Coordinate streaming multi-step workflows with sequential context propagation.
npx skills add https://github.com/ruvnet/claude-flow --skill stream-chain-ruvnet
Please help me install this Agent Skill. Skill: stream-chain Source: https://github.com/ruvnet/claude-flow/tree/main/.claude/skills/stream-chain Command: npx skills add https://github.com/ruvnet/claude-flow --skill stream-chain-ruvnet
This Skill streamlines the orchestration of complex, multi-step AI agent workflows where the output of one agent seamlessly feeds into the next. It eliminates manual hand-offs and ensures a smooth, automated data flow for sophisticated tasks, saving significant time and reducing errors.
refactor pipeline to automatically identify code smells, create a refactoring plan, apply changes to high-priority items, and verify behavior, all in a single, automated sequence.claude-flow stream-chain run
"Analyze codebase structure"
"Identify improvement areas"
"Generate action plan"
claude-flow stream-chain pipeline analysis
High-intent search queries and answers about installing and using this skill.
Multi-step workflow automation links sequential agent outputs as inputs to downstream steps. stream-chain coordinates this through two modes: custom chains (define your own prompt sequence) and predefined pipelines (use optimized workflows for analysis, refactoring, testing). Context from each step flows automatically to the next, eliminating manual hand-offs.
Yes. stream-chain orchestrates multi-agent workflows for data transformation, code analysis, security auditing, and other sequential processing tasks. It enforces streaming data flow with context propagation across steps, making it suitable for complex analysis pipelines where intermediate results guide downstream decisions.
Use stream-chain's predefined `refactor` pipeline to chain multiple analysis and transformation steps: identify code smells, generate a refactoring plan, apply changes to high-priority items, and verify behavior—all in one automated sequence without manual intervention between steps.
Context preservation ensures complete output from each step flows as rich context to the next step, maintaining continuity across the workflow. This eliminates information loss and lets downstream steps leverage full prior results for better decision-making.
Yes. Custom chains let you define unique prompt sequences for flexible workflows; predefined pipelines provide battle-tested sequences optimized for common development tasks like analysis and refactoring, reducing setup time.
stream-chain provides configurable CLI options including --verbose for detailed output, --timeout for execution limits, and --debug for troubleshooting, plus per-step progress tracking, timing metrics, and summaries to monitor workflow health.
pradyumnasagarAutomate inter-skill data transfer and provenance capture via JSON Material Passports.
NaveedTechLabSets up a WebSocket-based notification system with Socket.io, PostgreSQL, and React.
aegnticOrchestrate the software development lifecycle with SPARC methodology and multi-agent coordination.
NourcineAbOrchestrate sequential AI workflows by chaining prompts and transforming outputs across processing steps.