skills.rest
optimaxin
optimaxinCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

stream-chain

Chains sequential agent prompts so each step's output feeds the next workflow stage.

Updated Jul 16, 2026
Search Tags:#automation#workflow#code analysis#multi-agent#pipeline#claude-flow#stream-chain
One-click install
npx skills add https://github.com/optimaxin/Tredev_Gems --skill stream-chain-optimaxin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: stream-chain
Source: https://github.com/optimaxin/Tredev_Gems/tree/main/.claude/skills/stream-chain
Command: npx skills add https://github.com/optimaxin/Tredev_Gems --skill stream-chain-optimaxin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Multi-step development tasks like analysis, refactoring, and testing require manually passing context between separate agent runs, which loses information and breaks workflow continuity. ## Core Features & Use Cases - Custom Chains: Run sequences of prompts 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 a JSON config file with custom prompts and timeouts. - Use Case: Run a security audit chain that scans for vulnerabilities, categorizes issues by severity, proposes fixes, and generates security test cases in one continuous flow. ## Quick Start Run a stream chain that analyzes my 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 sequential agent workflow?▼

Use the stream-chain run command with two or more prompts as arguments. Each prompt becomes a step, and the complete output of each step is passed as context to the next step in the chain.

What predefined pipelines are available in stream-chain?▼

Four pipelines are built in: analysis for codebase review, refactor for prioritized code improvements, test for coverage analysis and test generation, and optimize for performance profiling and optimization.

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 the pipeline command.

Why does a stream chain step time out?▼

Steps default to a 30-second timeout, which complex analysis or implementation tasks can exceed. 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. The --verbose flag also shows detailed per-step execution information and timing.

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
DammianMillerDammianMiller
1

memory-management

Manage a 4-layer memory system using SQLite and Qdrant for AI coding agents.

Community
Advanced
wedosoftwedosoft

Hooks Automation

Automate Claude Code operations with pre/post hooks and MCP integration.

Official
Advanced
wedosoftwedosoft

Swarm Orchestration

Orchestrate multi-agent swarms with dynamic topologies and fault tolerance.

Official
Advanced