{"id":"1a1d8899-0773-4589-9612-5a8420729312","shortId":"jTRmNk","kind":"skill","title":"Ai Agents Architect","tagline":"Antigravity Awesome Skills skill by Sickn33","description":"# AI Agents Architect\n\nExpert in designing and building autonomous AI agents. Masters tool use,\nmemory systems, planning strategies, and multi-agent orchestration.\n\n**Role**: AI Agent Systems Architect\n\nI build AI systems that can act autonomously while remaining controllable.\nI understand that agents fail in unexpected ways - I design for graceful\ndegradation and clear failure modes. I balance autonomy with oversight,\nknowing when an agent should ask for help vs proceed independently.\n\n### Expertise\n\n- Agent loop design (ReAct, Plan-and-Execute, etc.)\n- Tool definition and execution\n- Memory architectures (short-term, long-term, episodic)\n- Planning strategies and task decomposition\n- Multi-agent communication patterns\n- Agent evaluation and observability\n- Error handling and recovery\n- Safety and guardrails\n\n### Principles\n\n- Agents should fail loudly, not silently\n- Every tool needs clear documentation and examples\n- Memory is for context, not crutch\n- Planning reduces but doesn't eliminate errors\n- Multi-agent adds complexity - justify the overhead\n\n## Capabilities\n\n- Agent architecture design\n- Tool and function calling\n- Agent memory systems\n- Planning and reasoning strategies\n- Multi-agent orchestration\n- Agent evaluation and debugging\n\n## Prerequisites\n\n- Required skills: LLM API usage, Understanding of function calling, Basic prompt engineering\n\n## Patterns\n\n### ReAct Loop\n\nReason-Act-Observe cycle for step-by-step execution\n\n**When to use**: Simple tool use with clear action-observation flow\n\n- Thought: reason about what to do next\n- Action: select and invoke a tool\n- Observation: process tool result\n- Repeat until task complete or stuck\n- Include max iteration limits\n\n### Plan-and-Execute\n\nPlan first, then execute steps\n\n**When to use**: Complex tasks requiring multi-step planning\n\n- Planning phase: decompose task into steps\n- Execution phase: execute each step\n- Replanning: adjust plan based on results\n- Separate planner and executor models possible\n\n### Tool Registry\n\nDynamic tool discovery and management\n\n**When to use**: Many tools or tools that change at runtime\n\n- Register tools with schema and examples\n- Tool selector picks relevant tools for task\n- Lazy loading for expensive tools\n- Usage tracking for optimization\n\n### Hierarchical Memory\n\nMulti-level memory for different purposes\n\n**When to use**: Long-running agents needing context\n\n- Working memory: current task context\n- Episodic memory: past interactions/results\n- Semantic memory: learned facts and patterns\n- Use RAG for retrieval from long-term memory\n\n### Supervisor Pattern\n\nSupervisor agent orchestrates specialist agents\n\n**When to use**: Complex tasks requiring multiple skills\n\n- Supervisor decomposes and delegates\n- Specialists have focused capabilities\n- Results aggregated by supervisor\n- Error handling at supervisor level\n\n### Checkpoint Recovery\n\nSave state for resumption after failures\n\n**When to use**: Long-running tasks that may fail\n\n- Checkpoint after each successful step\n- Store task state, memory, and progress\n- Resume from last checkpoint on failure\n- Clean up checkpoints on completion\n\n## Sharp Edges\n\n### Agent loops without iteration limits\n\nSeverity: CRITICAL\n\nSituation: Agent runs until 'done' without max iterations\n\nSymptoms:\n- Agent runs forever\n- Unexplained high API costs\n- Application hangs\n\nWhy this breaks:\nAgents can get stuck in loops, repeating the same actions, or spiral\ninto endless tool calls. Without limits, this drains API credits,\nhangs the application, and frustrates users.\n\nRecommended fix:\n\nAlways set limits:\n- max_iterations on agent loops\n- max_tokens per turn\n- timeout on agent runs\n- cost caps for API usage\n- Circuit breakers for tool failures\n\n### Vague or incomplete tool descriptions\n\nSeverity: HIGH\n\nSituation: Tool descriptions don't explain when/how to use\n\nSymptoms:\n- Agent picks wrong tools\n- Parameter errors\n- Agent says it can't do things it can\n\nWhy this breaks:\nAgents choose tools based on descriptions. Vague descriptions lead to\nwrong tool selection, misused parameters, and errors. The agent\nliterally can't know what it doesn't see in the description.\n\nRecommended fix:\n\nWrite complete tool specs:\n- Clear one-sentence purpose\n- When to use (and when not to)\n- Parameter descriptions with types\n- Example inputs and outputs\n- Error cases to expect\n\n### Tool errors not surfaced to agent\n\nSeverity: HIGH\n\nSituation: Catching tool exceptions silently\n\nSymptoms:\n- Agent continues with wrong data\n- Final answers are wrong\n- Hard to debug failures\n\nWhy this breaks:\nWhen tool errors are swallowed, the agent continues with bad or missing\ndata, compounding errors. The agent can't recover from what it can't\nsee. Silent failures become loud failures later.\n\nRecommended fix:\n\nExplicit error handling:\n- Return error messages to agent\n- Include error type and recovery hints\n- Let agent retry or choose alternative\n- Log errors for debugging\n\n### Storing everything in agent memory\n\nSeverity: MEDIUM\n\nSituation: Appending all observations to memory without filtering\n\nSymptoms:\n- Context window exceeded\n- Agent references outdated info\n- High token costs\n\nWhy this breaks:\nMemory fills with irrelevant details, old information, and noise.\nThis bloats context, increases costs, and can cause the model to\nlose focus on what matters.\n\nRecommended fix:\n\nSelective memory:\n- Summarize rather than store verbatim\n- Filter by relevance before storing\n- Use RAG for long-term memory\n- Clear working memory between tasks\n\n### Agent has too many tools\n\nSeverity: MEDIUM\n\nSituation: Giving agent 20+ tools for flexibility\n\nSymptoms:\n- Wrong tool selection\n- Agent overwhelmed by options\n- Slow responses\n\nWhy this breaks:\nMore tools means more confusion. The agent must read and consider all\ntool descriptions, increasing latency and error rate. Long tool lists\nget cut off or poorly understood.\n\nRecommended fix:\n\nCurate tools per task:\n- 5-10 tools maximum per agent\n- Use tool selection layer for large tool sets\n- Specialized agents with focused tools\n- Dynamic tool loading based on task\n\n### Using multiple agents when one would work\n\nSeverity: MEDIUM\n\nSituation: Starting with multi-agent architecture for simple tasks\n\nSymptoms:\n- Agents duplicating work\n- Communication overhead\n- Hard to debug failures\n\nWhy this breaks:\nMulti-agent adds coordination overhead, communication failures,\ndebugging complexity, and cost. Each agent handoff is a potential\nfailure point. Start simple, add agents only when proven necessary.\n\nRecommended fix:\n\nJustify multi-agent:\n- Can one agent with good tools solve this?\n- Is the coordination overhead worth it?\n- Are the agents truly independent?\n- Start with single agent, measure limits\n\n### Agent internals not logged or traceable\n\nSeverity: MEDIUM\n\nSituation: Running agents without logging thoughts/actions\n\nSymptoms:\n- Can't explain agent failures\n- No visibility into agent reasoning\n- Debugging takes hours\n\nWhy this breaks:\nWhen agents fail, you need to see what they were thinking, which\ntools they tried, and where they went wrong. Without observability,\ndebugging is guesswork.