Connect agent tasks into a sequence where each step receives the previous output. Use custom prompts or predefined workflows to analyze code, plan refactoring, generate tests, optimize performance, or transform data through multiple stages.
中文简介正在准备中。当前显示英语简介。
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows
安装前可以查看交给 AI 代理的指令内容。
Execute sophisticated multi-step workflows where each agent's output flows into the next, enabling complex data transformations and sequential processing pipelines.
Stream-Chain provides two powerful modes for orchestrating multi-agent workflows:
run): Execute custom prompt sequences with full controlpipeline): Use battle-tested workflows for common tasksEach step in a chain receives the complete output from the previous step, enabling sophisticated multi-agent coordination through streaming data flow.
claude-flow stream-chain run \
"Analyze codebase structure" \
"Identify improvement areas" \
"Generate action plan"
claude-flow stream-chain pipeline analysis
run)Execute custom stream chains with your own prompts for maximum flexibility.
claude-flow stream-chain run <prompt1> <prompt2> [...] [options]
Requirements:
| Option | Description | Default |
|---|---|---|
--verbose | Show detailed execution information | false |
--timeout <seconds> | Timeout per step | 30 |
--debug | Enable debug mode with full logging | false |
Each step receives the previous output as context:
Step 1: "Write a sorting function"
Output: [function implementation]
Step 2 receives:
"Previous step output:
[function implementation]
Next task: Add comprehensive tests"
Step 3 receives:
"Previous steps output:
[function + tests]
Next task: Optimize performance"
claude-flow stream-chain run \
"Write a user authentication function" \
"Add input validation and error handling" \
"Create unit tests with edge cases"
claude-flow stream-chain run \
"Analyze authentication system for vulnerabilities" \
"Identify and categorize security issues by severity" \
"Propose fixes with implementation priority" \
"Generate security test cases" \
--timeout 45 \
--verbose
claude-flow stream-chain run \
"Identify code smells in src/ directory" \
"Create refactoring plan with specific changes" \
"Apply refactoring to top 3 priority items" \
"Verify refactored code maintains behavior" \
--debug
claude-flow stream-chain run \
"Extract data from API responses" \
"Transform data into normalized format" \
"Validate data against schema" \
"Generate data quality report"
pipeline)Execute battle-tested workflows optimized for common development tasks.
claude-flow stream-chain pipeline <type> [options]
Comprehensive codebase analysis and improvement identification.
claude-flow stream-chain pipeline analysis
Workflow Steps:
Use Cases:
Systematic code refactoring with prioritization.
claude-flow stream-chain pipeline refactor
Workflow Steps:
Use Cases:
Comprehensive test generation with coverage analysis.
claude-flow stream-chain pipeline test
Workflow Steps:
Use Cases:
Performance optimization with profiling and implementation.
claude-flow stream-chain pipeline optimize
Workflow Steps:
Use Cases:
| Option | Description | Default |
|---|---|---|
--verbose | Show detailed execution | false |
--timeout <seconds> | Timeout per step | 30 |
--debug | Enable debug mode | false |
claude-flow stream-chain pipeline analysis
claude-flow stream-chain pipeline refactor --timeout 60 --verbose
claude-flow stream-chain pipeline test --debug
claude-flow stream-chain pipeline optimize --timeout 90 --verbose
Each pipeline execution provides:
Define reusable pipelines in .claude-flow/config.json:
{
"streamChain": {
"pipelines": {
"security": {
"name": "Security Audit Pipeline",
"description": "Comprehensive security analysis",
"prompts": [
"Scan codebase for security vulnerabilities",
"Categorize issues by severity (critical/high/medium/low)",
"Generate fixes with priority and implementation steps",
"Create security test suite"
],
"timeout": 45
},
"documentation": {
"name": "Documentation Generation Pipeline",
"prompts": [
"Analyze code structure and identify undocumented areas",
"Generate API documentation with examples",
"Create usage guides and tutorials",
"Build architecture diagrams and flow charts"
]
}
}
}
}
claude-flow stream-chain pipeline security
claude-flow stream-chain pipeline documentation
Chain different agent types for complex workflows:
claude-flow stream-chain run \
"Research best practices for API design" \
"Design REST API with discovered patterns" \
"Implement API endpoints with validation" \
"Generate OpenAPI specification" \
"Create integration tests" \
"Write deployment documentation"
Process and transform data through multiple stages:
claude-flow stream-chain run \
"Extract user data from CSV files" \
"Normalize and validate data format" \
"Enrich data with external API calls" \
