{"id":"6d2f6281-d8b8-4a16-85ec-09a323d9bb05","shortId":"rx2E2j","kind":"skill","title":"subagent-driven-development","tagline":"Use when executing implementation plans with independent tasks in the current session. Triggers on: \"execute the plan here\", \"dispatch subagents\", \"implement with reviews\", any same-session execution request. Dispatches fresh subagent per task with two-stage review (spec complian","description":"# Subagent-Driven Development\n\nExecute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.\n\n**Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration\n\n## When to Use\n\n```dot\ndigraph when_to_use {\n    \"Have implementation plan?\" [shape=diamond];\n    \"Tasks mostly independent?\" [shape=diamond];\n    \"Stay in this session?\" [shape=diamond];\n    \"subagent-driven-development\" [shape=box];\n    \"executing-plans\" [shape=box];\n    \"Manual execution or brainstorm first\" [shape=box];\n\n    \"Have implementation plan?\" -> \"Tasks mostly independent?\" [label=\"yes\"];\n    \"Have implementation plan?\" -> \"Manual execution or brainstorm first\" [label=\"no\"];\n    \"Tasks mostly independent?\" -> \"Stay in this session?\" [label=\"yes\"];\n    \"Tasks mostly independent?\" -> \"Manual execution or brainstorm first\" [label=\"no - tightly coupled\"];\n    \"Stay in this session?\" -> \"subagent-driven-development\" [label=\"yes\"];\n    \"Stay in this session?\" -> \"executing-plans\" [label=\"no - parallel session\"];\n}\n```\n\n**vs. Executing Plans (parallel session):**\n- Same session (no context switch)\n- Fresh subagent per task (no context pollution)\n- Two-stage review after each task: spec compliance first, then code quality\n- Faster iteration (no human-in-loop between tasks)\n\n## The Process\n\n```dot\ndigraph process {\n    rankdir=TB;\n\n    subgraph cluster_per_task {\n        label=\"Per Task\";\n        \"Dispatch implementer subagent (./implementer-prompt.md)\" [shape=box];\n        \"Implementer subagent asks questions?\" [shape=diamond];\n        \"Answer questions, provide context\" [shape=box];\n        \"Implementer subagent implements, tests, commits, self-reviews\" [shape=box];\n        \"Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)\" [shape=box];\n        \"Spec reviewer subagent confirms code matches spec?\" [shape=diamond];\n        \"Implementer subagent fixes spec gaps\" [shape=box];\n        \"Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)\" [shape=box];\n        \"Code quality reviewer subagent approves?\" [shape=diamond];\n        \"Implementer subagent fixes quality issues\" [shape=box];\n        \"Mark task complete in TodoWrite\" [shape=box];\n    }\n\n    \"Read plan, extract all tasks with full text, note context, create TodoWrite\" [shape=box];\n    \"More tasks remain?\" [shape=diamond];\n    \"Dispatch final code reviewer subagent for entire implementation\" [shape=box];\n    \"Use superpowers:finishing-a-development-branch\" [shape=box style=filled fillcolor=lightgreen];\n\n    \"Read plan, extract all tasks with full text, note context, create TodoWrite\" -> \"Dispatch implementer subagent (./implementer-prompt.md)\";\n    \"Dispatch implementer subagent (./implementer-prompt.md)\" -> \"Implementer subagent asks questions?\";\n    \"Implementer subagent asks questions?\" -> \"Answer questions, provide context\" [label=\"yes\"];\n    \"Answer questions, provide context\" -> \"Dispatch implementer subagent (./implementer-prompt.md)\";\n    \"Implementer subagent asks questions?\" -> \"Implementer subagent implements, tests, commits, self-reviews\" [label=\"no\"];\n    \"Implementer subagent implements, tests, commits, self-reviews\" -> \"Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)\";\n    \"Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)\" -> \"Spec reviewer subagent confirms code matches spec?