{"id":"62227cda-0f49-4623-81f6-ce697f0413a3","shortId":"aPse6U","kind":"skill","title":"orchestrate-batch-refactor","tagline":"Plan and execute large refactors with dependency-aware work packets and parallel analysis.","description":"# Orchestrate Batch Refactor\n\n## Overview\n\nUse this skill to run high-throughput refactors safely.\nAnalyze scope in parallel, synthesize a single plan, then execute independent work packets with sub-agents.\n\n## When to Use\n- When a refactor spans many files or subsystems and needs clear work partitioning.\n- When you need dependency-aware planning before parallel implementation.\n\n## Inputs\n\n- Repo path and target scope (paths, modules, or feature area)\n- Goal type: refactor, rewrite, or hybrid\n- Constraints: behavior parity, API stability, deadlines, test requirements\n\n## When to Use Parallelization\n\n- Use this skill for medium/large scope touching many files or subsystems.\n- Skip multi-agent execution for tiny edits or highly coupled single-file work.\n\n## Core Workflow\n\n1. Define scope and success criteria.\n   - List target paths/modules and non-goals.\n   - State behavior constraints (for example: preserve external behavior).\n2. Run parallel analysis first.\n   - Split target scope into analysis lanes.\n   - Spawn `explorer` sub-agents in parallel to analyze each lane.\n   - Ask each agent for: intent map, coupling risks, candidate work packets, required validations.\n3. Build one dependency-aware plan.\n   - Merge explorer output into a single work graph.\n   - Create work packets with clear file ownership and validation commands.\n   - Sequence packets by dependency level; run only independent packets in parallel.\n4. Execute with worker agents.\n   - Spawn one `worker` per independent packet.\n   - Assign explicit ownership (files/responsibility).\n   - Instruct every worker that they are not alone in the codebase and must ignore unrelated edits.\n5. Integrate and verify.\n   - Review packet outputs, resolve overlaps, and run validation gates.\n   - Run targeted tests per packet, then broader suite for integrated scope.\n6. Report and close.\n   - Summarize packet outcomes, key refactors, conflicts resolved, and residual risks.\n\n## Work Packet Rules\n\n- One owner per file per execution wave.\n- No parallel edits on overlapping file sets.\n- Keep packet goals narrow and measurable.\n- Include explicit done criteria and required checks.\n- Prefer behavior-preserving refactors unless user explicitly requests behavior change.\n\n## Planning Contract\n\nEvery packet must include:\n\n1. Packet ID and objective.\n2. Owned files.\n3. Dependencies (none or packet IDs).\n4. Risks and invariants to preserve.\n5. Required checks.\n6. Integration notes for main thread.\n\nUse [`references/work-packet-template.md`](references/work-packet-template.md) for the exact shape.\n\n## Agent Prompting Contract\n\n- Use the prompt templates in [`references/agent-prompt-templates.md`](references/agent-prompt-templates.md).\n- Explorer prompts focus on analysis and decomposition.\n- Worker prompts focus on implementation and validation with strict ownership boundaries.\n\n## Safety Guardrails\n\n- Do not start worker execution before plan synthesis is complete.\n- Do not parallelize across unresolved dependencies.\n- Do not claim completion if any required packet check fails.\n- Stop and re-plan when packet boundaries cause repeated merge conflicts.\n\n## Validation Strategy\n\nRun in this order:\n\n1. Packet-level checks (fast and scoped).\n2. Cross-packet integration checks.\n3. Full project safety checks when scope is broad.\n\nPrefer fast feedback loops, but never skip required behavior checks.\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":["orchestrate","batch","refactor","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding"],"capabilities":["skill","source-sickn33","skill-orchestrate-batch-refactor","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/orchestrate-batch-refactor","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 · 34616 github stars · SKILL.md body (3,700 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":"2026-04-23T00:51:21.791Z","embedding":null,"createdAt":"2026-04-18T21:42:04.611Z","updatedAt":"2026-04-23T00:51:21.791Z","lastSeenAt":"2026-04-23T00:51:21.791Z","tsv":"'1':133,341,451 '2':154,346,459 '3':189,349,465 '4':225,355 '5':256,361 '6':280,364 'across':420 'agent':49,119,169,178,229,377 'alon':247 'analysi':18,157,163,391 'analyz':33,173 'api':96 'area':86 'ask':176,517 'assign':236 'awar':13,71,194 'batch':3,20 'behavior':94,147,153,326,333,482 'behavior-preserv':325 