"Generate analytics report" \
"Create visualization code"
Systematic code migration with validation:
claude-flow stream-chain run \
"Analyze legacy codebase dependencies" \
"Create migration plan with risk assessment" \
"Generate modernized code for high-priority modules" \
"Create migration tests" \
"Document migration steps and rollback procedures"
Comprehensive code quality workflow:
claude-flow stream-chain pipeline analysis
claude-flow stream-chain pipeline refactor
claude-flow stream-chain pipeline test
claude-flow stream-chain pipeline optimize
Good:
"Analyze authentication.js for SQL injection vulnerabilities"
Avoid:
"Check security"
Order prompts to build on previous outputs:
1. "Identify the problem"
2. "Analyze root causes"
3. "Design solution"
4. "Implement solution"
5. "Verify implementation"
Include validation in your chains:
claude-flow stream-chain run \
"Implement feature X" \
"Write tests for feature X" \
"Verify tests pass and cover edge cases"
Use chains for iterative improvement:
claude-flow stream-chain run \
"Generate initial implementation" \
"Review and identify issues" \
"Refine based on issues found" \
"Final quality check"
# Initialize swarm for coordination
claude-flow swarm init --topology mesh
# Execute stream chain with swarm agents
claude-flow stream-chain run \
"Agent 1: Research task" \
"Agent 2: Implement solution" \
"Agent 3: Test implementation" \
"Agent 4: Review and refine"
Stream chains automatically store context in memory for cross-session persistence:
# Execute chain with memory
claude-flow stream-chain run \
"Analyze requirements" \
"Design architecture" \
--verbose
# Results stored in .claude-flow/memory/stream-chain/
Successful chains train neural patterns for improved performance:
# Enable neural training
claude-flow stream-chain pipeline optimize --debug
# Patterns learned and stored for future optimizations
If steps timeout, increase timeout value:
claude-flow stream-chain run "complex task" --timeout 120
If context not flowing properly, use --debug:
claude-flow stream-chain run "step 1" "step 2" --debug
Verify pipeline name and custom definitions:
# Check available pipelines
cat .claude-flow/config.json | grep -A 10 "streamChain"
# Full feature development chain
claude-flow stream-chain run \
"Analyze requirements for user profile feature" \
"Design database schema and API endpoints" \
"Implement backend with validation" \
"Create frontend components" \
"Write comprehensive tests" \
"Generate API documentation" \
--timeout 60 \
--verbose
# Automated code review workflow
claude-flow stream-chain run \
"Analyze recent git changes" \
"Identify code quality issues" \
"Check for security vulnerabilities" \
"Verify test coverage" \
"Generate code review report with recommendations"
# Framework migration helper
claude-flow stream-chain run \
"Analyze current Vue 2 codebase" \
"Identify Vue 3 breaking changes" \
"Create migration checklist" \
"Generate migration scripts" \
"Provide updated code examples"
Stream-Chain enables sophisticated multi-step workflows by:
Use run for custom workflows and pipeline for battle-tested solutions.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Build advanced AgentDB workflows with database synchronization, multiple databases, and search that combines meaning with attribute filters. Covers similarity measures, diverse search results, and operational patterns for distributed AI applications.
中文简介正在准备中。当前显示英语简介。
Create AgentDB learning plugins that use recorded experience to improve agent decisions. Choose a learning method, store states, actions, and rewards, train models, and evaluate suggested actions through CLI and API workflows.
中文简介正在准备中。当前显示英语简介。
Build AI agents that retain conversation history, user preferences, and useful interaction patterns with AgentDB. The skill covers persistent storage, meaning memories survive between sessions, plus retrieval, context management, and ReasoningBank integration.
中文简介正在准备中。当前显示英语简介。
Tune AgentDB memory use and search speed through quantization, which stores vectors more compactly, search indexes, caching, and batch operations. Includes configuration examples and benchmarks to help balance accuracy, speed, and storage as datasets grow.
中文简介正在准备中。当前显示英语简介。
Build document search with AgentDB that finds related content by meaning. Store documents as numerical representations, combine similarity search with metadata filters, and retrieve relevant passages for systems that generate answers using source material.
中文简介正在准备中。当前显示英语简介。
Automate browser tasks with agent-browser, using snapshots that label page elements for the agent. Handle login flows, fill and submit forms, extract page information, and capture screenshots through a repeatable navigation and interaction workflow.
中文简介正在准备中。当前显示英语简介。