{"id":"41299fd3-96de-488d-b69c-2552be0dcbf2","shortId":"GaN8mH","kind":"skill","title":"recipe-fullstack-build","tagline":"Execute decomposed fullstack tasks with layer-aware agent routing","description":"## Orchestrator Definition\n\n**Core Identity**: \"I am an orchestrator.\" (see subagents-orchestration-guide skill)\n\n## Required Reference\n\n**MANDATORY**: Read `references/monorepo-flow.md` from subagents-orchestration-guide skill BEFORE proceeding. Follow the Extended Task Cycle and Agent Routing defined there.\n\n## Execution Protocol\n\n1. **Delegate all work through Agent tool** — invoke sub-agents, pass deliverable paths between them, and report results (permitted tools: see subagents-orchestration-guide \"Orchestrator's Permitted Tools\")\n2. **Route agents by task filename pattern** (see monorepo-flow.md reference):\n   - `*-backend-task-*` → task-executor + quality-fixer\n   - `*-frontend-task-*` → task-executor-frontend + quality-fixer-frontend\n3. **Follow the 4-step task cycle exactly**: executor → escalation check → quality-fixer → commit\n4. **Enter autonomous mode** when user provides execution instruction with existing task files — this IS the batch approval\n5. **Scope**: Complete when all tasks are committed or escalation occurs\n\n**CRITICAL**: Run layer-appropriate quality-fixer(s) before every commit.\n\nWork plan: $ARGUMENTS\n\n## Pre-execution Prerequisites\n\n### Implementation Readiness Check\n\nBefore any task processing, locate the work plan to gate against. Resolution rule:\n1. List task files in `docs/plans/tasks/` matching the layer-aware patterns `{plan-name}-backend-task-*.md` and `{plan-name}-frontend-task-*.md` only. Single-layer tasks (`{plan-name}-task-*.md`) are excluded here so a stale single-layer run does not redirect this recipe to the wrong work plan\n2. From the matched files, also exclude every file matching any of these patterns — they originate from other workflow phases and are not implementation tasks for this run's plan: `*-task-prep-*.md` (readiness preflight tasks), `_overview-*.md` (decomposition overview file), `*-phase*-completion.md` (per-phase completion files), `review-fixes-*.md` (post-implementation review fixes), `integration-tests-*-task-*.md` (integration-test add-on scaffolding)\n3. For each remaining file, extract the `{plan-name}` prefix as the segment that appears before `-backend-task-` or `-frontend-task-`\n4. When at least one task file matches, the work plan is `docs/plans/{plan-name}.md` for the prefix that has the most recent task-file mtime; ties broken by the lexicographically last `{plan-name}`\n5. When no task file matches the restricted pattern, the work plan is the most-recent-mtime non-template `.md` in `docs/plans/`\n\nRead the work plan header and find the line `Implementation Readiness: <status>`. Apply this rule:\n\n| Status | Action |\n|--------|--------|\n| `ready` | Proceed to Consumed Task Set computation |\n| `escalated` | Read the work plan's Readiness Report section, surface remaining gaps to the user via AskUserQuestion: \"Implementation Readiness is `escalated` with the following remaining gaps: [list]. Continue execution? (y/n)\". On `y` proceed; on `n` stop |\n| `pending` | Present via AskUserQuestion: \"Implementation Readiness is `pending`. Run `/recipe-prepare-implementation [plan-path]` first to verify the work plan is implementable, then resume. Continue without preflight? (y/n)\". On `y` proceed; on `n` stop |\n| absent (line missing) | Treat as `pending` — older work plans created before the readiness marker existed should be preflighted explicitly |\n\n### Consumed Task Set\n\nCompute the **Consumed Task Set** for this run — the exact files this recipe owns, executes, and later deletes. Use the same restricted pattern as the Implementation Readiness Check:\n\n1. List task files in `docs/plans/tasks/` matching the layer-aware patterns `{plan-name}-backend-task-*.md` and `{plan-name}-frontend-task-*.md` for the `{plan-name}` resolved by the readiness check. Single-layer tasks are excluded\n2. Exclude every file matching: `*-task-prep-*.md`, `_overview-*.md`, `*-phase*-completion.md`, `review-fixes-*.md`, `integration-tests-*-task-*.md` (these originate from other workflow phases)\n\nEvery subsequent reference to \"task files\" in this recipe — Task Generation Decision Flow, Task Execution Cycle iteration, and Final Cleanup — uses this set, not the unrestricted `docs/plans/tasks/*.md` glob.\n\n### Task Generation Decision Flow\n\nAnalyze the Consumed Task Set and determine the action required:\n\n| State | Criteria | Next Action |\n|-------|----------|-------------|\n| Tasks exist | Consumed Task Set is non-empty | User's execution instruction serves as batch approval → Enter autonomous execution immediately |\n| No tasks + plan exists | Consumed Task Set is empty but the resolved work plan exists | Confirm with user → run task-decomposer |\n| Neither exists + Design Doc exists | No plan, no Consumed Task Set, but `docs/design/*.md` exists | Invoke work-planner to create work plan from Design Doc(s), then proceed to task decomposition |\n| Neither exists | No plan, no Consumed Task Set, no Design Doc | Report missing prerequisites to user and stop |\n\n## Task Decomposition Phase (Conditional)\n\nWhen the Consumed Task Set is empty:\n\n### 1. User Confirmation\n```\nNo task files in the Consumed Task Set.\nWork plan: docs/plans/[plan-name].md\n\nGenerate tasks from the work plan? (y/n):\n```\n\n### 2. Task Decomposition (if approved)\nInvoke task-decomposer using Agent tool:\n- `subagent_type`: \"dev-workflows:task-decomposer\"\n- `description`: \"Decompose work plan\"\n- `prompt`: \"Read work plan at docs/plans/[plan-name].md and decompose into atomic tasks. Output: Individual task files in docs/plans/tasks/. Granularity: 1 task = 1 commit = independently executable. Use layer-aware naming: {plan}-backend-task-{n}.md, {plan}-frontend-task-{n}.md based on Target files paths.\"\n\n### 3. Verify Generation\nRecompute the Consumed Task Set using the same restricted pattern from the Consumed Task Set section above. Confirm it is now non-empty. If it is still empty, escalate to the user — task-decomposer either failed silently or produced files that don't match the expected pattern.\n\n## Pre-execution Checklist\n\n- [ ] Confirmed Consumed Task Set is non-empty (computed in the Consumed Task Set section above)\n- [ ] Identified task execution order within the Consumed Task Set (dependencies)\n- [ ] **Environment check**: Can I execute per-task commit cycle?\n  - If commit capability unavailable → Escalate before autonomous mode\n  - Other environments (tests, quality tools) → Subagents will escalate\n\n## Task Execution Cycle (Filename-Pattern-Based)\n\n**MANDATORY**: For each task in the Consumed Task Set, route agents by task filename pattern from monorepo-flow.md reference.