rlm-orchestrator
RLM-Style Recursive Orchestrator
Implement the orchestrator pattern from RLM research to handle arbitrarily large contexts and complex multi-part tasks. The main conversation acts as the recursive coordinator, spawning depth-1 subagents and aggregating results.
Core Principle
"No single language model call should require handling a huge context." — RLM Research (arXiv:2512.24601)
Since Claude Code subagents cannot spawn children (architectural limit), the main conversation becomes the "recursion stack," enabling functional depth >1.
When to Use This Skill
More from belumume/claude-skills
ralph-loop
Activate autonomous Ralph Wiggum loop mode for iterative task completion. Use when you have a well-defined task with clear completion criteria that benefits from persistent, autonomous execution.
156rtl-document-translation
Translate structured documents (DOCX) to RTL languages (Arabic, Hebrew, Urdu) while preserving exact formatting, table structures, colors, and layouts. Handles quote normalization, multi-pass translation matching, and RTL-specific formatting patterns.
52obsidian-study-vault-builder
Build comprehensive, mobile-compatible Obsidian study vaults from academic course materials with checkpoint-based workflow, error pattern recognition, and quality assurance. Battle-tested patterns from 828KB/37-file projects. Works across all subjects - CS, medicine, business, self-study.
41docx-advanced-patterns
Advanced python-docx patterns for handling nested tables, complex cell structures, and content extraction beyond basic .text property. Complements the official docx skill with specialized techniques for forms, checklists, and complex layouts.
32document-quality-standards
Use when creating or editing documents (DOCX, PDF, XLSX, PPTX) that need professional output. Adds visual verification, typography hygiene, and formula patterns to the document-skills plugin.
29deep-brainstorming
Use when brainstorming a product or feature where multiple valid technology choices exist and the wrong one is costly, when the user asks for 'objectively best' or 'highest quality', or when the domain has tools/frameworks where marketing or popularity biases could mislead research agents. Also use when starting architecture decisions, evaluating tech stacks, or when the user mentions bias, vendor lock-in, hallucinated benchmarks, or wants research-backed decisions rather than default recommendations.
7