{"id":"b583ab97-5ad9-4297-a7fa-b5be8dbe66f1","shortId":"Zy36UE","kind":"skill","title":"ai-agent-development","tagline":"AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents.","description":"# AI Agent Development Workflow\n\n## Overview\n\nSpecialized workflow for building AI agents including single autonomous agents, multi-agent systems, agent orchestration, tool integration, and human-in-the-loop patterns.\n\n## When to Use This Workflow\n\nUse this workflow when:\n- Building autonomous AI agents\n- Creating multi-agent systems\n- Implementing agent orchestration\n- Adding tool integration to agents\n- Setting up agent memory\n\n## Workflow Phases\n\n### Phase 1: Agent Design\n\n#### Skills to Invoke\n- `ai-agents-architect` - Agent architecture\n- `autonomous-agents` - Autonomous patterns\n\n#### Actions\n1. Define agent purpose\n2. Design agent capabilities\n3. Plan tool integration\n4. Design memory system\n5. Define success metrics\n\n#### Copy-Paste Prompts\n```\nUse @ai-agents-architect to design AI agent architecture\n```\n\n### Phase 2: Single Agent Implementation\n\n#### Skills to Invoke\n- `autonomous-agent-patterns` - Agent patterns\n- `autonomous-agents` - Autonomous agents\n\n#### Actions\n1. Choose agent framework\n2. Implement agent logic\n3. Add tool integration\n4. Configure memory\n5. Test agent behavior\n\n#### Copy-Paste Prompts\n```\nUse @autonomous-agent-patterns to implement single agent\n```\n\n### Phase 3: Multi-Agent System\n\n#### Skills to Invoke\n- `crewai` - CrewAI framework\n- `multi-agent-patterns` - Multi-agent patterns\n\n#### Actions\n1. Define agent roles\n2. Set up agent communication\n3. Configure orchestration\n4. Implement task delegation\n5. Test coordination\n\n#### Copy-Paste Prompts\n```\nUse @crewai to build multi-agent system with roles\n```\n\n### Phase 4: Agent Orchestration\n\n#### Skills to Invoke\n- `langgraph` - LangGraph orchestration\n- `workflow-orchestration-patterns` - Orchestration\n\n#### Actions\n1. Design workflow graph\n2. Implement state management\n3. Add conditional branches\n4. Configure persistence\n5. Test workflows\n\n#### Copy-Paste Prompts\n```\nUse @langgraph to create stateful agent workflows\n```\n\n### Phase 5: Tool Integration\n\n#### Skills to Invoke\n- `agent-tool-builder` - Tool building\n- `tool-design` - Tool design\n\n#### Actions\n1. Identify tool needs\n2. Design tool interfaces\n3. Implement tools\n4. Add error handling\n5. Test tool usage\n\n#### Copy-Paste Prompts\n```\nUse @agent-tool-builder to create agent tools\n```\n\n### Phase 6: Memory Systems\n\n#### Skills to Invoke\n- `agent-memory-systems` - Memory architecture\n- `conversation-memory` - Conversation memory\n\n#### Actions\n1. Design memory structure\n2. Implement short-term memory\n3. Set up long-term memory\n4. Add entity memory\n5. Test memory retrieval\n\n#### Copy-Paste Prompts\n```\nUse @agent-memory-systems to implement agent memory\n```\n\n### Phase 7: Evaluation\n\n#### Skills to Invoke\n- `agent-evaluation` - Agent evaluation\n- `evaluation` - AI evaluation\n\n#### Actions\n1. Define evaluation criteria\n2. Create test scenarios\n3. Measure agent performance\n4. Test edge cases\n5. Iterate improvements\n\n#### Copy-Paste Prompts\n```\nUse @agent-evaluation to evaluate agent performance\n```\n\n## Agent Architecture\n\n```\nUser Input -> Planner -> Agent -> Tools -> Memory -> Response\n              |          |        |        |\n         Decompose   LLM Core  Actions  Short/Long-term\n```\n\n## Quality Gates\n\n- [ ] Agent logic working\n- [ ] Tools integrated\n- [ ] Memory functional\n- [ ] Orchestration tested\n- [ ] Evaluation passing\n\n## Related Workflow Bundles\n\n- `ai-ml` - AI/ML development\n- `rag-implementation` - RAG systems\n- `workflow-automation` - Workflow patterns\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.","tags":["agent","development","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows"],"capabilities":["skill","source-sickn33","skill-ai-agent-development","topic-agent-skills","topic-agentic-skills","topic-ai-agent-skills","topic-ai-agents","topic-ai-coding","topic-ai-workflows","topic-antigravity","topic-antigravity-skills","topic-claude-code","topic-claude-code-skills","topic-codex-cli","topic-codex-skills"],"categories":["antigravity-awesome-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/sickn33/antigravity-awesome-skills/ai-agent-development","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add sickn33/antigravity-awesome-skills","source_repo":"https://github.com/sickn33/antigravity-awesome-skills","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 34964 github stars · SKILL.md body (3,776 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":"2026-04-25T00:50:24.224Z","embedding":null,"createdAt":"2026-04-18T21:30:37.650Z","updatedAt":"2026-04-25T00:50:24.224Z","lastSeenAt":"2026-04-25T00:50:24.224Z","tsv":"'1':89,107,161,214,263,311,362,415 '2':111,142,165,218,267,315,366,419 '3':115,169,194,223,271,319,372,423 '4':119,173,226,248,275,322,379,427 '5':123,176,230,278,293,326,383,431 '6':344 '7':401 'action':106,160,213,262,310,361,414,458 'ad':77 'add':170,272,323,380 