\n\n### Agent Routing Table\n\n| Filename Pattern | Executor | Quality Fixer |\n|-----------------|----------|---------------|\n| `*-backend-task-*` | dev-workflows:task-executor | dev-workflows:quality-fixer |\n| `*-frontend-task-*` | dev-workflows-frontend:task-executor-frontend | dev-workflows-frontend:quality-fixer-frontend |\n| `*-task-*` (no layer prefix) | dev-workflows:task-executor | dev-workflows:quality-fixer (default) |\n\n### Task Execution (4-Step Cycle)\n\nFor EACH task, YOU MUST:\n1. **Register tasks using TaskCreate**: Register work steps. Always include first task \"Map preloaded skills to applicable concrete rules\" and final task \"Verify the mapped rules before final JSON\"\n2. **Agent tool** (subagent_type per routing table) → Pass task file path in prompt, receive structured response\n3. **CHECK executor response**:\n   - `status: \"escalation_needed\"` or `\"blocked\"` → STOP and escalate to user\n   - `requiresTestReview` is `true` → Execute **integration-test-reviewer**\n     - `needs_revision` → Return to step 2 with `requiredFixes`\n     - `approved` → Proceed to step 4\n   - `readyForQualityCheck: true` → Proceed to step 4\n4. **INVOKE quality-fixer**: Execute all quality checks and fixes (layer-appropriate per routing table). **Always pass** the current task file path as `task_file`\n5. **CHECK quality-fixer response**:\n   - `stub_detected` → Return to step 2 with `incompleteImplementations[]` details\n   - `blocked` → STOP and escalate to user\n   - `approved` → Proceed to step 6\n6. **COMMIT on approval**: Execute git commit\n\n**CRITICAL**: Parse every sub-agent response for status fields. Execute the matching branch in the 4-step cycle. Proceed to next task only after layer-appropriate quality-fixer returns `approved`.\n\n## Scope Boundary for Subagents\n\nAppend the following block to every subagent prompt invoked from this recipe:\n\n```\nScope boundary for subagents:\nOperate within the task scope and referenced files in the prompt.\nUse loaded skills to execute that scope.\nEscalate when the required fix or investigation falls outside that scope.\n```\n\nVerify task files exist per Pre-execution Checklist, then enter autonomous execution mode. When requirement changes are detected during execution, escalate to the user with the change summary before continuing.\n\n## Post-Implementation Verification (After All Tasks Complete)\n\nAfter all task cycles finish, run verification agents **in parallel** before the completion report:\n\n1. **Invoke both in parallel** using Agent tool:\n   - code-verifier (subagent_type: \"dev-workflows:code-verifier\") → invoke **once per Design Doc** (`doc_type: design-doc`, single `document_path`, `code_paths`: implementation file list from `git diff --name-only main...HEAD`)\n   - security-reviewer (subagent_type: \"dev-workflows:security-reviewer\") → Design Doc path(s), implementation file list\n\n2. **Consolidate results** — check pass/fail for each:\n   - code-verifier: **pass** when `status` is `consistent` or `mostly_consistent`. **fail** when `needs_review` or `inconsistent`. Collect `discrepancies` with status `drift`, `conflict`, or `gap`\n   - security-reviewer: **pass** when `status` is `approved` or `approved_with_notes`. **fail** when `needs_revision`. **blocked** → Escalate to user\n   - Present unified verification report to user\n\n3. **Fix cycle** (when any verifier