skills.rest
wandreandrade2018-maker
wandreandrade2018-makerCOMMUNITY
Explore all skills by this author →
GitHub

stream-chain

Chains sequential prompts so each step's output feeds the next in multi-agent workflows.

Updated Aug 18, 2026
Search Tags:#code analysis#workflow automation#multi-agent#pipeline#prompt chaining#claude-flow#stream-chain
One-click install
npx skills add https://github.com/wandreandrade2018-maker/claude-config --skill stream-chain-wandreandrade2018-maker
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: stream-chain
Source: https://github.com/wandreandrade2018-maker/claude-config/tree/main/.claude/skills/stream-chain
Command: npx skills add https://github.com/wandreandrade2018-maker/claude-config --skill stream-chain-wandreandrade2018-maker

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Coordinating multi-step AI workflows manually means copying outputs between prompts and losing context at each stage. This Skill automates sequential prompt chaining so each step's full output flows into the next, enabling complex data transformations and multi-agent pipelines without manual handoffs. ## Core Features & Use Cases - Custom Chains: Run arbitrary prompt sequences with claude-flow stream-chain run, where each step receives the complete output of the previous step as context. - Predefined Pipelines: Execute built-in workflows for analysis, refactoring, testing, and optimization with a single command. - Custom Pipeline Definitions: Define reusable named pipelines in .claude-flow/config.json with configurable 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 AI 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 prompts in a claude-flow workflow?▼

Use `claude-flow stream-chain run` followed by at least two quoted prompts. Each step receives the complete output of the previous step as context, so order prompts to build logically on earlier results.

What predefined pipelines are available in stream-chain?▼

Four built-in pipelines exist: analysis, refactor, test, and optimize. Run them with `claude-flow stream-chain pipeline <type>`, optionally adding --timeout, --verbose, or --debug flags.

How do I create a custom reusable pipeline?▼

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

Why does my stream chain step time out?▼

Steps default to a 30-second timeout, which is too short for analysis or implementation tasks. Increase it with `--timeout 60` or higher, and use `--debug` to inspect where context flow fails.

What are the limitations of stream-chain pipelines?▼

Chains require at least two prompts and process steps sequentially at roughly 2-5 steps per minute. Context is limited to about 100K tokens per step, so very large outputs may be truncated between steps.

Related Skills

Explore More Software Engineering Skills→
summarybotngsummarybotng
2

stream-chain

Execute sequential multi-agent workflows through custom prompt chaining and predefined pipelines.

Official
Advanced
zapierzapier
373

Git Commit

Generate Conventional Commits with Jira context and push changes.

Official
Advanced
BURHANDEV-ENTERPRISEBURHANDEV-ENTERPRISE

Hooks Automation

Coordinate Claude Code operations with lifecycle hooks and MCP tools.

Official
Advanced
bjconlanbjconlan

dispatching-parallel-agents

Dispatch separate agents to investigate independent problems in parallel.

Community
Intermediate