\n\nRecommended fix:\n\nImplement tracing:\n- Log each thought/action/observation\n- Track tool calls with inputs/outputs\n- Trace token usage and latency\n- Use structured logging for analysis\n\n### Fragile parsing of agent outputs\n\nSeverity: MEDIUM\n\nSituation: Regex or exact string matching on LLM output\n\nSymptoms:\n- Parse errors in agent loop\n- Works sometimes, fails sometimes\n- Small prompt changes break parsing\n\nWhy this breaks:\nLLMs don't produce perfectly consistent output. Minor format variations\nbreak brittle parsers. This causes agent crashes or incorrect behavior\nfrom parsing errors.\n\nRecommended fix:\n\nRobust output handling:\n- Use structured output (JSON mode, function calling)\n- Fuzzy matching for actions\n- Retry with format instructions on parse failure\n- Handle multiple output formats\n\n## Related Skills\n\nWorks well with: `rag-engineer`, `prompt-engineer`, `backend`, `mcp-builder`\n\n## When to Use\n- User mentions or implies: build agent\n- User mentions or implies: AI agent\n- User mentions or implies: autonomous agent\n- User mentions or implies: tool use\n- User mentions or implies: function calling\n- User mentions or implies: multi-agent\n- User mentions or implies: agent memory\n- User mentions or implies: agent planning\n- User mentions or implies: langchain agent\n- User mentions or implies: crewai\n- User mentions or implies: autogen\n- User mentions or implies: claude agent sdk\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":["agents","architect","antigravity","awesome","skills","sickn33"],"capabilities":["skill","source-sickn33","category-antigravity-awesome-skills"],"categories":["antigravity-awesome-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/sickn33/antigravity-awesome-skills/ai-agents-architect","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 sickn33/antigravity-awesome-skills","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":"2026-04-25T11:40:49.117Z","embedding":null,"createdAt":"2026-04-18T20:35:04.780Z","updatedAt":"2026-04-25T11:40:49.117Z","lastSeenAt":"2026-04-25T11:40:49.117Z","tsv":"'-10':858 '20':806 '5':857 'act':44,202 'action':220,230,485,1123 'action-observ':219 'add':156,917,936 'adjust':281 'agent':2,11,20,31,35,52,74,83,112,115,127,155,162,169,178,180,347,377,380,448,456,464,476,512,520,549,555,567,585,633,642,664,674,699,707,719,735,796,805,814,829,862,872,884,896,902,916,927,937,947,950,964,970,973,983,991,996,1005,1054,1071,1100,1158,1164,1170,1189,1194,1200,1207,1223 'aggreg':398 'ai':1,10,19,34,40,1163 'altern':711 'alway':506 'analysi':1050 'answer':648 'antigrav':4 'api':188,469,496,525 'append':724 'applic':471,500 'architect':3,12,37 'architectur':97,163,897 'ask':76,1258 'autogen':1217 'autonom':18,45,1169 'autonomi':68 'awesom':5 'backend':1146 'bad':667 'balanc':67 'base':283,570,879 'basic':194 'becom':686 'behavior':1104 'bloat':755 'boundari':1266 'break':475,566,657,744,822,913,1003,1080,1084,1095 'breaker':528 'brittl':1096 'build':17,39,1157 'builder':1149 'call':168,193,491,1038,1119,1182 'cap':523 'capabl':161,396 'case':625 'catch':637 'category-antigravity-awesome-skills' 'caus':761,1099 'chang':307,1079 'checkpoint':406,424,438,443 'choos':568,710 'circuit':527 'clarif':1260 'claud':1222 'clean':441 'clear':63,136,218,604,791,1233 'communic':113,905,920 'complet':243,445,601 'complex':157,262,384,923 'compound':671 'confus':827 'consid':833 'consist':1090 'context':143,349,354,732,756 'continu':643,665 'control':48 