'boundari':404,440,525 'broad':473 'broader':275 'build':190 'candid':184 'caus':441 'chang':334 'check':323,363,431,455,464,469,483 'claim':425 'clarif':519 'clear':63,208,492 'close':283 'codebas':250 'command':213 'complet':416,426 'conflict':289,444 'constraint':93,148 'contract':336,379 'core':131 'coupl':126,182 'creat':204 'criteria':138,320,528 'cross':461 'cross-packet':460 'deadlin':98 'decomposit':393 'defin':134 'depend':12,70,193,217,350,422 'dependency-awar':11,69,192 'describ':496 'done':319 'edit':123,255,306 'environ':508 'environment-specif':507 'everi':241,337 'exact':375 'exampl':150 'execut':7,42,120,226,302,411 'expert':513 'explicit':237,318,331 'explor':166,197,387 'extern':152 'fail':432 'fast':456,475 'featur':85 'feedback':476 'file':58,113,129,209,300,309,348 'files/responsibility':239 'first':158 'focus':389,396 'full':466 'gate':268 'goal':87,145,313 'graph':203 'guardrail':406 'high':29,125 'high-throughput':28 'hybrid':92 'id':343,354 'ignor':253 'implement':75,398 'includ':317,340 'independ':43,221,234 'input':76,522 'instruct':240 'integr':257,278,365,463 'intent':180 'invari':358 'keep':311 'key':287 'lane':164,175 'larg':8 'level':218,454 'limit':484 'list':139 'loop':477 'main':368 'mani':57,112 'map':181 'match':493 'measur':316 'medium/large':109 'merg':196,443 'miss':530 'modul':83 'multi':118 'multi-ag':117 'must':252,339 'narrow':314 'need':62,68 'never':479 'non':144 'non-goal':143 'none':351 'note':366 'object':345 'one':191,231,297 'orchestr':2,19 'orchestrate-batch-refactor':1 'order':450 'outcom':286 'output':198,262,502 'overlap':264,308 'overview':22 'own':347 'owner':298 'ownership':210,238,403 'packet':15,45,186,206,215,222,235,261,273,285,295,312,338,342,353,430,439,453,462 'packet-level':452 'parallel':17,36,74,104,156,171,224,305,419 'pariti':95 'partit':65 'path':78,82 'paths/modules':141 'per':233,272,299,301 'permiss':523 'plan':5,40,72,195,335,413,437 'prefer':324,474 'preserv':151,327,360 'project':467 'prompt':378,382,388,395 're':436 're-plan':435 'refactor':4,9,21,31,55,89,288,328 'references/agent-prompt-templates.md':385,386 'references/work-packet-template.md':371,372 'repeat':442 'repo':77 'report':281 'request':332 'requir':100,187,322,362,429,481,521 'residu':292 'resolv':263,290 'review':260,514 'rewrit':90 'risk':183,293,356 'rule':296 'run':27,155,219,266,269,447 'safe':32 'safeti':405,468,524 'scope':34,81,110,135,161,279,458,471,495 'sequenc':214 'set':310 'shape':376 'singl':39,128,201 'single-fil':127 'skill':25,107,487 'skill-orchestrate-batch-refactor' 'skip':116,480 'source-sickn33' 'span':56 'spawn':165,230 'specif':509 'split':159 'stabil':97 'start':409 'state':146 'stop':433,515 'strategi':446 'strict':402 'sub':48,168 'sub-ag':47,167 'substitut':505 'subsystem':60,115 'success':137,527 'suit':276 'summar':284 'synthes':37 'synthesi':414 'target':80,140,160,270 'task':491 'templat':383 'test':99,271,511 'thread':369 'throughput':30 'tini':122 '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' 'touch':111 'treat':500 'type':88 'unless':329 'unrel':254 'unresolv':421 'use':23,52,103,105,370,380,485 'user':330 'valid':188,212,267,400,445,510 'verifi':259 'wave':303 'work':14,44,64,130,185,202,205,294 'worker':228,232,242,394,410 'workflow':132","prices":[{"id":"211df6ed-9efb-423c-887b-de094b70afaa","listingId":"62227cda-0f49-4623-81f6-ce697f0413a3","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":"2026-04-18T21:42:04.611Z"}],"sources":[{"listingId":"62227cda-0f49-4623-81f6-ce697f0413a3","source":"github","sourceId":"sickn33/antigravity-awesome-skills/orchestrate-batch-refactor","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/orchestrate-batch-refactor","isPrimary":false,"firstSeenAt":"2026-04-18T21:42:04.611Z","lastSeenAt":"2026-04-23T00:51:21.791Z"}],"details":{"listingId":"62227cda-0f49-4623-81f6-ce697f0413a3","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"orchestrate-batch-refactor","github":{"repo":"sickn33/antigravity-awesome-skills","stars":34616,"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":"2026-04-22T06:40:00Z","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":"dc973b8ae295f56169516c82411a72a8286cc4c0","skill_md_path":"skills/orchestrate-batch-refactor/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/orchestrate-batch-refactor"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"orchestrate-batch-refactor","description":"Plan and execute large refactors with dependency-aware work packets and parallel analysis."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/orchestrate-batch-refactor"},"updatedAt":"2026-04-23T00:51:21.791Z"}}