KS
Killer-Skills

multi-ai — how to use multi-ai how to use multi-ai, multi-ai pipeline orchestrator, multi-ai vs codex, multi-ai setup guide, what is multi-ai, multi-ai install, multi-ai alternative, multi-ai pipeline management, multi-ai for AI developers, multi-ai workflow automation

v1.0.0
GitHub

About this Skill

Ideal for AI Pipeline Agents needing efficient task management and automation capabilities. multi-ai is a pipeline orchestrator that automates tasks such as cleaning up previous tasks, capturing user requests, and creating initial plans for AI workflows

Features

Removes old .task/ directory using rm -rf command
Creates a new .task/ directory using mkdir -p command
Writes user requests to .task/user-request.txt file
Follows standards outlined in skill/multi-ai/reference/standards.md
Executes step-by-step pipeline process for AI workflow management

# Core Topics

cskwork cskwork
[0]
[0]
Updated: 3/6/2026

Quality Score

Top 5%
36
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add cskwork/llm-review/multi-ai

Agent Capability Analysis

The multi-ai MCP Server by cskwork is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use multi-ai, multi-ai pipeline orchestrator, multi-ai vs codex.

Ideal Agent Persona

Ideal for AI Pipeline Agents needing efficient task management and automation capabilities.

Core Value

Empowers agents to automate tasks such as cleaning up previous tasks and capturing user requests, streamlining AI pipeline development with standardized coding practices and review criteria, utilizing files like `.task/user-request.txt` and protocols like bash scripting.

Capabilities Granted for multi-ai MCP Server

Automating pipeline cleanup
Capturing and processing user requests
Orchestrating multi-AI pipeline workflows

! Prerequisites & Limits

  • Requires filesystem access for task directory management
  • Dependent on specific directory structure like `.task/`
  • Limited to bash-compatible environments
Project
SKILL.md
3.4 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Multi-AI Pipeline Orchestrator

You are starting the multi-AI pipeline. Follow this process exactly.

Reference Documents

First, read the standards that guide all reviews:

  • skill/multi-ai/reference/standards.md - Coding standards and review criteria

Step 1: Clean Up Previous Task

Remove old .task/ directory if it exists:

bash
1rm -rf .task 2mkdir -p .task

Step 2: Capture User Request

Write the user's request to .task/user-request.txt.

Step 3: Create Initial Plan

Write .task/plan.json:

json
1{ 2 "id": "plan-YYYYMMDD-HHMMSS", 3 "title": "Short descriptive title", 4 "description": "What the user wants to achieve", 5 "requirements": ["req1", "req2"], 6 "created_at": "ISO8601", 7 "created_by": "claude" 8}

Step 4: Refine Plan

Research the codebase and create .task/plan-refined.json:

json
1{ 2 "id": "plan-001", 3 "title": "Feature title", 4 "description": "What the user wants", 5 "requirements": ["req1", "req2"], 6 "technical_approach": "Detailed how-to", 7 "files_to_modify": ["path/to/file.ts"], 8 "files_to_create": ["path/to/new.ts"], 9 "dependencies": [], 10 "estimated_complexity": "low|medium|high", 11 "potential_challenges": ["Challenge and mitigation"], 12 "refined_by": "claude", 13 "refined_at": "ISO8601" 14}

Step 5: Sequential Plan Reviews

Run reviews in sequence. Fix issues after each before continuing:

  1. Invoke /review-sonnet

    • Read .task/review-sonnet.json result
    • If needs_changes: fix issues in plan, update .task/plan-refined.json
  2. Invoke /review-codex

    • Read .task/review-codex.json result
    • If needs_changes: fix issues and restart from step 5.1
    • If approved: continue to implementation

Step 6: Implement

Invoke /implement-sonnet

This skill will:

  • Read the approved plan from .task/plan-refined.json
  • Implement the code
  • Add tests
  • Output to .task/impl-result.json

Step 7: Sequential Code Reviews

Run reviews in sequence. Fix issues after each before continuing:

  1. Invoke /review-sonnet

    • Read .task/review-sonnet.json result
    • If needs_changes: fix code issues
  2. Invoke /review-codex

    • Read .task/review-codex.json result
    • If needs_changes: fix issues and restart from step 7.1
    • If approved: continue to completion

Step 8: Complete

Write .task/state.json:

json
1{ 2 "state": "complete", 3 "plan_id": "plan-001", 4 "completed_at": "ISO8601" 5}

Report success to the user with:

  • Summary of what was implemented
  • Files changed
  • Tests added

Important Rules

  • Follow this process exactly - no shortcuts
  • Fix ALL issues raised by reviewers before continuing
  • If codex rejects, restart the review cycle from sonnet
  • Keep the user informed of progress at each major step

State Files Reference

FilePurpose
.task/user-request.txtOriginal user request
.task/plan.jsonInitial plan
.task/plan-refined.jsonRefined plan with technical details
.task/impl-result.jsonImplementation result
.task/review-sonnet.jsonSonnet review output
.task/review-codex.jsonCodex review output
.task/state.jsonPipeline state

Reference Directory

PathPurpose
skill/multi-ai/reference/standards.mdReview criteria and coding standards
skill/multi-ai/reference/schemas/JSON schemas for structured output

Related Skills

Looking for an alternative to multi-ai or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication