{"id":"265efc64-79f1-4ad4-9be0-8ef85901144c","shortId":"PnQ68t","kind":"skill","title":"manus","tagline":"Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product compariso","description":"# Manus\n\nManus is an autonomous AI agent that handles complex tasks asynchronously. Particularly strong at **deep research** with parallel processing, web browsing, and generating comprehensive reports with data visualizations.\n\n## When to Use Manus\n\n- **Deep research** - Market analysis, competitive landscaping, product comparisons\n- **Stock/financial analysis** - Company research, technical analysis, price charts\n- **Product research** - Feature comparisons across brands, specs analysis\n- **Report generation** - Creates markdown reports, CSVs, charts, and visualizations\n- **Multi-source synthesis** - Gathers and combines information from multiple websites\n- **Long-running tasks** - Anything taking 1-10+ minutes of autonomous work\n\n## Research Prompt Examples\n\nEffective research prompts are specific about scope, sources, and desired output:\n\n**Product comparison:**\n```\nFind the best 4K monitors for Mac with Thunderbolt connectivity and 120Hz+ refresh rate.\nFocus on BenQ, Samsung, Dell, LG. Only include models released in the last year.\nCompare specs, prices, and Mac-specific features. Output a comparison table.\n```\n\n**Stock/company analysis:**\n```\nAnalyze [TICKER] stock: company profile, recent performance, technical indicators,\nvaluation metrics, and insider activity. Include a price chart for the past year.\n```\n\n**Market research:**\n```\nResearch the [industry] market: key players, market size, growth trends,\nrecent developments, and competitive landscape. Focus on [region/segment].\n```\n\n**Competitive analysis:**\n```\nCompare [Product A] vs [Product B] vs [Product C]: features, pricing,\nuser reviews, pros/cons. Create a decision matrix for [use case].\n```\n\n## Environment Setup\n\nRequires `MANUS_API_KEY` environment variable. Base URL: `https://api.manus.ai`\n\n## Core Workflow\n\n1. **Create task** → Returns `task_id` immediately\n2. **Poll status** → Check until `status` is `completed` or `failed`\n3. **Return results** → Extract output text and file attachments\n\n## Creating a Task\n\n```bash\ncurl -s -X POST \"https://api.manus.ai/v1/tasks\" -H \"API_KEY:$MANUS_API_KEY\" -H \"Content-Type:application/json\" -d '{\"prompt\":\"<task description>\",\"agentProfile\":\"manus-1.6\"}'\n```\n\n**Agent Profiles:**\n- `manus-1.6-lite` - Fast, simple tasks (quick lookups, simple questions)\n- `manus-1.6` - Standard (default, good for most research)\n- `manus-1.6-max` - Complex reasoning (deep research, multi-source analysis, detailed reports)\n\n**Response:**\n```json\n{\"task_id\":\"abc123\",\"task_title\":\"...\",\"task_url\":\"https://manus.im/app/abc123\"}\n```\n\n## Checking Task Status\n\n```bash\ncurl -s -X GET \"https://api.manus.ai/v1/tasks/{task_id}\" -H \"API_KEY:$MANUS_API_KEY\"\n```\n\n**Status values:** `pending`, `running`, `completed`, `failed`\n\nPoll every 5-10 seconds until completed.\n\n**Extract text output:**\n```bash\ncurl -s -X GET \"https://api.manus.ai/v1/tasks/{task_id}\" -H \"API_KEY:$MANUS_API_KEY\" | jq -r '.output[] | select(.role==\"assistant\") | .content[] | select(.type==\"output_text\") | .text'\n```\n\n**Extract file attachments:**\n```bash\ncurl -s -X GET \"https://api.manus.ai/v1/tasks/{task_id}\" -H \"API_KEY:$MANUS_API_KEY\" | jq -r '.output[] | select(.role==\"assistant\") | .content[] | select(.type==\"output_file\") | \"\\(.fileName): \\(.fileUrl)\"'\n```\n\n## Listing Tasks\n\n```bash\ncurl -s -X GET \"https://api.manus.ai/v1/tasks\" -H \"API_KEY:$MANUS_API_KEY\" | jq '.data[] | {id, status, title: .metadata.task_title}'\n```\n\n## Multi-turn Conversations\n\nContinue an existing task by including `taskId`:\n\n```bash\ncurl -s -X POST \"https://api.manus.ai/v1/tasks\" -H \"API_KEY:$MANUS_API_KEY\" -H \"Content-Type:application/json\" -d '{\"prompt\":\"follow-up question\",\"taskId\":\"abc123\",\"agentProfile\":\"manus-1.6\"}'\n```\n\n## Delete a Task\n\n```bash\ncurl -s -X DELETE \"https://api.manus.ai/v1/tasks/{task_id}\" -H \"API_KEY:$MANUS_API_KEY\"\n```\n\n## Advanced Options\n\n| Parameter | Description |\n|-----------|-------------|\n| `taskMode` | `chat`, `adaptive`, or `agent` |\n| `projectId` | Associate with project for shared instructions |\n| `attachments` | Array of file objects (see below) |\n| `connectors` | Pre-configured connector IDs (Gmail, Calendar, Notion) |\n| `createShareableLink` | Enable public access URL |\n\n## File Attachments\n\nAttach files using one of three formats:\n\n**URL attachment:**\n```json\n{\"prompt\":\"Analyze this\",\"attachments\":[{\"type\":\"url\",\"url\":\"https://example.com/doc.pdf\"}]}\n```\n\n**Base64 attachment:**\n```json\n{\"prompt\":\"What's in this image?\",\"attachments\":[{\"type\":\"base64\",\"data\":\"<base64>\",\"mime_type\":\"image/png\"}]}\n```\n\n**File ID (after upload):**\n```json\n{\"prompt\":\"Review this file\",\"attachments\":[{\"type\":\"file\",\"file_id\":\"file-xxx\"}]}\n```\n\n## Projects\n\nCreate a project with shared instructions:\n```bash\ncurl -s -X POST \"https://api.manus.ai/v1/projects\" -H \"API_KEY:$MANUS_API_KEY\" -H \"Content-Type:application/json\" -d '{\"name\":\"My Project\",\"instruction\":\"Always respond concisely\"}'\n```\n\nUse project in task:\n```bash\ncurl -s -X POST \"https://api.manus.ai/v1/tasks\" -H \"API_KEY:$MANUS_API_KEY\" -H \"Content-Type:application/json\" -d '{\"prompt\":\"...\",\"projectId\":\"proj_xxx\",\"agentProfile\":\"manus-1.6\"}'\n```\n\n## Best Practices\n\n- Use `manus-1.6-lite` for simple queries (faster, cheaper)\n- Use `manus-1.6` or `manus-1.6-max` for research tasks\n- Always report `task_url` so user can view progress in browser\n- Poll status with reasonable intervals (5-10s for simple, 15-30s for research)\n- Check `credit_usage` field to track consumption\n- For research: be specific about scope, timeframe, sources, and desired output format\n- Research tasks typically produce multiple output files (reports, CSVs, charts) - extract all attachments\n- Manus uses parallel processing for multi-faceted research - one prompt can cover multiple angles\n\n## Error Handling\n\nCheck for failed tasks:\n```bash\ncurl -s -X GET \"https://api.manus.ai/v1/tasks/{task_id}\" -H \"API_KEY:$MANUS_API_KEY\" | jq '{status, error}'\n```\n\nIf `status` is `failed`, the `error` field contains the reason. Common issues:\n- Invalid API key → Check `MANUS_API_KEY` is set\n- Task timeout → Simplify prompt or use `manus-1.6-max`\n- Rate limited → Wait and retry\n\n## API Reference\n\nFor complete endpoint documentation, see [references/api.md](references/api.md).","tags":["manus","skills","sanjay3290","agent-skills","ai-skills","atlassian","azure-devops","claude-code","claude-skills","confluence","deep-research","elevenlabs"],"capabilities":["skill","source-sanjay3290","skill-manus","topic-agent-skills","topic-ai-skills","topic-atlassian","topic-azure-devops","topic-claude-code","topic-claude-skills","topic-confluence","topic-deep-research","topic-elevenlabs","topic-gmail","topic-google-calendar","topic-google-drive"],"categories":["ai-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/sanjay3290/ai-skills/manus","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add sanjay3290/ai-skills","source_repo":"https://github.com/sanjay3290/ai-skills","install_from":"skills.sh"}},"qualityScore":"0.574","qualityRationale":"deterministic score 0.57 from registry signals: · indexed on github topic:agent-skills · 248 github stars · SKILL.md body (6,233 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":"2026-05-02T18:54:11.287Z","embedding":null,"createdAt":"2026-04-18T22:05:20.198Z","updatedAt":"2026-05-02T18:54:11.287Z","lastSeenAt":"2026-05-02T18:54:11.287Z","tsv":"'-1.6':323,327,337,345,527,703,708,717,720,851 '-10':130,397,742 '-30':747 '/app/abc123':368 '/doc.pdf':605 '/v1/projects':653 '/v1/tasks':307,473,505,684 '/v1/tasks/':379,411,442,538,811 '1':129,271 '120hz':162 '15':746 '2':278 '3':288 '4k':154 '5':396,741 'abc123':361,524 'access':582 'across':99 'activ':206 'adapt':553 'advanc':547 'agent':11,52,324,555 'agentprofil':321,525,701 'ai':10,51 'alway':670,725 'analysi':43,82,88,92,102,192,236,354 'analyz':193,597 'angl':797 'anyth':127 'api':262,309,312,383,386,415,418,446,449,475,478,507,510,542,545,655,658,686,689,815,818,836,840,858 'api.manus.ai':268,306,378,410,441,472,504,537,652,683,810 'api.manus.ai/v1/projects':651 'api.manus.ai/v1/tasks':305,471,503,682 'api.manus.ai/v1/tasks/':377,409,440,536,809 'application/json':318,516,664,695 'array':564 'ask':30 'assist':425,456 'associ':557 'asynchron':57 'attach':296,434,563,585,586,594,599,607,615,631,782 'autonom':13,50,133 'b':242 'base':266 'base64':606,617 'bash':300,372,404,435,466,498,531,646,677,804 'benq':167 'best':153,704 'brand':100 'brows':67 'browser':735 'c':245 'calendar':577 'case':257 'chart':94,109,210,779 'chat':552 'cheaper':714 'check':32,281,369,751,800,838 'combin':118 'common':833 'compani':89,196 'compar':179,237 'compariso':45 'comparison':86,98,150,189 'competit':83,230,235 'complet':285,392,400,861 'complex':3,55,347 'comprehens':70 'concis':672 'configur':573 'connect':160 'connector':570,574 'consumpt':757 'contain':830 'content':316,426,457,514,662,693 'content-typ':315,513,661,692 'continu':491 'convers':490 'core':269 'cover':795 'creat':105,251,272,297,640 'createshareablelink':579 'credit':752 'csvs':108,778 'curl':301,373,405,436,467,499,532,647,678,805 'd':319,517,665,696 'data':73,481,618 'decis':253 'deep':39,61,79,349 'default':339 'deleg':2,21 'delet':528,535 'dell':169 'descript':550 'desir':147,767 'detail':355 'develop':228 'document':863 'effect':138 'enabl':580 'endpoint':862 'environ':258,264 'error':798,822,828 'everi':395 'exampl':137 'example.com':604 'example.com/doc.pdf':603 'execut':14 'exist':493 'extract':291,401,432,780 'facet':790 'fail':287,393,802,826 'fast':329 'faster':713 'featur':97,186,246 'field':754,829 'file':295,433,461,566,584,587,622,630,633,634,637,776 'file-xxx':636 'filenam':462 'fileurl':463 'find':151 'focus':165,232 'follow':520 'follow-up':519 'format':592,769 'gather':116 'generat':69,104 'get':376,408,439,470,808 'gmail':576 'good':340 'growth':225 'h':308,314,382,414,445,474,506,512,541,654,660,685,691,814 'handl':54,799 'id':276,360,381,413,444,482,540,575,623,635,813 'imag':614 'image/png':621 'immedi':277 'includ':172,207,496 'indic':201 'industri':219 'inform':119 'insid':205 'instruct':562,645,669 'interv':740 'invalid':835 'issu':834 'jq':420,451,480,820 'json':358,595,608,626 'key':221,263,310,313,384,387,416,419,447,450,476,479,508,511,543,546,656,659,687,690,816,819,837,841 'landscap':84,231 'last':177 'lg':170 'limit':854 'list':464 'lite':328,709 'long':5,124 'long-run':4,123 'lookup':333 'mac':157,184 'mac-specif':183 'manus':1,9,20,23,26,28,31,33,46,47,78,261,311,322,326,336,344,385,417,448,477,509,526,544,657,688,702,707,716,719,783,817,839,850 'manus.im':367 'manus.im/app/abc123':366 'markdown':106 'market':42,81,215,220,223 'matrix':254 'max':346,721,852 'metadata.task':485 'metric':203 'mime':619 'minut':131 'model':173 'monitor':155 'multi':113,352,488,789 'multi-facet':788 'multi-sourc':112,351 'multi-turn':487 'multipl':121,774,796 'name':666 'notion':578 'object':567 'one':589,792 'option':548 'output':148,187,292,403,422,429,453,460,768,775 'parallel':64,785 'paramet':549 'particular':58 'past':213 'pend':390 'perform':199 'player':222 'poll':279,394,736 'post':304,502,650,681 'practic':705 'pre':572 'pre-configur':571 'price':93,181,209,247 'process':65,786 