# sathvikar01/agent-engineering-skills architecture

> Architecture diagram of the GitHub repository sathvikar01/agent-engineering-skills, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-06). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sathvikar01/agent-engineering-skills
- Repository: https://github.com/sathvikar01/agent-engineering-skills

## Overview

Agent Engineering Skills is a framework-agnostic collection of 19 reusable `SKILL.md` guides for designing, building, evaluating, and operating AI agents. The user-to-result workflow is to identify the engineering problem, select the relevant skill, and use its guidance; the README emphasizes loading only the skill that fits. Skills span architecture and workflow, contracts, authority and safety, data, and operations and quality. The README documents these capabilities, but source excerpts are limited to the repository validator, so the graph shows skill guidance rather than internal execution or companion-skill call relationships.

Main entry points: [`agent-architecture/SKILL.md`](https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-architecture/SKILL.md) (Agent Architecture), [`agent-development-workflow/SKILL.md`](https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-development-workflow/SKILL.md) (Development Workflow), [`agent-orchestration/SKILL.md`](https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-orchestration/SKILL.md) (Agent Orchestration), [`tool-design/SKILL.md`](https://github.com/sathvikar01/agent-engineering-skills/blob/main/tool-design/SKILL.md) (Tool Design)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_design["Design"]
  node_architecture["Agent Architecture<br/>[SKILL.md]"]
  node_workflow["Development Workflow<br/>[SKILL.md]"]
  node_orchestration["Agent Orchestration<br/>[SKILL.md]"]
end

subgraph group_contracts["Contracts"]
  node_tool_design["Tool Design<br/>[SKILL.md]"]
  node_structured_output["Structured Output<br/>[SKILL.md]"]
  node_prompt["Prompt Engineering<br/>[SKILL.md]"]
end

subgraph group_safety["Authority &amp; Safety"]
  node_authority["Deterministic Authority<br/>[SKILL.md]"]
  node_human_loop["Human Review<br/>[SKILL.md]"]
  node_guardrails["Agent Guardrails<br/>[SKILL.md]"]
  node_security["Agent Security<br/>[SKILL.md]"]
end

subgraph group_data["Data"]
  node_rag["RAG Engineering<br/>[SKILL.md]"]
  node_provenance["Evidence Provenance<br/>[SKILL.md]"]
  node_state["State &amp; Memory<br/>[SKILL.md]"]
end

subgraph group_quality["Operations &amp; Quality"]
  node_recovery["Failure Recovery<br/>[SKILL.md]"]
  node_observability["Agent Observability<br/>[SKILL.md]"]
  node_cost["Cost &amp; Latency<br/>[SKILL.md]"]
  node_agent_evals["Agent Evaluations<br/>[SKILL.md]"]
  node_testing["Agent Testing<br/>[SKILL.md]"]
  node_tool_evals["Tool Evaluations<br/>[SKILL.md]"]
end

node_engineer(("Agent Builder"))

node_engineer -->|"consults for design"| node_architecture
node_engineer -->|"consults for lifecycle"| node_workflow
node_engineer -->|"consults for routing"| node_orchestration
node_engineer -->|"consults for tools"| node_tool_design
node_engineer -->|"consults for output"| node_structured_output
node_engineer -->|"consults for prompts"| node_prompt
node_engineer -->|"consults for authority"| node_authority
node_engineer -->|"consults for approval"| node_human_loop
node_engineer -->|"consults for controls"| node_guardrails
node_engineer -->|"consults for threats"| node_security
node_engineer -->|"consults for retrieval"| node_rag
node_engineer -->|"consults for lineage"| node_provenance
node_engineer -->|"consults for memory"| node_state
node_engineer -->|"consults for recovery"| node_recovery
node_engineer -->|"consults for operations"| node_observability
node_engineer -->|"consults for optimization"| node_cost
node_engineer -->|"consults for quality"| node_agent_evals
node_engineer -->|"consults for testing"| node_testing
node_engineer -->|"consults for tool quality"| node_tool_evals