\";\n    \"Spec reviewer subagent confirms code matches spec?\" -> \"Implementer subagent fixes spec gaps\" [label=\"no\"];\n    \"Implementer subagent fixes spec gaps\" -> \"Dispatch spec reviewer subagent (./spec-reviewer-prompt.md)\" [label=\"re-review\"];\n    \"Spec reviewer subagent confirms code matches spec?\" -> \"Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)\" [label=\"yes\"];\n    \"Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)\" -> \"Code quality reviewer subagent approves?\";\n    \"Code quality reviewer subagent approves?\" -> \"Implementer subagent fixes quality issues\" [label=\"no\"];\n    \"Implementer subagent fixes quality issues\" -> \"Dispatch code quality reviewer subagent (./code-quality-reviewer-prompt.md)\" [label=\"re-review\"];\n    \"Code quality reviewer subagent approves?\" -> \"Mark task complete in TodoWrite\" [label=\"yes\"];\n    \"Mark task complete in TodoWrite\" -> \"More tasks remain?\";\n    \"More tasks remain?\" -> \"Dispatch implementer subagent (./implementer-prompt.md)\" [label=\"yes\"];\n    \"More tasks remain?\" -> \"Dispatch final code reviewer subagent for entire implementation\" [label=\"no\"];\n    \"Dispatch final code reviewer subagent for entire implementation\" -> \"Use superpowers:finishing-a-development-branch\";\n}\n```\n\n## Prompt Templates\n\n- `./implementer-prompt.md` - Dispatch implementer subagent\n- `./spec-reviewer-prompt.md` - Dispatch spec compliance reviewer subagent\n- `./code-quality-reviewer-prompt.md` - Dispatch code quality reviewer subagent\n\n## Example Workflow\n\n```\nYou: I'm using Subagent-Driven Development to execute this plan.\n\n[Read plan file once: docs/plans/feature-plan.md]\n[Extract all 5 tasks with full text and context]\n[Create TodoWrite with all tasks]\n\nTask 1: Hook installation script\n\n[Get Task 1 text and context (already extracted)]\n[Dispatch implementation subagent with full task text + context]\n\nImplementer: \"Before I begin - should the hook be installed at user or system level?\"\n\nYou: \"User level (~/.config/superpowers/hooks/)\"\n\nImplementer: \"Got it. Implementing now...\"\n[Later] Implementer:\n  - Implemented install-hook command\n  - Added tests, 5/5 passing\n  - Self-review: Found I missed --force flag, added it\n  - Committed\n\n[Dispatch spec compliance reviewer]\nSpec reviewer: ✅ Spec compliant - all requirements met, nothing extra\n\n[Get git SHAs, dispatch code quality reviewer]\nCode reviewer: Strengths: Good test coverage, clean. Issues: None. Approved.\n\n[Mark Task 1 complete]\n\nTask 2: Recovery modes\n\n[Get Task 2 text and context (already extracted)]\n[Dispatch implementation subagent with full task text + context]\n\nImplementer: [No questions, proceeds]\nImplementer:\n  - Added verify/repair modes\n  - 8/8 tests passing\n  - Self-review: All good\n  - Committed\n\n[Dispatch spec compliance reviewer]\nSpec reviewer: ❌ Issues:\n  - Missing: Progress reporting (spec says \"report every 100 items\")\n  - Extra: Added --json flag (not requested)\n\n[Implementer fixes issues]\nImplementer: Removed --json flag, added progress reporting\n\n[Spec reviewer reviews again]\nSpec reviewer: ✅ Spec compliant now\n\n[Dispatch code quality reviewer]\nCode reviewer: Strengths: Solid. Issues (Important): Magic number (100)\n\n[Implementer fixes]\nImplementer: Extracted PROGRESS_INTERVAL constant\n\n[Code reviewer reviews again]\nCode reviewer: ✅ Approved\n\n[Mark Task 2 complete]\n\n...\n\n[After all tasks]\n[Dispatch final code-reviewer]\nFinal reviewer: All requirements met, ready to merge\n\nDone!