'coordin':918,958 'cost':470,522,741,758,925 'crash':1101 'credit':497 'crewai':1212 'criteria':1269 'critic':454 'crutch':145 'curat':853 'current':352 'cut':846 'cycl':204 'data':646,670 'debug':183,653,715,909,922,998,1026 'decompos':271,390 'decomposit':109 'definit':93 'degrad':61 'deleg':392 'describ':1237 'descript':536,541,572,574,597,617,836 'design':15,58,85,164 'detail':749 'differ':339 'discoveri':296 'document':137 'doesn':149,592 'done':459 'drain':495 'duplic':903 'dynam':294,876 'edg':447 'elimin':151 'endless':489 'engin':196,1142,1145 'environ':1249 'environment-specif':1248 'episod':104,355 'error':119,152,401,554,583,624,629,660,672,693,696,701,713,840,1069,1107 'etc':91 'evalu':116,181 'everi':133 'everyth':717 'exact':1061 'exampl':139,315,620 'exceed':734 'except':639 'execut':90,95,210,253,257,275,277 'executor':289 'expect':627 'expens':326 'expert':13,1254 'expertis':82 'explain':544,990 'explicit':692 'fact':362 'fail':53,129,423,1006,1075 'failur':64,413,440,531,654,685,688,910,921,932,992,1130 'fill':746 'filter':730,779 'final':647 'first':255 'fix':505,599,691,771,852,943,1030,1109 'flexibl':809 'flow':222 'focus':395,766,874 'forev':466 'format':1093,1126,1134 'fragil':1051 'frustrat':502 'function':167,192,1118,1181 'fuzzi':1120 'get':478,845 'give':804 'good':952 'grace':60 'guardrail':125 'guesswork':1028 'handl':120,402,694,1112,1131 'handoff':928 'hang':472,498 'hard':651,907 'help':78 'hierarch':332 'high':468,538,635,739 'hint':705 'hour':1000 'implement':1031 'impli':1156,1162,1168,1174,1180,1186,1193,1199,1205,1211,1216,1221 'includ':246,700 'incomplet':534 'incorrect':1103 'increas':757,837 'independ':81,966 'info':738 'inform':751 'input':621,1263 'inputs/outputs':1040 'instruct':1127 'interactions/results':358 'intern':974 'invok':233 'irrelev':748 'iter':248,451,462,510 'json':1116 'justifi':158,944 'know':71,589 'langchain':1206 'larg':868 'last':437 'latenc':838,1045 'later':689 'layer':866 'lazi':323 'lead':575 'learn':361 'let':706 'level':336,405 'limit':249,452,493,508,972,1225 'list':844 'liter':586 'llm':187,1065 'llms':1085 'load':324,878 'log':712,976,985,1033,1048 'long':102,345,371,418,788,842 'long-run':344,417 'long-term':101,370,787 'loop':84,199,449,481,513,1072 'lose':765 'loud':130,687 'manag':298 'mani':302,799 'master':21 'match':1063,1121,1234 'matter':769 'max':247,461,509,514 'maximum':860 'may':422 'mcp':1148 'mcp-builder':1147 'mean':825 'measur':971 'medium':722,802,890,980,1057 'memori':24,96,140,170,333,337,351,356,360,373,432,720,728,745,773,790,793,1195 'mention':1154,1160,1166,1172,1178,1184,1191,1197,1203,1209,1214,1219 'messag':697 'minor':1092 'miss':669,1271 'misus':580 'mode':65,1117 'model':290,763 'multi':30,111,154,177,266,335,895,915,946,1188 'multi-ag':29,110,153,176,894,914,945,1187 'multi-level':334 'multi-step':265 'multipl':387,883,1132 'must':830 'necessari':941 'need':135,348,1008 'next':229 'nois':753 'observ':118,203,221,236,726,1025 'old':750 'one':606,886,949 'one-sent':605 'optim':331 'option':817 'orchestr':32,179,378 'outdat':737 'output':623,1055,1066,1091,1111,1115,1133,1243 'overhead':160,906,919,959 'oversight':70 'overwhelm':815 'paramet':553,581,616 'pars':1052,1068,1081,1106,1129 'parser':1097 'past':357 'pattern':114,197,364,375 'per':516,855,861 'perfect':1089 'permiss':1264 'phase':270,276 'pick':318,550 'plan':26,88,105,146,172,251,254,268,269,282,1201 'plan-and-execut':87,250 'planner':287 'point':933 'poor':849 'possibl':291 'potenti':931 'prerequisit':184 'principl':126 'proceed':80 'process':237 'produc':1088 'progress':434 'prompt':195,1078,1144 'prompt-engin':1143 'proven':940 'purpos':340,608 'rag':366,785,1141 