'find':535 'fire':675 'first':466 'flac':733 'flag':298,399,643,826,1376,1509,1657,1674 'follow':1431 'follow-up':1430 'forens':227,1361,1787 'format':160,620,727,1356 'found':1818 'frame/segment':779 'frequenc':768 'full':566,580,801,1050,1260,1352,1359 'futur':370 'gdpr/compliance-sensitive':1921 'generat':12,50,152,209,249,279,359,636,648,856,1000,1066,1273,1715 'get':299,507,525,540,564,706,972,1119,1122,1160,1332 'gif':742 'good':981 'guess':82 'guidelin':1695 'handl':1790,1910 'header':427 'heatmap':770 'heatmap/visualization':649 'hierarch':776 'high':831,848 'higher':1244 'host':460 'https':440,464,1564,1941 'human':1276,1340 'human-written':1275 'ident':25,54,201,345,349,367,372,1193,1199,1254,1635 'identifi':166,667,1062 'ifl':764 'ignor':1531,1647 'imag':14,41,146,630,685,687,739,755,758,930,1403 'image/video':1179,1476 'import':1101 'includ':916,933,1165,1294,1336,1738 'incom':1203 'inconclus':818,1754,1763 'inconsist':1023 'indic':812,847,994,1661,1708 'infer':83 'info':184,301,873,918 'inform':454,1214,1586 'inlin':483 'insight':869 'inspect':1529 'instead':450,497,1689 'intellig':29,57,306,316,386,397,651,655,864,883,889,945,1048,1385,1436,1609,1678,1743,1831 'intelligence.description':1412 'interpret':804,808,1725 'interv':713,1598 'invalid':1795,1805 'invis':323,767,1129 'involv':138 'iron':66 'job':100 'join':1210 'jpg':740 'json':1378 'judgment':126 'k':1237 'key':408,420,642,1299,1809,1813 'keyword':538 'know':285 'known':203,347,1089 'label':104,751,761,1060,1090,1108,1420,1467,1473,1538,1541,1630 'languag':192,919,957,991 'later':1500 'law':67 'layer':769 'lead':1702 'legal':1779 'level':1014 'like':824,1712 'limit':1591,1730,1841 'list':547,549 'local':447,472,1553 'longer':1574 'lookup':506,559 'loop':1604 'lower':1248 'm4a':732 'machin':212 'machine-written':211 'made':289 'make':402,577,596,614,1668 'manipul':47,154 'manual':1772 'match':197,371,1202,1241,1250 'max':1303 'mcp':484,490 'mean':1019,1545 'media':7,28,37,56,70,87,159,162,179,181,222,226,275,305,326,333,430,433,696,798,815,865,871,1132,1167,1360,1415,1498,1521,1653,1663,1873,1881,1911,1926 'mention':216,1729 'messag':925,1151 'metric':749,759,775,787,790,1402,1404,1406 'minim':1458 'misinform':188,877,929,943 'miss':1799,1807 'mode':691,1311,1650,1863,1867,1892,1895,1929 'model':1099 'mov':736 'mp3':730 'mp4':735 'multimod':654 'multipl':377,1669 'must':92,434,458,1030 'name':604,1229 'natur':191,956 'natural-languag':190,955 'need':907,1439 'never':68,857,1519,1775 'next':1740 'note':1860 'notif':1322 'ogg':731 'one':895 'openapi':527 'option':1145,1149 'origin':1491 'other':1096 'page':541,545 'paramet':603,1051,1189,1300,1770,1803 'path':449,1555 'pattern':555 'phase':621,862,1052,1125,1191,1262 'pictur':567 'pipelin':1484 'plain':990 'plan':1292 'platform':62,169,288,670,1065,1427 'png':741 'poll':705,971,1159,1331,1396,1462,1592 'post':283,295,307,317,329,339,351,362,374,392,478,640,892,899,960,1078,1141,1170,1224,1231,1279,1446,1493,1503,1888 'post-complet':1887 'predict':1337 'prefer':894,1153,1325 'prerequisit':1027 'present':835,1694,1697,1776 'prevent':1901 'preview':1212 'principl':64 'privaci':1310,1858,1891,1894,1928 'privat':1667 'probabilist':1733 'process':114,1039 'produc':1112 'product':1298,1640 'production-readi':1639 'profil':205,348,368,1200,1223 'program':1213 'proof':1736 'proven':165,1134,1449,1483,1502 'provid':445,1719 'public':438,463,1562 'purpos':503 'queri':966,1118,1744 'question':193,310,947,958,969,977,982,1036,1433,1610 'quick':1452 'rang':807 'rank':1240 'rate':1840 'rather':400 'raw':499 'reach':1836 'read':542,744,795,1401,1411 'readi':1641 'reading-results-by-media-typ':794 'real':72,234,1094,1110,1523,1622 'reassess':1512 'receiv':1946 'recommend':819,1357,1765 'red':1508 'redact':1879 'refer':582,616 'references/api-reference.md':591,592,792,793,1046,1047,1184,1185,1252,1253,1346,1347 'relev':1451 'report':1478,1535,1855 'request':137,404,1080,1692,1796 'request/response':574,584 'requir':405,431,1209,1283,1302,1561,1802 'resembl':2,31,33,60,98,261,413,418,489,504,516,522,532,539,546,557,569,1091,1811 'resemble-detect':1 'resolut':1793 'respons':606,802,1086,1157,1164,1238,1329,1335,1693,1825 'result':79,196,745,780,796,949,988,1008,1081,1116,1479,1518,1614,1698,1755,1761,1782 'retent':690,1649,1862,1866,1925 'retri':1845,1852 'return':103,785,842,967,1043,1175,1180,1239 'revers':680,684,1392 'review':828,1773 'rich':867 'role':1288 'round':661 'round-trip':660 'rule':1190 'run':653,882,1105,1627 'safeti':8,38 'save':658 'say':119,839,1520 'scene':934 'schema':575,585,803,1261,1353 'score':105,754,763,805,806,836,844,1470,1475,1481,1533,1543,1550,1716,1720,1724 'search':350,517,518,534,681,686,1230,1393 'second':725 'section':609 'secur':1932 'see':791,1045,1183,1251,1345 'send':1572 'sensit':700,1652,1665 'separ':260,403,1670,1691 'server':491,1850 'set':416,941,1071,1864,1884,1893 'setup':406 'shape':607 'singl':391 'skill':132 'skill-resemble-detect' 'someth':1546 'sourc':20,172,230,293,664,1055,1073,1102,1114,1388,1426,1619,1624,1682,1745 'source-github' 'speak':922 'speaker':24,53,183,200,300,343,872,917,1194,1256 'speaker-verification-beta':1255 'spec':528 'specif':543,993 'specul':85 'speech':248,254 'speech-to-text':253 'split':1582 'standalon':898,1117 'start':1595 'state':1759 'status':107,715,1032,1398,1646,1838 'step':1741 'still':113 'stop':1510 'store':1316,1906,1917 'strength':1146 'strong':811 'stronger':1245 'structur':868,914,931,1414 'style':923 'sub':514 'sub-top':513 'subject':936 'submit':628,1034,1372,1457,1552 'substitut':123 'suggest':984,995,1655,1742 'summar':985 'support':726 'synchron':1156,1328 'synthes':170,671 'synthesi':19 'synthet':46,221,825 'synthetic/ai-generated':833 'tabl':1726 'text':17,44,148,214,238,239,246,256,355,360,481,1264,1268,1297,1301,1313,1349,1570,1573,1580,1636,1890,1898,1902,1914,1930 'text-detect':1348 'text-to-speech':245 'thorough':1363 'threshold':1307 'token':410 'tool':485,496,502,553,1785 'top':1236 'topic':515,548,552,561 'topic-agent-skills' 'topic-agents' 'topic-awesome' 'topic-custom-agents' 'topic-github-copilot' 'topic-hacktoberfest' 'topic-prompt-engineering' 'trace':18,173,231,294,665,1056,1074,1103,1115,1389,1620,1625,1683,1746 'track':1135 'transcript':186,257,303,875,927 'translat':876,928 'treat':1632 'tree':265,777 'trip':662 'true':398,647,652,666,682,692,890,1075,1312,1384,1386,1390,1394,1679,1684,1868,1886,1896 'two':879 'type':799 'upload':471 'url':422,441,453,465,903,1144,1168,1173,1228,1235,1320,1379,1460,1565,1800,1877,1912,1936 'usag':554 'use':30,58,129,130,243,269,395,494,556,679,750,760,1391,1677,1722,1934 'user':135,266,381,444,1216,1287,1588,1643,1660,1700,1857 'uuid':319,708,963,970,975,978,1124,1162,1334,1816,1821 'verdict':747,756,772,912,1409,1705 'verif':224,1195,1257 'verifi':23,161,199,341,601,1501,1810,1819 'via':639,959,1278,1434,1445 'video':15,42,145,632,734,771,774,782,789,1006,1405 'video-with-audio':781 'visual':646,1383 'visual/auditory':1528 'voic':204,223,250,366,1198 'wait':115,1154,1326,1832 'want':267,382 'warn':1642 'watermark':22,52,177,225,324,327,336,337,1127,1130,1139,1166,1177,1182,1186,1444,1489,1497,1748 'wav':729 'way':880 'webhook':1323 'webp':743 'whenev':133 'whether':1267 'without':75,1515 'wmv':738 'workflow':1358,1922 'written':213,237,1277 'zero':689,1648,1861,1865,1924","prices":[{"id":"02074b6d-5b87-40cc-8fc2-c01b9ddfd5ef","listingId":"c0b47fea-02dd-4401-9b4b-538bbc2aa5ef","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":"2026-04-28T06:52:09.834Z"}],"sources":[{"listingId":"c0b47fea-02dd-4401-9b4b-538bbc2aa5ef","source":"github","sourceId":"github/awesome-copilot/resemble-detect","sourceUrl":"https://github.com/github/awesome-copilot/tree/main/skills/resemble-detect","isPrimary":false,"firstSeenAt":"2026-04-28T06:52:09.834Z","lastSeenAt":"2026-05-18T18:52:23.995Z"}],"details":{"listingId":"c0b47fea-02dd-4401-9b4b-538bbc2aa5ef","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"github","slug":"resemble-detect","github":{"repo":"github/awesome-copilot","stars":33270,"topics":["agent-skills","agents","ai","awesome","custom-agents","github-copilot","hacktoberfest","prompt-engineering"],"license":"mit","html_url":"https://github.com/github/awesome-copilot","pushed_at":"2026-05-18T01:26:59Z","description":"Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.","skill_md_sha":"48bc63cf9814894143aa06fe212a389dcbbf8833","skill_md_path":"skills/resemble-detect/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/github/awesome-copilot/tree/main/skills/resemble-detect"},"layout":"multi","source":"github","category":"awesome-copilot","frontmatter":{"name":"resemble-detect","license":"Apache-2.0","description":"Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using Resemble AI","compatibility":"Requires a Resemble AI API key (https://app.resemble.ai) set as RESEMBLE_API_KEY. All media must be accessible via public HTTPS URLs — local file paths are not supported except for text detection."},"skills_sh_url":"https://skills.sh/github/awesome-copilot/resemble-detect"},"updatedAt":"2026-05-18T18:52:23.995Z"}}