\n```\n\n## Advantages\n\n**vs. Manual execution:**\n- Subagents follow TDD naturally\n- Fresh context per task (no confusion)\n- Parallel-safe (subagents don't interfere)\n- Subagent can ask questions (before AND during work)\n\n**vs. Executing Plans:**\n- Same session (no handoff)\n- Continuous progress (no waiting)\n- Review checkpoints automatic\n\n**Efficiency gains:**\n- No file reading overhead (controller provides full text)\n- Controller curates exactly what context is needed\n- Subagent gets complete information upfront\n- Questions surfaced before work begins (not after)\n\n**Quality gates:**\n- Self-review catches issues before handoff\n- Two-stage review: spec compliance, then code quality\n- Review loops ensure fixes actually work\n- Spec compliance prevents over/under-building\n- Code quality ensures implementation is well-built\n\n**Cost:**\n- More subagent invocations (implementer + 2 reviewers per task)\n- Controller does more prep work (extracting all tasks upfront)\n- Review loops add iterations\n- But catches issues early (cheaper than debugging later)\n\n## Red Flags\n\n**Never:**\n- Start implementation on main/master branch without explicit user consent\n- Skip reviews (spec compliance OR code quality)\n- Proceed with unfixed issues\n- Dispatch multiple implementation subagents in parallel (conflicts)\n- Make subagent read plan file (provide full text instead)\n- Skip scene-setting context (subagent needs to understand where task fits)\n- Ignore subagent questions (answer before letting them proceed)\n- Accept \"close enough\" on spec compliance (spec reviewer found issues = not done)\n- Skip review loops (reviewer found issues = implementer fixes = review again)\n- Let implementer self-review replace actual review (both are needed)\n- **Start code quality review before spec compliance is ✅** (wrong order)\n- Move to next task while either review has open issues\n\n**If subagent asks questions:**\n- Answer clearly and completely\n- Provide additional context if needed\n- Don't rush them into implementation\n\n**If reviewer finds issues:**\n- Implementer (same subagent) fixes them\n- Reviewer reviews again\n- Repeat until approved\n- Don't skip the re-review\n\n**If subagent fails task:**\n- Dispatch fix subagent with specific instructions\n- Don't try to fix manually (context pollution)\n\n## Integration\n\n**Required workflow skills:**\n- **superpowers:using-git-worktrees** - REQUIRED: Set up isolated workspace before starting\n- **superpowers:writing-plans** - Creates the plan this skill executes\n- **superpowers:requesting-code-review** - Code review template for reviewer subagents\n- **superpowers:finishing-a-development-branch** - Complete development after all tasks\n\n**Subagents should use:**\n- **superpowers:test-driven-development** - Subagents follow TDD for each task\n\n**Alternative workflow:**\n- **superpowers:executing-plans** - Use for parallel session instead of same-session execution\n\n## Examples\n\n### Example 1: Simple Task Execution\nTask: \"Add button component\"\nDispatch: Implementer subagent with full task text\nImplementer: Implements, tests, commits\nReview 1: Spec reviewer confirms matches spec\nReview 2: Code reviewer approves quality\nResult: Task complete, move to next\n\n### Example 2: Task with Questions\nTask: \"Add authentication\"\nDispatch: Implementer subagent with full task text\nImplementer: \"Should I use OAuth or credentials?\"\nYou: \"OAuth with Google\"\nImplementer: Implements with OAuth\nReview 1: Spec reviewer confirms OAuth integration correct\nReview 2: Code reviewer approves security practices\nResult: Task complete\n\n### Example 3: Review Loop\nTask: \"Add form validation\"\nDispatch: Implementer subagent\nImplementer: Implements, tests pass\nReview 1: Spec reviewer finds missing email validation\nImplementer: Adds email validation\nReview 1 (re-check): Spec reviewer confirms complete\nReview 2: Code reviewer approves\nResult: Task complete\n\n## Troubleshooting\n\n### Issue: Subagent asks questions\nSolution: Answer clearly and completely. Provide additional context if needed. Don't rush them into implementation.