A fusion-style multi-agent research skill for Claude Code: spawn multiple sub-agents in parallel, then synthesize results with a judge while preserving minority and 'I don't know' votes.
Sansheng is a multi-agent research skill designed for Claude Code that implements a fusion-style approach inspired by OpenRouter's Fusion methodology. It enables an AI agent to spawn multiple sub-agents in parallel, each performing independent research or reasoning on a given problem. After the sub-agents finish, a 'Judge' agent synthesizes their outputs, with special attention given to preserving minority opinions and 'I don't know' votes—ensuring nuanced results that avoid premature consensus. The skill leverages Claude Code's native agent tools to orchestrate this workflow, making it highly compatible with the platform while offering developers a robust framework for exploring diverse perspectives in AI-assisted research tasks.
npx skills add DQT-bit/claude-skill-sanshengInstalled? Explore more Research & Data Analysis skills: affaan-m/uspto-database, affaan-m/scholar-evaluation, affaan-m/literature-review · View all 6 →
Fusion-style multi-agent research skill for Claude Code: spawn N sub-agents in parallel, then Judge + synthesize while preserving the minority I-don't-know vote. Implements the OpenRouter Fusion approach using native Agent tools.
USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.
Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.
Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Agent skill repository discovered by 10x-chat research.
Review backend code for quality, security, maintainability, and best practices based on established checklist rules. Use when the user requests a review, analysis, or improvement of backend files (e.g., `.py`) under the `api/` directory. Do NOT use for frontend files (e.g., `.tsx`, `.ts`, `.js`). Supports pending-change review, code snippets review, and file-focused review.