Building Agentic Systems

Category: Development & Coding | Uploader: diegouis | Downloads: 0 | Version: v1.0（Latest）

Comprehensive skill for designing, building, orchestrating, and optimizing AI agent systems with Claude Code. Covers agent design patterns, multi-agent orchestration, skill/command/hook creation, MCP server development, prompt engineering, plugin architecture, agent evaluation, context engineering, autonomous coding loops, multi-backend orchestration, trust/autonomy frameworks, spec-driven development, thinking model commands, and the Workflow Factory for template-driven artifact creation with complexity assessment and inter-artifact contracts.

Changelog: Source: GitHub https://github.com/diegouis/provectus-marketplace

Directory Structure

Current level: plugins/proagent-agentic-engineering/skills/agentic-engineering-assistant/

📁 references/
- 📄 artifacts.md 11.5 KB
- 📄 complexity.md 1.8 KB
- 📄 component-architecture.md 13.6 KB
- 📄 contracts.md 1.9 KB
- 📄 error-handling.md 2.1 KB
- 📄 external-frameworks.md 3.9 KB
- 📄 naming-conventions.md 1.8 KB
- 📄 orchestration-patterns.md 10.6 KB
- 📄 prompt-engineering.md 2.2 KB
- 📄 quality-checklists.md 6.4 KB
- 📄 report-types.md 4.2 KB
- 📄 workflow-patterns.md 6.0 KB
📁 templates/
- 📄 agent-body.md 1.2 KB
- 📄 command-body.md 1.2 KB
- 📄 creation-report.md 1.1 KB
- 📄 design-decisions.md 1.2 KB
- 📄 expert-build.md 776 B
- 📄 expert-improve.md 847 B
- 📄 expert-plan.md 831 B
- 📄 hook-body.py 1.7 KB
- 📄 hook-settings.json 371 B
- 📄 skill-body.md 1.0 KB
📄 SKILL.md 4.6 KB

SKILL.md

---
name: Building Agentic Systems
description: >
  Comprehensive skill for designing, building, orchestrating, and optimizing AI agent systems
  with Claude Code. Covers agent design patterns, multi-agent orchestration, skill/command/hook
  creation, MCP server development, prompt engineering, plugin architecture, agent evaluation,
  context engineering, autonomous coding loops, multi-backend orchestration, trust/autonomy
  frameworks, spec-driven development, thinking model commands, and the Workflow Factory for
  template-driven artifact creation with complexity assessment and inter-artifact contracts.

  This skill should be used when the user mentions:
  - Creating agents, skills, commands, hooks, or plugins for Claude Code
  - Multi-agent orchestration, parallel agents, subagent workflows
  - MCP server development or integration
  - Prompt engineering, context engineering, or prompt-driven development
  - Agent evaluation, testing agent systems, or agent quality assurance
  - Claude Code extensions, customization, or configuration
  - Agentic development workflows (ADW), trust ladder, progressive autonomy
  - Subagent-driven development (SDD), dispatching parallel agents
  - File-based planning with hooks, plan execution with agents
  - Autonomous coding loops (ralph, casdk-harness, Auto-Claude, gastown)
  - Multi-backend adapters (Claude, Kiro, Gemini, Codex)
  - Spec-driven development (AWOS spec/implement/verify, ProAgent SDLC pipeline)
  - Tool registry, plugin lifecycle, knowledge graph integration
  - Thinking models, first-principles reasoning, mental model commands
  - 3-file planning pattern, context handoff, session persistence
  - Workflow factory, create workflow, generate artifacts
  - Complexity assessment (simple, medium, complex)
  - Design decisions, mandatory design gates
  - Expert system trio (plan, build, improve), self-improving workflows
  - Inter-artifact contracts, producer-consumer data passing
  - Report types (summary, diff, handoff, progress, audit, path-only)
  - Error handling patterns (gate guard, step fallback, graceful degradation)
  - Naming conventions, artifact templates, coherence validation

  Do NOT use for:
  - General software development without an agentic component (use sdlc or backend/frontend skills)
  - DevOps infrastructure without agent involvement (use devops skills)
  - Pure testing without agent evaluation (use qa skills)
allowed-tools: Read, Write, Edit, Grep, Glob, Bash, WebFetch, WebSearch
---

# Building Agentic Systems

Comprehensive skill for building, orchestrating, and optimizing AI agent systems using Claude Code.

## Overview

This skill covers the full lifecycle of agentic engineering: from designing individual agents to orchestrating complex multi-agent workflows, building MCP servers, creating plugins, and evaluating agent systems.

## Reference Routing

> **CONTEXT GUARD**: Load reference files only when the user's request matches a specific topic below. Do NOT load all references upfront.

| User Intent | Reference File |
|---|---|
| Creating agents, skills, commands, hooks, plugins, or MCP servers | `references/component-architecture.md` |
| Multi-agent orchestration, autonomous coding loops, context engineering, agent teams, spec-driven dev | `references/orchestration-patterns.md` |
| Prompt engineering, context engineering, trust ladder, agent evaluation, thinking models | `references/prompt-engineering.md` |
| Step-by-step workflows for creating agents, skills, commands, hooks, plugins, MCP servers | `references/workflow-patterns.md` |
| Quality checklists, AWOS architecture, confirmation patterns, Composio SDK, decision matrix | `references/quality-checklists.md` |
| Artifact frontmatter schemas, expert systems, agent teams, headless automation | `references/artifacts.md` |
| Complexity assessment (Simple/Medium/Complex) for artifact depth | `references/complexity.md` |
| Inter-artifact contracts, producer-consumer data passing | `references/contracts.md` |
| Error handling patterns (Gate Guard, Step Fallback, Graceful Degradation, Pipeline Abort, Retry) | `references/error-handling.md` |
| Report type selection (Summary, YAML, Diff, Progress, Handoff, Comparison, Audit, Path-Only) | `references/report-types.md` |
| File naming, variable naming, placement rules | `references/naming-conventions.md` |
| Body templates for commands, skills, agents, hooks, expert systems | `templates/` directory |

## Visual Diagramming with Excalidraw

Use the Excalidraw MCP server to generate agent orchestration flows, MCP server architecture diagrams, plugin component maps, and fan-out/fan-in pattern visualizations. Describe what you need in natural language.

Comments 0

Latest | Hot

Please login before commenting.

No comments yet. Be the first one!

Building Agentic Systems

Directory Structure

SKILL.md

Report

Notice