\n\n### Issue: Reviewer finds issues\nSolution: Same subagent fixes them. Reviewer reviews again. Repeat until approved. Don't skip re-review.\n\n### Issue: Subagent fails task\nSolution: Dispatch fix subagent with specific instructions. Don't try to fix manually (context pollution).","tags":["subagent","driven","development","synapse","deve1993","agent-skills","ai-agents","ai-coding","ai-workspace","anti-poisoning","auto-learning-ai","automation"],"capabilities":["skill","source-deve1993","skill-subagent-driven-development","topic-agent-skills","topic-ai-agents","topic-ai-coding","topic-ai-workspace","topic-anti-poisoning","topic-auto-learning-ai","topic-automation","topic-claude-code","topic-code-quality","topic-cursor","topic-developer-tools","topic-devops"],"categories":["Synapse"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/deve1993/Synapse/subagent-driven-development","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add deve1993/Synapse","source_repo":"https://github.com/deve1993/Synapse","install_from":"skills.sh"}},"qualityScore":"0.453","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 7 github stars · SKILL.md body (11,245 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":"2026-05-18T19:14:14.316Z","embedding":null,"createdAt":"2026-05-18T13:21:47.441Z","updatedAt":"2026-05-18T19:14:14.316Z","lastSeenAt":"2026-05-18T19:14:14.316Z","tsv":"'/.config/superpowers/hooks':675 '/code-quality-reviewer-prompt.md':301,488,496,524,598 '/implementer-prompt.md':248,382,386,408,555,588 '/spec-reviewer-prompt.md':277,435,440,471,592 '1':638,644,735,1252,1272,1321,1354,1366 '100':788,827 '2':738,743,844,976,1279,1291,1329,1375 '3':1339 '5':625 '5/5':690 '8/8':765 'accept':1060 'actual':957,1088 'ad':688,700,762,791,803 'add':991,1257,1296,1343,1362 'addit':1122,1393 'advantag':863 'alreadi':648,747 'altern':1234 'answer':257,395,401,1055,1117,1388 'approv':308,501,506,533,732,841,1146,1282,1332,1378,1417 'ask':253,389,393,411,886,1115,1385 'authent':1297 'automat':905 'begin':661,932 'box':119,124,131,250,262,272,279,295,303,317,324,338,353,362 'brainstorm':128,146,165 'branch':360,585,1008,1214 'built':970 'button':1258 'catch':940,994 'cheaper':997 'check':1369 'checkpoint':904 'clean':729 'clear':1118,1389 'close':1061 'cluster':239 'code':70,220,284,297,304,346,445,452,480,484,492,497,502,520,529,563,573,600,720,723,816,819,835,839,852,951,963,1018,1094,1201,1203,1280,1330,1376 'code-review':851 'command':687 'commit':267,417,427,702,773,1270 'complet':320,536,543,736,845,925,1120,1215,1286,1337,1373,1381,1391 'complian':45 'complianc':66,217,595,705,776,949,960,1016,1065,1099 'compliant':710,813 'compon':1259 'confirm':283,444,451,479,1275,1324,1372 'conflict':1030 'confus':876 'consent':1012 'constant':834 'context':200,207,260,334,376,398,404,631,647,657,746,756,872,920,1044,1123,1170,1394,1441 'continu':899 'control':912,916,980 'core':73 'correct':1327 'cost':971 'coupl':170 'coverag':728 'creat':335,377,632,1192 'credenti':1311 'curat':917 'current':15 'debug':999 'develop':4,49,117,178,359,584,613,1213,1216,1227 'diamond':102,107,113,256,288,310,343 'digraph':94,234 'dispatch':23,34,53,245,273,296,344,379,383,405,431,436,467,483,491,519,552,561,571,589,593,599,650,703,719,749,774,815,849,1024,1158,1260,1298,1346,1429 'docs/plans/feature-plan.md':622 'done':862,1071 'dot':93,233 'driven':3,48,116,177,612,1226 'earli':996 'effici':906 'either':1108 'email':1359,1363 'enough':1062 'ensur':955,965 'entir':350,567,577 'everi':787 'exact':918 'exampl':604,1250,1251,1290,1338 'execut':7,19,32,50,121,126,144,163,186,193,615,866,893,1197,1238,1249,1255 'executing-plan':120,185,1237 'explicit':1010 'extra':715,790 'extract':327,369,623,649,748,831,985 'fail':1156,1426 'fast':88 'faster':222 'file':620,909,1035 'fill':364 'fillcolor':365 'final':345,562,572,850,854 'find':1134,1357,1405 'finish':357,582,1211 'finishing-a-development-branch':356,581,1210 