'agent':3,6,12,15,18,25,27,36,40,43,45,68,72,75,81,84,90,97,99,103,109,113,134,139,144,151,153,157,159,163,167,178,187,192,197,207,211,216,221,243,249,290,300,336,341,351,393,398,407,409,425,440,444,446,451,462 'agent-evalu':406,439 'agent-memory-system':350,392 'agent-tool-build':299,335 'ai':2,5,26,35,67,96,133,138,412,477 'ai-agent-develop':1 'ai-agents-architect':95,132 'ai-ml':476 'ai/ml':479 'architect':98,135 'architectur':100,140,355,447 'ask':524 'autom':488 'autonom':11,39,66,102,104,150,156,158,186 'autonomous-ag':101,155 'autonomous-agent-pattern':149,185 'behavior':179 'boundari':532 'branch':274 'build':10,34,65,240,304 'builder':302,338 'bundl':475 'capabl':114 'case':430 'choos':162 'clarif':526 'clear':499 'communic':222 'condit':273 'configur':174,224,276 'convers':357,359 'conversation-memori':356 'coordin':232 'copi':128,181,234,282,331,388,435 'copy-past':127,180,233,281,330,387,434 'core':457 'creat':69,288,340,420 'crewai':21,202,203,238 'criteria':418,535 'custom':24 'decompos':455 'defin':108,124,215,416 'deleg':229 'describ':503 'design':91,112,120,137,264,307,309,316,363 'develop':4,7,28,480 'edg':429 'entiti':381 'environ':515 'environment-specif':514 'error':324 'evalu':402,408,410,411,413,417,441,443,471 'expert':520 'framework':164,204 'function':468 'gate':461 'graph':266 'handl':325 'human':51 'human-in-the-loop':50 'identifi':312 'implement':74,145,166,190,227,268,320,367,397,483 'improv':433 'includ':37 'input':449,529 'integr':48,79,118,172,295,466 'interfac':318 'invok':94,148,201,253,298,349,405 'iter':432 'langgraph':22,254,255,286 'limit':491 'llm':456 'logic':168,463 'long':376 'long-term':375 'loop':54 'manag':270 'match':500 'measur':424 'memori':85,121,175,345,352,354,358,360,364,371,378,382,385,394,399,453,467 'metric':126 'miss':537 'ml':478 'multi':14,42,71,196,206,210,242 'multi-ag':13,41,70,195,209,241 'multi-agent-pattern':205 'need':314 'orchestr':19,46,76,225,250,256,259,261,469 'output':509 'overview':30 'pass':472 'past':129,182,235,283,332,389,436 'pattern':55,105,152,154,188,208,212,260,490 'perform':426,445 'permiss':530 'persist':277 'phase':87,88,141,193,247,292,343,400 'plan':116 'planner':450 'prompt':130,183,236,284,333,390,437 'purpos':110 'qualiti':460 'rag':482,484 'rag-implement':481 'relat':473 'requir':528 'respons':454 'retriev':386 'review':521 'role':217,246 'safeti':531 'scenario':422 'scope':502 'set':82,219,373 'short':369 'short-term':368 'short/long-term':459 'singl':38,143,191 'skill':92,146,199,251,296,347,403,494 'skill-ai-agent-development' 'source-sickn33' 'special':31 'specif':516 'state':269,289 'stop':522 'structur':365 'substitut':512 'success':125,534 'system':16,44,73,122,198,244,346,353,395,485 'task':228,498 'term':370,377 'test':177,231,279,327,384,421,428,470,518 'tool':47,78,117,171,294,301,303,306,308,313,317,321,328,337,342,452,465 'tool-design':305 'topic-agent-skills' 'topic-agentic-skills' 'topic-ai-agent-skills' 'topic-ai-agents' 'topic-ai-coding' 'topic-ai-workflows' 'topic-antigravity' 'topic-antigravity-skills' 'topic-claude-code' 'topic-claude-code-skills' 'topic-codex-cli' 'topic-codex-skills' 'treat':507 'usag':329 'use':58,61,131,184,237,285,334,391,438,492 'user':448 'valid':517 'work':464 'workflow':8,29,32,60,63,86,258,265,280,291,474,487,489 'workflow-autom':486 'workflow-orchestration-pattern':257","prices":[{"id":"810fad7d-8a04-41fd-bc47-d810bbb2751f","listingId":"b583ab97-5ad9-4297-a7fa-b5be8dbe66f1","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"sickn33","category":"antigravity-awesome-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T21:30:37.650Z"}],"sources":[{"listingId":"b583ab97-5ad9-4297-a7fa-b5be8dbe66f1","source":"github","sourceId":"sickn33/antigravity-awesome-skills/ai-agent-development","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/ai-agent-development","isPrimary":false,"firstSeenAt":"2026-04-18T21:30:37.650Z","lastSeenAt":"2026-04-25T00:50:24.224Z"}],"details":{"listingId":"b583ab97-5ad9-4297-a7fa-b5be8dbe66f1","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"ai-agent-development","github":{"repo":"sickn33/antigravity-awesome-skills","stars":34964,"topics":["agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows","antigravity","antigravity-skills","claude-code","claude-code-skills","codex-cli","codex-skills","cursor","cursor-skills","developer-tools","gemini-cli","gemini-skills","kiro","mcp","skill-library"],"license":"mit","html_url":"https://github.com/sickn33/antigravity-awesome-skills","pushed_at":"2026-04-24T06:41:17Z","description":"Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.","skill_md_sha":"de60ce1dc9def20e2eb8bd9f46d4e5cdaf855950","skill_md_path":"skills/ai-agent-development/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/ai-agent-development"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"ai-agent-development","description":"AI agent development workflow for building autonomous agents, multi-agent systems, and agent orchestration with CrewAI, LangGraph, and custom agents."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/ai-agent-development"},"updatedAt":"2026-04-25T00:50:24.224Z"}}