failed):\n   - Consolidate all actionable findings into a single task file\n   - Execute layer-appropriate task-executor with consolidated fixes → quality-fixer\n   - Re-run only the failed verifiers (by the criteria in step 2)\n   - Repeat until all pass or `blocked` → Escalate to user\n\n4. **All passed** → Proceed to Final Cleanup\n\n## Final Cleanup\n\nBefore the completion report, delete the implementation task files this recipe consumed. Their work is committed; `docs/plans/` is ephemeral working state and is not retained between recipe runs:\n\n- Delete every file in the Consumed Task Set\n- Delete every file matching `docs/plans/tasks/{plan-name}-phase*-completion.md` (the per-phase completion files generated by task-decomposer for this `{plan-name}`)\n- Delete the corresponding `docs/plans/tasks/_overview-{plan-name}.md` if present\n- Preserve the work plan itself (`docs/plans/{plan-name}.md`) — the user decides whether to delete it after final review\n\nIf task files cannot be deleted (filesystem error), report the failure but do not block the completion report.\n\n## Output Example\nFullstack implementation phase completed.\n- Task decomposition: Generated under docs/plans/tasks/\n- Implemented tasks: [number] tasks (backend: X, frontend: Y)\n- Quality checks: All passed\n- Commits: [number] commits created\n- Cleanup: Task files removed from docs/plans/tasks/","tags":["recipe","fullstack","build","claude","code","workflows","shinpr","agent-skills","agentic-ai","ai-agents","automation","claude-code"],"capabilities":["skill","source-shinpr","skill-recipe-fullstack-build","topic-agent-skills","topic-agentic-ai","topic-ai-agents","topic-automation","topic-claude-code","topic-claude-code-plugin","topic-code-quality","topic-developer-tools","topic-development-workflow","topic-llm-orchestration","topic-productivity","topic-prompt-engineering"],"categories":["claude-code-workflows"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/shinpr/claude-code-workflows/recipe-fullstack-build","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add shinpr/claude-code-workflows","source_repo":"https://github.com/shinpr/claude-code-workflows","install_from":"skills.sh"}},"qualityScore":"0.613","qualityRationale":"deterministic score 0.61 from registry signals: · indexed on github topic:agent-skills · 327 github stars · SKILL.md body (11,303 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":"2026-05-02T18:53:52.590Z","embedding":null,"createdAt":"2026-04-18T22:03:12.016Z","updatedAt":"2026-05-02T18:53:52.590Z","lastSeenAt":"2026-05-02T18:53:52.590Z","tsv":"'/recipe-prepare-implementation':474 '1':54,193,548,770,841,843,1071,1353 '2':84,250,591,795,1100,1144,1196,1416,1515 '3':114,320,869,1117,1474 '4':117,129,344,1063,1151,1157,1158,1234,1525 '5':147,382,1185 '6':1210,1211 'absent':498 'action':421,660,665,1483 'add':317 'add-on':316 'agent':13,48,59,64,86,805,994,1002,1101,1223,1346,1359 'also':255 'alway':1079,1175 'analyz':652 'appear':335 'append':1255 'appli':417 'applic':1087 'appropri':162,1171,1245,1493 'approv':146,682,799,1147,1206,1214,1250,1455,1457 'argument':172 'askuserquest':445,468 'atom':832 'autonom':131,684,967,1311 'awar':12,203,558,850 'backend':95,209,338,564,854,1011,1659 'backend-task':94,208,337,563,853,1010 'base':864,983 'batch':145,681 'block':1125,1200,1258,1464,1521,1640 'boundari':1252,1268 'branch':1231 'broken':374 'build':4 'cannot':1629 'capabl':963 