'first':68,129,147,166,218 'fit':1051 'fix':291,313,457,464,509,516,797,829,956,1079,1139,1159,1168,1410,1430,1439 'flag':699,793,802,1002 'follow':868,1229 'forc':698 'form':1344 'found':695,1068,1076 'fresh':35,54,75,202,871 'full':331,373,628,654,753,914,1037,1264,1302 'gain':907 'gap':293,459,466 'gate':936 'get':642,716,741,924 'git':717,1179 'good':726,772 'googl':1315 'got':677 'handoff':898,943 'high':86 'hook':639,664,686 'human':226 'human-in-loop':225 'ignor':1052 'implement':8,25,99,133,141,246,251,263,265,289,311,351,380,384,387,391,406,409,413,415,423,425,455,462,507,514,553,568,578,590,651,658,676,679,682,683,750,757,761,796,799,828,830,966,975,1005,1026,1078,1083,1131,1136,1261,1267,1268,1299,1305,1316,1317,1347,1349,1350,1361,1402 'import':824 'independ':11,105,137,152,161 'inform':926 'instal':640,666,685 'install-hook':684 'instead':1039,1244 'instruct':1163,1434 'integr':1172,1326 'interfer':883 'interv':833 'invoc':974 'isol':1184 'issu':315,511,518,730,780,798,823,941,995,1023,1069,1077,1112,1135,1383,1403,1406,1424 'item':789 'iter':89,223,992 'json':792,801 'label':138,148,157,167,179,188,242,399,421,460,472,489,512,525,539,556,569 'later':681,1000 'let':1057,1082 'level':671,674 'lightgreen':366 'loop':228,954,990,1074,1341 'm':608 'magic':825 'main/master':1007 'make':1031 'manual':125,143,162,865,1169,1440 'mark':318,534,541,733,842 'match':285,446,453,481,1276 'merg':861 'met':713,858 'miss':697,781,1358 'mode':740,764 'most':104,136,151,160 'move':1103,1287 'multipl':1025 'natur':870 'need':922,1046,1092,1125,1396 'never':1003 'next':1105,1289 'none':731 'note':333,375 'noth':714 'number':826 'oauth':1309,1313,1319,1325 'open':1111 'order':1102 'over/under-building':962 'overhead':911 'parallel':190,195,878,1029,1242 'parallel-saf':877 'pass':691,767,1352 'per':37,56,77,204,240,243,873,978 'plan':9,21,51,100,122,134,142,187,194,326,368,617,619,894,1034,1191,1194,1239 'pollut':208,1171,1442 'practic':1334 'prep':983 'prevent':961 'principl':74 'proceed':760,1020,1059 'process':232,235 'progress':782,804,832,900 'prompt':586 'provid':259,397,403,913,1036,1121,1392 'qualiti':71,85,87,221,298,305,314,485,493,498,503,510,517,521,530,601,721,817,935,952,964,1019,1095,1283 'question':254,258,390,394,396,402,412,759,887,928,1054,1116,1294,1386 'rankdir':236 're':474,527,1152,1368,1422 're-check':1367 're-review':473,526,1151,1421 'read':325,367,618,910,1033 'readi':859 'recoveri':739 'red':1001 'remain':341,548,551,560 'remov':800 'repeat':1144,1415 'replac':1087 'report':783,786,805 'request':33,795,1200 'requesting-code-review':1199 'requir':712,857,1173,1181 'result':1284,1335,1379 'review':27,43,62,67,72,82,212,270,275,281,299,306,347,420,430,433,438,442,449,469,475,477,486,494,499,504,522,528,531,564,574,596,602,694,706,708,722,724,770,777,779,807,808,811,818,820,836,837,840,853,855,903,939,947,953,977,989,1014,1067,1073,1075,1080,1086,1089,1096,1109,1133,1141,1142,1153,1202,1204,1207,1271,1274,1278,1281,1320,1323,1328,1331,1340,1353,1356,1365,1371,1374,1377,1404,1412,1413,1423 'rush':1128,1399 'safe':879 'same-sess':29,1246 'say':785 'scene':1042 'scene-set':1041 'script':641 'secur':1333 'self':269,419,429,693,769,938,1085 'self-review':268,418,428,692,768,937,1084 'session':16,31,111,156,174,184,191,196,198,896,1243,1248 'set':1043,1182 'shape':101,106,112,118,123,130,249,255,261,271,278,287,294,302,309,316,323,337,342,352,361 'shas':718 'simpl':1253 'skill':1175,1196 'skill-subagent-driven-development' 'skip':1013,1040,1072,1149,1420 'solid':822 'solut':1387,1407,1428 'source-deve1993' 'spec':44,65,83,216,274,280,286,292,432,437,441,447,448,454,458,465,468,476,482,594,704,707,709,775,778,784,806,810,812,948,959,1015,1064,1066,1098,1273,1277,1322,1355,1370 'specif':1162,1433 'stage':42,61,81,211,946 'start':1004,1093,1187 'stay':108,153,171,181 'strength':725,821 'style':363 