click node_architecture "https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-architecture/SKILL.md"
click node_workflow "https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-development-workflow/SKILL.md"
click node_orchestration "https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-orchestration/SKILL.md"
click node_tool_design "https://github.com/sathvikar01/agent-engineering-skills/blob/main/tool-design/SKILL.md"
click node_structured_output "https://github.com/sathvikar01/agent-engineering-skills/blob/main/structured-output-design/SKILL.md"
click node_prompt "https://github.com/sathvikar01/agent-engineering-skills/blob/main/prompt-engineering/SKILL.md"
click node_authority "https://github.com/sathvikar01/agent-engineering-skills/blob/main/deterministic-authority/SKILL.md"
click node_human_loop "https://github.com/sathvikar01/agent-engineering-skills/blob/main/human-in-the-loop/SKILL.md"
click node_guardrails "https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-guardrails/SKILL.md"
click node_security "https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-security/SKILL.md"
click node_rag "https://github.com/sathvikar01/agent-engineering-skills/blob/main/rag-engineering/SKILL.md"
click node_provenance "https://github.com/sathvikar01/agent-engineering-skills/blob/main/evidence-provenance/SKILL.md"
click node_state "https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-state-and-memory/SKILL.md"
click node_recovery "https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-failure-recovery/SKILL.md"
click node_observability "https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-observability/SKILL.md"
click node_cost "https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-cost-and-latency/SKILL.md"
click node_agent_evals "https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-evals/SKILL.md"
click node_testing "https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-testing/SKILL.md"
click node_tool_evals "https://github.com/sathvikar01/agent-engineering-skills/blob/main/tool-evals/SKILL.md"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_architecture,node_workflow,node_orchestration toneBlue
class node_tool_design,node_structured_output,node_prompt toneAmber
class node_authority,node_human_loop,node_guardrails,node_security toneMint
class node_rag,node_provenance,node_state toneRose
class node_recovery,node_observability,node_cost,node_agent_evals,node_testing,node_tool_evals,node_engineer toneIndigo
```

## Components

### Design

- [Agent Architecture](https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-architecture/SKILL.md): `agent-architecture/SKILL.md`
- [Development Workflow](https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-development-workflow/SKILL.md): `agent-development-workflow/SKILL.md`
- [Agent Orchestration](https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-orchestration/SKILL.md): `agent-orchestration/SKILL.md`

### Contracts

- [Tool Design](https://github.com/sathvikar01/agent-engineering-skills/blob/main/tool-design/SKILL.md): `tool-design/SKILL.md`
- [Structured Output](https://github.com/sathvikar01/agent-engineering-skills/blob/main/structured-output-design/SKILL.md): `structured-output-design/SKILL.md`
- [Prompt Engineering](https://github.com/sathvikar01/agent-engineering-skills/blob/main/prompt-engineering/SKILL.md): `prompt-engineering/SKILL.md`

### Authority & Safety

- [Deterministic Authority](https://github.com/sathvikar01/agent-engineering-skills/blob/main/deterministic-authority/SKILL.md): `deterministic-authority/SKILL.md`
- [Human Review](https://github.com/sathvikar01/agent-engineering-skills/blob/main/human-in-the-loop/SKILL.md): `human-in-the-loop/SKILL.md`
- [Agent Guardrails](https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-guardrails/SKILL.md): `agent-guardrails/SKILL.md`
- [Agent Security](https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-security/SKILL.md): `agent-security/SKILL.md`

### Data

- [RAG Engineering](https://github.com/sathvikar01/agent-engineering-skills/blob/main/rag-engineering/SKILL.md): `rag-engineering/SKILL.md`
- [Evidence Provenance](https://github.com/sathvikar01/agent-engineering-skills/blob/main/evidence-provenance/SKILL.md): `evidence-provenance/SKILL.md`
- [State & Memory](https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-state-and-memory/SKILL.md): `agent-state-and-memory/SKILL.md`

### Operations & Quality

- [Failure Recovery](https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-failure-recovery/SKILL.md): `agent-failure-recovery/SKILL.md`
- [Agent Observability](https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-observability/SKILL.md): `agent-observability/SKILL.md`
- [Cost & Latency](https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-cost-and-latency/SKILL.md): `agent-cost-and-latency/SKILL.md`
- [Agent Evaluations](https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-evals/SKILL.md): `agent-evals/SKILL.md`
- [Agent Testing](https://github.com/sathvikar01/agent-engineering-skills/blob/main/agent-testing/SKILL.md): `agent-testing/SKILL.md`
- [Tool Evaluations](https://github.com/sathvikar01/agent-engineering-skills/blob/main/tool-evals/SKILL.md): `tool-evals/SKILL.md`

### Other components

- **Agent Builder**

## Connections

- Agent Builder → Agent Architecture: consults for design (evidence: `README.md`)
- Agent Builder → Development Workflow: consults for lifecycle (evidence: `README.md`)
- Agent Builder → Agent Orchestration: consults for routing (evidence: `README.md`)
- Agent Builder → Tool Design: consults for tools (evidence: `README.md`)
- Agent Builder → Structured Output: consults for output (evidence: `README.md`)
- Agent Builder → Prompt Engineering: consults for prompts (evidence: `README.md`)
- Agent Builder → Deterministic Authority: consults for authority (evidence: `README.md`)
- Agent Builder → Human Review: consults for approval (evidence: `README.md`)
- Agent Builder → Agent Guardrails: consults for controls (evidence: `README.md`)
- Agent Builder → Agent Security: consults for threats (evidence: `README.md`)
- Agent Builder → RAG Engineering: consults for retrieval (evidence: `README.md`)
- Agent Builder → Evidence Provenance: consults for lineage (evidence: `README.md`)
- Agent Builder → State & Memory: consults for memory (evidence: `README.md`)
- Agent Builder → Failure Recovery: consults for recovery (evidence: `README.md`)
- Agent Builder → Agent Observability: consults for operations (evidence: `README.md`)
- Agent Builder → Cost & Latency: consults for optimization (evidence: `README.md`)
- Agent Builder → Agent Evaluations: consults for quality (evidence: `README.md`)
- Agent Builder → Agent Testing: consults for testing (evidence: `README.md`)
- Agent Builder → Tool Evaluations: consults for tool quality (evidence: `README.md`)