'chang':1316,1327 'check':124,179,547,584,952,1118,1166,1186,1419,1664 'checklist':924,1308 'cleanup':638,1531,1533,1671 'code':1362,1370,1385,1424 'code-verifi':1361,1369,1423 'collect':1440 'commit':128,154,169,844,959,962,1212,1217,1549,1667,1669 'complet':149,297,1338,1351,1536,1584,1642,1649 'completion.md':293,603,1579 'comput':428,520,933 'concret':1088 'condit':762 'confirm':702,772,889,925 'conflict':1445 'consist':1430,1433 'consolid':1417,1481,1498 'consum':425,517,522,654,668,691,717,746,765,778,874,884,926,936,947,990,1545,1567 'continu':456,488,1330 'core':17 'correspond':1598 'creat':507,729,1670 'criteria':663,1512 'critic':158,1218 'current':1178 'cycl':46,120,634,960,979,1065,1236,1342,1476 'decid':1618 'decis':630,650 'decompos':6,708,803,814,816,830,907,1590 'decomposit':289,740,760,797,1651 'default':1060 'defin':50 'definit':16 'deleg':55 'delet':537,1538,1562,1570,1596,1621,1631 'deliver':66 'depend':950 'descript':815 'design':711,733,750,1375,1380,1409 'design-doc':1379 'detail':1199 'detect':1192,1318 'determin':658 'dev':810,1014,1020,1029,1037,1049,1055,1367,1404 'dev-workflow':809,1013,1019,1048,1054,1366,1403 'dev-workflows-frontend':1028,1036 'diff':1392 'discrep':1441 'doc':712,734,751,1376,1377,1381,1410 'docs/design':721 'docs/plans':356,405,783,824,1550,1611 'docs/plans/tasks':198,553,645,839,1574,1654,1676 'docs/plans/tasks/_overview-':1599 'document':1383 'drift':1444 'either':908 'empti':674,695,769,895,900,932 'enter':130,683,1310 'environ':951,970 'ephemer':1552 'error':1633 'escal':123,156,429,449,901,965,976,1122,1128,1203,1289,1321,1465,1522 'everi':168,257,593,619,1220,1260,1563,1571 'exact':121,529 'exampl':1645 'exclud':231,256,590,592 'execut':5,52,136,175,457,534,633,677,685,846,923,943,955,978,1062,1134,1163,1215,1228,1286,1307,1312,1320,1490 'executor':99,108,122,1007,1018,1034,1053,1119,1496 'exist':139,512,667,690,701,710,713,723,742,1303 'expect':919 'explicit':516 'extend':44 'extract':325 'fail':909,1434,1460,1480,1508 'failur':1636 'fall':1296 'field':1227 'file':141,196,254,258,291,298,324,350,371,386,530,551,594,624,775,837,867,913,1110,1180,1184,1278,1302,1388,1414,1489,1542,1564,1572,1585,1628,1673 'filenam':89,981,997,1005 'filename-pattern-bas':980 'filesystem':1632 'final':637,1091,1098,1530,1532,1624 'find':412,1484 'finish':1343 'first':478,1081 'fix':301,307,606,1168,1293,1475,1499 'fixer':102,112,127,165,1009,1024,1042,1059,1162,1189,1248,1502 'flow':631,651 'follow':42,115,452,1257 'frontend':104,109,113,217,342,572,860,1026,1031,1035,1039,1043,1661 'frontend-task':103,216,341,571,859,1025 'fullstack':3,7,1646 'gap':440,454,1447 'gate':189 'generat':629,649,788,871,1586,1652 'git':1216,1391 'glob':647 'granular':840 'guid':27,38,79 'head':1397 'header':410 'ident':18 'identifi':941 'immedi':686 'implement':177,273,305,415,446,469,485,545,1333,1387,1413,1540,1647,1655 'includ':1080 'incompleteimplement':1198 'inconsist':1439 'independ':845 'individu':835 'instruct':137,678 'integr':309,314,609,1136 'integration-test':308,313,608 'integration-test-review':1135 'investig':1295 'invok':61,724,800,1159,1263,1354,1372 'iter':635 'json':1099 'last':378 'later':536 'layer':11,161,202,223,238,557,587,849,1046,1170,1244,1492 'layer-appropri':160,1169,1243,1491 'layer-awar':10,201,556,848 'least':347 'lexicograph':377 'line':414,499 'list':194,455,549,1389,1415 'load':1283 'locat':184 'main':1396 'mandatori':31,984 