'subag':2,24,36,47,55,76,115,176,203,247,252,264,276,282,290,300,307,312,348,381,385,388,392,407,410,414,424,434,439,443,450,456,463,470,478,487,495,500,505,508,515,523,532,554,565,575,591,597,603,611,652,751,867,880,884,923,973,1027,1032,1045,1053,1114,1138,1155,1160,1208,1220,1228,1262,1300,1348,1384,1409,1425,1431 'subagent-driven':46,610 'subagent-driven-develop':1,114,175 'subgraph':238 'superpow':355,580,1176,1188,1198,1209,1223,1236 'surfac':929 'switch':201 'system':670 'task':12,38,57,78,103,135,150,159,205,215,230,241,244,319,329,340,371,535,542,547,550,559,626,636,637,643,655,734,737,742,754,843,848,874,979,987,1050,1106,1157,1219,1233,1254,1256,1265,1285,1292,1295,1303,1336,1342,1380,1427 'tb':237 'tdd':869,1230 'templat':587,1205 'test':266,416,426,689,727,766,1225,1269,1351 'test-driven-develop':1224 'text':332,374,629,645,656,744,755,915,1038,1266,1304 'tight':169 'todowrit':322,336,378,538,545,633 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-coding' 'topic-ai-workspace' 'topic-anti-poisoning' 'topic-auto-learning-ai' 'topic-automation' 'topic-claude-code' 'topic-code-quality' 'topic-cursor' 'topic-developer-tools' 'topic-devops' 'tri':1166,1437 'trigger':17 'troubleshoot':1382 'two':41,60,80,210,945 'two-stag':40,59,79,209,944 'understand':1048 'unfix':1022 'upfront':927,988 'use':5,92,97,354,579,609,1178,1222,1240,1308 'user':668,673,1011 'using-git-worktre':1177 'valid':1345,1360,1364 'verify/repair':763 'vs':192,864,892 'wait':902 'well':969 'well-built':968 'without':1009 'work':891,931,958,984 'workflow':605,1174,1235 'workspac':1185 'worktre':1180 'write':1190 'writing-plan':1189 'wrong':1101 'yes':139,158,180,400,490,540,557","prices":[{"id":"28b82d7e-20ce-4dc2-b666-1a2534a64f30","listingId":"6d2f6281-d8b8-4a16-85ec-09a323d9bb05","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"deve1993","category":"Synapse","install_from":"skills.sh"},"createdAt":"2026-05-18T13:21:47.441Z"}],"sources":[{"listingId":"6d2f6281-d8b8-4a16-85ec-09a323d9bb05","source":"github","sourceId":"deve1993/Synapse/subagent-driven-development","sourceUrl":"https://github.com/deve1993/Synapse/tree/main/skills/subagent-driven-development","isPrimary":false,"firstSeenAt":"2026-05-18T13:21:47.441Z","lastSeenAt":"2026-05-18T19:14:14.316Z"}],"details":{"listingId":"6d2f6281-d8b8-4a16-85ec-09a323d9bb05","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"deve1993","slug":"subagent-driven-development","github":{"repo":"deve1993/Synapse","stars":7,"topics":["agent-skills","ai-agents","ai-coding","ai-workspace","anti-poisoning","auto-learning-ai","automation","claude-code","code-quality","cursor","developer-tools","devops","fullstack-development","multi-agent-systems","nextjs","opencode","persistent-memory","self-improving","telegram-bot"],"license":"other","html_url":"https://github.com/deve1993/Synapse","pushed_at":"2026-05-15T21:34:01Z","description":"Self-improving AI brain for Claude Code & Desktop — 28 MCP tools, 253 skills, collective memory, project tracking, work logs. One server, all your sessions share the same knowledge. Deploy on Coolify in 2 minutes.","skill_md_sha":"c95075a7601440cb0f6e111c34ba2af8d59f9f08","skill_md_path":"skills/subagent-driven-development/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/deve1993/Synapse/tree/main/skills/subagent-driven-development"},"layout":"multi","source":"github","category":"Synapse","frontmatter":{"name":"subagent-driven-development","description":"Use when executing implementation plans with independent tasks in the current session. Triggers on: \"execute the plan here\", \"dispatch subagents\", \"implement with reviews\", any same-session execution request. Dispatches fresh subagent per task with two-stage review (spec compliance then code quality)."},"skills_sh_url":"https://skills.sh/deve1993/Synapse/subagent-driven-development"},"updatedAt":"2026-05-18T19:14:14.316Z"}}