'produc':773 'product':44,85,95,149,238,241,244 'profil':197,325 'progress':733 'proj':699 'project':559,639,642,668,674 'projectid':556,698 'prompt':136,140,320,518,596,609,627,697,793,847 'pros/cons':250 'public':581 'queri':712 'question':335,522 'quick':332 'r':421,452 'rate':164,853 'reason':348,739,832 'recent':198,227 'refer':859 'references/api.md':865,866 'refresh':163 'region/segment':234 'releas':174 'report':71,103,107,356,726,777 'requir':38,260 'research':41,62,80,90,96,135,139,216,217,343,350,723,750,759,770,791 'respond':671 'respons':357 'result':290 'retri':857 'return':274,289 'review':249,628 'role':424,455 'run':6,125,391 'samsung':168 'say':18 'scope':144,763 'second':398 'see':568,864 'select':423,427,454,458 'send':24 'session':34 'set':843 'setup':259 'share':561,644 'simpl':330,334,711,745 'simplifi':846 'size':224 'skill' 'skill-manus' 'sourc':114,145,353,765 'source-sanjay3290' 'spec':101,180 'specif':142,185,761 'standard':338 'status':280,283,371,388,483,737,821,824 'stock':195 'stock/company':191 'stock/financial':87 'strong':59 'synthesi':115 'tabl':190 'take':128 'task':7,37,56,126,273,275,299,331,359,362,364,370,380,412,443,465,494,530,539,676,724,727,771,803,812,844 'taskid':497,523 'taskmod':551 'technic':91,200 'text':293,402,430,431 'three':591 'thunderbolt':159 'ticker':194 'timefram':764 'timeout':845 'titl':363,484,486 'topic-agent-skills' 'topic-ai-skills' 'topic-atlassian' 'topic-azure-devops' 'topic-claude-code' 'topic-claude-skills' 'topic-confluence' 'topic-deep-research' 'topic-elevenlabs' 'topic-gmail' 'topic-google-calendar' 'topic-google-drive' 'track':756 'trend':226 'turn':489 'type':317,428,459,515,600,616,620,632,663,694 'typic':772 'upload':625 'url':267,365,583,593,601,602,728 'usag':753 'use':15,19,77,256,588,673,706,715,784,849 'user':17,248,730 'valu':389 'valuat':202 'variabl':265 'view':732 'visual':74,111 'vs':240,243 'wait':855 'web':40,66 'websit':122 'work':134 'workflow':270 'x':303,375,407,438,469,501,534,649,680,807 'xxx':638,700 'year':178,214","prices":[{"id":"ab2c09ed-8ecc-499f-ac39-c79838394007","listingId":"265efc64-79f1-4ad4-9be0-8ef85901144c","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"sanjay3290","category":"ai-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T22:05:20.198Z"}],"sources":[{"listingId":"265efc64-79f1-4ad4-9be0-8ef85901144c","source":"github","sourceId":"sanjay3290/ai-skills/manus","sourceUrl":"https://github.com/sanjay3290/ai-skills/tree/main/skills/manus","isPrimary":false,"firstSeenAt":"2026-04-18T22:05:20.198Z","lastSeenAt":"2026-05-02T18:54:11.287Z"}],"details":{"listingId":"265efc64-79f1-4ad4-9be0-8ef85901144c","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sanjay3290","slug":"manus","github":{"repo":"sanjay3290/ai-skills","stars":248,"topics":["agent-skills","ai-skills","atlassian","azure-devops","claude-code","claude-skills","confluence","deep-research","elevenlabs","gmail","google-calendar","google-drive","google-workspace","imagen","jira","mcp","mysql","notebooklm","postgresql","text-to-speech"],"license":"apache-2.0","html_url":"https://github.com/sanjay3290/ai-skills","pushed_at":"2026-04-13T14:16:19Z","description":"Collection of agent skills for AI coding assistants","skill_md_sha":"92b1f6f0ad8632213057d31427501f8e0c2da8fc","skill_md_path":"skills/manus/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sanjay3290/ai-skills/tree/main/skills/manus"},"layout":"multi","source":"github","category":"ai-skills","frontmatter":{"name":"manus","license":"Apache-2.0","description":"Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product comparisons, stock analysis, competitive research, document generation, data analysis, or multi-step workflows that benefit from autonomous agent execution with parallel processing."},"skills_sh_url":"https://skills.sh/sanjay3290/ai-skills/manus"},"updatedAt":"2026-05-02T18:54:11.287Z"}}