'map':1083,1095 'marker':511 'match':199,253,259,351,387,554,595,917,1230,1573 'md':211,219,229,283,288,302,312,360,403,566,574,599,601,607,612,646,722,787,828,857,863,1603,1615 'miss':500,753 'mode':132,968,1313 'monorepo-flow.md':92,1000 'most':1432 'most-recent-mtim':396 'mtime':372,399 'must':1070 'n':463,496,856,862 'name':207,215,227,329,359,381,562,570,579,786,827,851,1394,1577,1595,1602,1614 'name-on':1393 'need':1123,1139,1436,1462 'neither':709,741 'next':664,1239 'non':401,673,894,931 'non-empti':672,893,930 'non-templ':400 'note':1459 'number':1657,1668 'occur':157 'older':504 'one':348 'oper':1271 'orchestr':15,22,26,37,78,80 'order':944 'origin':265,614 'output':834,1644 'outsid':1297 'overview':287,290,600 'own':533 'parallel':1348,1357 'pars':1219 'pass':65,1108,1176,1426,1451,1519,1527,1666 'pass/fail':1420 'path':67,477,868,1111,1181,1384,1386,1411 'pattern':90,204,263,390,542,559,881,920,982,998,1006 'pend':465,472,503 'per':295,957,1105,1172,1304,1374,1582 'per-phas':294,1581 'per-task':956 'permit':73,82 'phase':269,292,296,602,618,761,1578,1583,1648 'plan':171,187,206,214,226,249,279,328,354,358,380,393,409,433,476,483,506,561,569,578,689,700,715,731,744,782,785,793,818,822,826,852,858,1576,1594,1601,1609,1613 'plan-nam':205,213,225,327,357,379,560,568,577,784,825,1575,1593,1600,1612 'plan-path':475 'planner':727 'post':304,1332 'post-implement':303,1331 'pre':174,922,1306 'pre-execut':173,921,1305 'prefix':330,363,1047 'preflight':285,490,515 'preload':1084 'prep':282,598 'prerequisit':176,754 'present':466,1468,1605 'preserv':1606 'proceed':41,423,461,494,737,1148,1154,1207,1237,1528 'process':183 'produc':912 'prompt':819,1113,1262,1281 'protocol':53 'provid':135 'qualiti':101,111,126,164,972,1008,1023,1041,1058,1161,1165,1188,1247,1501,1663 'quality-fix':100,125,163,1022,1057,1160,1187,1246,1500 'quality-fixer-frontend':110,1040 're':1504 're-run':1503 'read':32,406,430,820 'readi':178,284,416,422,435,447,470,510,546,583 'readyforqualitycheck':1152 'receiv':1114 'recent':368,398 'recip':2,244,532,627,1266,1544,1560 'recipe-fullstack-build':1 'recomput':872 'redirect':242 'refer':30,93,621,1001 'referenc':1277 'references/monorepo-flow.md':33 'regist':1072,1076 'remain':323,439,453 'remov':1674 'repeat':1516 'report':71,436,752,1352,1471,1537,1634,1643 'requir':29,661,1292,1315 'requiredfix':1146 'requirestestreview':1131 'resolut':191 'resolv':580,698 'respons':1116,1120,1190,1224 'restrict':389,541,880 'result':72,1418 'resum':487 'retain':1558 'return':1141,1193,1249 'review':300,306,605,1138,1400,1408,1437,1450,1625 'review-fix':299,604 'revis':1140,1463 'rout':14,49,85,993,1003,1106,1173 'rule':192,419,1089,1096 'run':159,239,277,473,527,705,1344,1505,1561 'scaffold':319 'scope':148,1251,1267,1275,1288,1299 'section':437,887,939 'secur':1399,1407,1449 'security-review':1398,1406,1448 'see':23,75,91 'segment':333 'serv':679 'set':427,519,524,641,656,670,693,719,748,767,780,876,886,928,938,949,992,1569 'silent':910 'singl':222,237,586,1382,1487 'single-lay':221,236,585 'skill':28,39,1085,1284 'skill-recipe-fullstack-build' 'source-shinpr' 'stale':235 'state':662,1554 'status':420,1121,1226,1428,1443,1453 'step':118,1064,1078,1143,1150,1156,1195,1209,1235,1514 'still':899 'stop':464,497,758,1126,1201 'structur':1115 'stub':1191 'sub':63,1222 'sub-ag':62,1221 'subag':25,36,77,807,974,1103,1254,1261,1270,1364,1401 'subagents-orchestration-guid':24,35,76 'subsequ':620 'summari':1328 'surfac':438 'tabl':1004,1107,1174 'target':866 'task':8,45,88,96,98,105,107,119,140,152,182,195,210,218,224,228,274,281,286,311,339,343,349,370,385,426,518,523,550,565,573,588,597,611,623,628,632,648,655,666,669,688,692,707,718,739,747,759,766,774,779,789,796,802,813,833,836,842,855,861,875,885,906,927,937,942,948,958,977,987,991,996,1012,1017,1027,1033,1044,1052,1061,1068,1073,1082,1092,1109,1179,1183,1240,1274,1301,1337,1341,1488,1495,1541,1568,1589,1627,1650,1656,1658,1672 'task-decompos':706,801,812,905,1588 'task-executor':97,1016,1051,1494 'task-executor-frontend':106,1032 'task-fil':369 'task-prep':280,596 'taskcreat':1075 'templat':402 'test':310,315,610,971,1137 'tie':373 'tool':60,74,83,806,973,1102,1360 'topic-agent-skills' 'topic-agentic-ai' 'topic-ai-agents' 'topic-automation' 'topic-claude-code' 'topic-claude-code-plugin' 'topic-code-quality' 'topic-developer-tools' 'topic-development-workflow' 'topic-llm-orchestration' 'topic-productivity' 'topic-prompt-engineering' 'treat':501 'true':1133,1153 'type':808,1104,1365,1378,1402 'unavail':964 'unifi':1469 'unrestrict':644 'use':538,639,804,847,877,1074,1282,1358 'user':134,443,675,704,756,771,904,1130,1205,1324,1467,1473,1524,1617 'verif':1334,1345,1470 'verifi':480,870,1093,1300,1363,1371,1425,1479,1509 'via':444,467 'whether':1619 'within':945,1272 'without':489 'work':57,170,186,248,353,392,408,432,482,505,699,726,730,781,792,817,821,1077,1547,1553,1608 'work-plann':725 'workflow':268,617,811,1015,1021,1030,1038,1050,1056,1368,1405 'wrong':247 'x':1660 'y':460,493,1662 'y/n':458,491,794","prices":[{"id":"4f18b554-35ae-433f-bb45-a45ce582a8bf","listingId":"41299fd3-96de-488d-b69c-2552be0dcbf2","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"shinpr","category":"claude-code-workflows","install_from":"skills.sh"},"createdAt":"2026-04-18T22:03:12.016Z"}],"sources":[{"listingId":"41299fd3-96de-488d-b69c-2552be0dcbf2","source":"github","sourceId":"shinpr/claude-code-workflows/recipe-fullstack-build","sourceUrl":"https://github.com/shinpr/claude-code-workflows/tree/main/skills/recipe-fullstack-build","isPrimary":false,"firstSeenAt":"2026-04-18T22:03:12.016Z","lastSeenAt":"2026-05-02T18:53:52.590Z"}],"details":{"listingId":"41299fd3-96de-488d-b69c-2552be0dcbf2","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"shinpr","slug":"recipe-fullstack-build","github":{"repo":"shinpr/claude-code-workflows","stars":327,"topics":["agent-skills","agentic-ai","ai-agents","automation","claude-code","claude-code-plugin","code-quality","developer-tools","development-workflow","llm-orchestration","productivity","prompt-engineering","skills"],"license":"mit","html_url":"https://github.com/shinpr/claude-code-workflows","pushed_at":"2026-05-02T15:39:17Z","description":"Production-ready development workflows for Claude Code, powered by specialized AI agents.","skill_md_sha":"6488bf2ea16a545f12943f59456364cb1f6de32b","skill_md_path":"skills/recipe-fullstack-build/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/shinpr/claude-code-workflows/tree/main/skills/recipe-fullstack-build"},"layout":"multi","source":"github","category":"claude-code-workflows","frontmatter":{"name":"recipe-fullstack-build","description":"Execute decomposed fullstack tasks with layer-aware agent routing"},"skills_sh_url":"https://skills.sh/shinpr/claude-code-workflows/recipe-fullstack-build"},"updatedAt":"2026-05-02T18:53:52.590Z"}}