skills.rest
ishandutta2007
ishandutta2007COMMUNITY
Explore all skills by this author →
Website𝕏@ishandutta2007GitHub

stream-chain

Chains sequential agent prompts into multi-step workflows with streaming context flow.

11|Updated Jan 20, 2026
Search Tags:#automation#workflow#multi-agent#streaming#pipeline#chaining#claude-flow
One-click install
npx skills add https://github.com/ishandutta2007/claude-agent-orchestration --skill stream-chain-ishandutta2007
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: stream-chain
Source: https://github.com/ishandutta2007/claude-agent-orchestration/tree/main/.claude/skills/stream-chain
Command: npx skills add https://github.com/ishandutta2007/claude-agent-orchestration --skill stream-chain-ishandutta2007

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Coordinating multi-step AI workflows manually requires copying each step's output into the next prompt, which is error-prone and breaks context. This Skill automates sequential agent pipelines where each step's output flows directly into the next step as context. ## Core Features & Use Cases - Custom Chains: Run arbitrary prompt sequences with claude-flow stream-chain run, where each step receives the full output of previous steps. - Predefined Pipelines: Execute built-in workflows for analysis, refactoring, testing, and optimization with a single command. - Configurable Pipelines: Define reusable custom pipelines in .claude-flow/config.json with per-step timeouts. - Use Case: Run a security audit chain that analyzes authentication code, categorizes vulnerabilities by severity, proposes fixes, and generates security test cases in one command. ## Quick Start Ask the agent to run a stream chain that analyzes the codebase structure, identifies improvement areas, and generates an action plan.

Frequently Asked Questions about stream-chain

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I chain multiple AI agent prompts together?▼

Use `claude-flow stream-chain run` followed by two or more quoted prompts. Each prompt becomes a step, and the output of each step is passed as context to the next step automatically.

What predefined pipelines are available in stream-chain?▼

Four built-in pipelines exist: analysis (codebase structure and issues), refactor (prioritized refactoring), test (coverage analysis and test generation), and optimize (performance profiling and improvements). Run them with `claude-flow stream-chain pipeline <type>`.

How do I create a custom reusable pipeline?▼

Define it in `.claude-flow/config.json` under the `streamChain.pipelines` key with a name, description, array of prompts, and optional timeout. Then execute it by name with `claude-flow stream-chain pipeline <name>`.

Why does my stream chain step time out?▼

Steps default to a 30-second timeout, which is too short for complex analysis or implementation tasks. Increase it with the `--timeout` flag, using 45-60 seconds for analysis and 60-120 seconds for complex workflows.

How do I debug context not flowing between chain steps?▼

Run the chain with the `--debug` flag to enable full logging of execution and context passing. This shows exactly what output each step produced and what context the next step received.

Related Skills

Explore More Software Engineering Skills→
ruvnetruvnet
70.1k

swarm-advanced

Orchestrates multi-agent swarms for research, development, testing, and analysis workflows.

Community
Advanced
weebcoder101weebcoder101
3

pieces-ltm

Persist skill chain outcomes to Long-Term Memory with structured metadata.

Community
Advanced
d-oitd-oit

agent-coordination

Coordinate multiple agents across software development workflows with parallel, sequential, swarm, and hybrid patterns.

Community
Advanced
Himanshu040604Himanshu040604

dispatching-parallel-agents

Dispatches multiple independent agents concurrently to handle distinct tasks.

Community
Intermediate