'rag-engin':1140 'rate':841 'rather':775 'react':86,198 'read':831 'reason':174,201,224,997 'reason-act-observ':200 'recommend':504,598,690,770,851,942,1029,1108 'recov':677 'recoveri':122,407,704 'reduc':147 'refer':736 'regex':1059 'regist':310 'registri':293 'relat':1135 'relev':319,781 'remain':47 'repeat':240,482 'replan':280 'requir':185,264,386,1262 'respons':819 'result':239,285,397 'resum':435 'resumpt':411 'retri':708,1124 'retriev':368 'return':695 'review':1255 'robust':1110 'role':33 'run':346,419,457,465,521,982 'runtim':309 'safeti':123,1265 'save':408 'say':556 'schema':313 'scope':1236 'sdk':1224 'see':594,683,1010 'select':231,579,772,813,865 'selector':317 'semant':359 'sentenc':607 'separ':286 'set':507,870 'sever':453,537,634,721,801,889,979,1056 'sharp':446 'short':99 'short-term':98 'sickn33':9 'silent':132,640,684 'simpl':214,899,935 'singl':969 'situat':455,539,636,723,803,891,981,1058 'skill':6,7,186,388,1136,1228 'slow':818 'small':1077 'solv':954 'sometim':1074,1076 'source-sickn33' 'spec':603 'special':871 'specialist':379,393 'specif':1250 'spiral':487 'start':892,934,967 'state':409,431 'step':207,209,258,267,274,279,428 'step-by-step':206 'stop':1256 'store':429,716,777,783 'strategi':27,106,175 'string':1062 'structur':1047,1114 'stuck':245,479 'substitut':1246 'success':427,1268 'summar':774 'supervisor':374,376,389,400,404 'surfac':631 'swallow':662 'symptom':463,548,641,731,810,901,987,1067 'system':25,36,41,171 'take':999 'task':108,242,263,272,322,353,385,420,430,795,856,881,900,1232 'term':100,103,372,789 'test':1252 'thing':561 'think':1014 'thought':223 'thought/action/observation':1035 'thoughts/actions':986 'timeout':518 'token':515,740,1042 'tool':22,92,134,165,215,235,238,292,295,303,305,311,316,320,327,490,530,535,540,552,569,578,602,628,638,659,800,807,812,824,835,843,854,859,864,869,875,877,953,1016,1037,1175 'trace':1032,1041 'traceabl':978 'track':329,1036 'treat':1241 'tri':1018 'truli':965 'turn':517 'type':619,702 'understand':50,190 'understood':850 'unexpect':55 'unexplain':467 'usag':189,328,526,1043 'use':23,213,216,261,301,343,365,383,416,547,611,784,863,882,1046,1113,1152,1176,1226 'user':503,1153,1159,1165,1171,1177,1183,1190,1196,1202,1208,1213,1218 'vagu':532,573 'valid':1251 'variat':1094 'verbatim':778 'visibl':994 'vs':79 'way':56 'well':1138 'went':1022 'when/how':545 'window':733 'without':450,460,492,729,984,1024 'work':350,792,888,904,1073,1137 'worth':960 'would':887 'write':600 'wrong':551,577,645,650,811,1023","prices":[{"id":"360746a4-c26f-4eb5-9a95-5f4c2d0f9ad9","listingId":"1a1d8899-0773-4589-9612-5a8420729312","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":"2026-04-18T20:35:04.780Z"}],"sources":[{"listingId":"1a1d8899-0773-4589-9612-5a8420729312","source":"github","sourceId":"sickn33/antigravity-awesome-skills/ai-agents-architect","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/ai-agents-architect","isPrimary":false,"firstSeenAt":"2026-04-18T21:30:38.384Z","lastSeenAt":"2026-04-25T06:50:23.977Z"},{"listingId":"1a1d8899-0773-4589-9612-5a8420729312","source":"skills_sh","sourceId":"sickn33/antigravity-awesome-skills/ai-agents-architect","sourceUrl":"https://skills.sh/sickn33/antigravity-awesome-skills/ai-agents-architect","isPrimary":true,"firstSeenAt":"2026-04-18T20:35:04.780Z","lastSeenAt":"2026-04-25T11:40:49.117Z"}],"details":{"listingId":"1a1d8899-0773-4589-9612-5a8420729312","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"ai-agents-architect","source":"skills_sh","category":"antigravity-awesome-skills","skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/ai-agents-architect"},"updatedAt":"2026-04-25T11:40:49.117Z"}}