Agent skill

AWS Architecture Diagram

by vidanov in vidanov/aws-architecture-diagram-skill

Generate AWS architecture diagrams in draw.io format. An agent skill from vidanov/aws-architecture-diagram-skill.

MITAuto-check passedDevOps & Cloud

Install AWS Architecture Diagram

skills CLI
$ npx skills add vidanov/aws-architecture-diagram-skill --skill aws-architecture-diagram -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install vidanov/aws-architecture-diagram-skill aws-architecture-diagram --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/vidanov/aws-architecture-diagram-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/kiro .claude/skills/aws-architecture-diagram && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
aws-architecture-diagram
GitHub stars
159
Token cost
~4.9k tokens
SKILL.md length
2,069 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Generate AWS architecture diagrams in draw.io format. An agent skill from vidanov/aws-architecture-diagram-skill.

  • Works in 4 steps: Header + left side (frontend, delivery… → Middle (processing lambdas, database) → Right side (ingest, messaging, data… → …
  • Build an architecture diagram
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Draw.io diagram for AWS services

What it does

AWS Architecture Diagram is an agent skill from vidanov/aws-architecture-diagram-skill. Generate AWS architecture diagrams in draw.io format. Activates when the user asks to create, generate, or build an architecture diagram, system diagram, or draw.io diagram for AWS services.

Its SKILL.md is about 4.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering Diagrams and Cloud architecture. It works with draw.io and Amazon Web Services. The repository describes itself as: Reusable skill for generating AWS architecture diagrams in draw.io format. Works with Kiro CLI and Claude Code. The licence is MIT.

When your agent uses it

  • Build an architecture diagram
  • Draw.io diagram for AWS services

Example prompts

  • “/aws-architecture-diagram”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Header + left side (frontend, delivery layer)
  2. Middle (processing lambdas, database)
  3. Right side (ingest, messaging, data sources)
  4. Bottom (optional/outbound flows) + close XML

What it can do on your machine

Read from SKILL.md and the folder at commit d0f8550. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are xml).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • raw.githubusercontent.com
    • aws.amazon.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

AWS Architecture Diagram loads about 4.9k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 2,069 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~4.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from vidanov/aws-architecture-diagram-skill at commit d0f8550, republished under its MIT licence (© vidanov). 2,069 words, ~4,889 tokens.

Download SKILL.mdSave it as .claude/skills/aws-architecture-diagram/SKILL.md (or your agent's skills folder).
name
aws-architecture-diagram
description
Generate AWS architecture diagrams in draw.io format. Activates when the user asks to create, generate, or build an architecture diagram, system diagram, or draw.io diagram for AWS services.

Instructions

Generate a draw.io (.drawio) XML file representing an AWS architecture diagram.

Layout
  • Left-to-right flow for data/request path
  • UI/Frontend on the LEFT (users access from left side)
  • Data sources / external systems on the RIGHT
  • Use horizontal lanes for parallel paths (top lane, bottom lane)
  • Minimum 220px horizontal spacing between icons (to leave room for edge labels)
  • Minimum 250px vertical spacing between lanes (so vertical edges don't crowd)
  • Secondary/auxiliary services (monitoring, DLQ, error paths) go BELOW the main flow with 280px+ vertical gap
Canvas
  • Large canvas: pageWidth="2400" pageHeight="1400" minimum
  • Set dx="2800" dy="1600" for proper viewport
  • Always include a title block as the first element after the background:
xml
<mxCell value="&lt;b&gt;Diagram Title&lt;/b&gt;&lt;br&gt;Author | Date | Version" style="text;html=1;align=left;verticalAlign=top;whiteSpace=wrap;rounded=0;fontSize=14;spacing=8;" vertex="1" parent="1">
  <mxGeometry x="40" y="30" width="420" height="60" as="geometry" />
</mxCell>
Icon Style
  • Icons are from draw.io's built-in mxgraph.aws4 stencil library — the official AWS Architecture Icons (https://aws.amazon.com/architecture/icons/, updated quarterly)
  • Icon size: 78x78px for main services, 65x65px for secondary
  • Use sketch=0;outlineConnect=0; on all icons
  • Use strokeColor=#ffffff on all AWS service icons
  • MUST include fillColor — without it, icons render as invisible/white in PNG export
  • Font size: 12px for labels
  • Always include: fontColor=#232F3E;verticalLabelPosition=bottom;verticalAlign=top;align=center;html=1;aspect=fixed;

fillColor by AWS service category:

CategoryfillColorServices
Compute#ED7100Lambda, EC2, ECS, EKS, Fargate
Networking#8C4FFFVPC, ELB, CloudFront, Route 53, API Gateway
Database#C925D1RDS, DynamoDB, Aurora, ElastiCache
Storage#3F8624S3, EFS, EBS
Security#DD344CIAM, Cognito, KMS, WAF
Integration#E7157BSQS, SNS, EventBridge, Step Functions
Analytics#8C4FFFKinesis, Athena, Redshift
Management#E7157BCloudWatch, CloudTrail
AI/ML#01A88DBedrock, SageMaker
3D / Isometric Diagrams — use a different icon library

If the user asks for a 3D, isometric, or "AWS 3D" diagram, do NOT fake it by placing flat aws4 icons on hand-built platform/pedestal shapes. draw.io has a real, separate built-in library for this: mxgraph.aws3d.*.

  • Load references/aws-icons-3d.md before picking any icon — it has the verified shape table, style prefix, sizes, and the native isometricEdgeStyle edge templates.
  • This library is a legacy pre-2019 icon set with much smaller coverage than aws4 (no API Gateway, ECS/EKS/Fargate, Step Functions, EventBridge, SNS, Aurora, CloudWatch, IAM, etc.). Check the gap table in that reference file before assuming an icon exists, and flag substitutions to the user rather than guessing a stencil name.
  • For generic hardware (clients, on-prem servers, racks, switches) with no AWS-specific icon, see references/aws-icons-allied-telesis.md — a separate bundled isometric image library that fills that gap.
  • These icons are already 3D on their own — arrange them in an ascending isometric staircase (diagonal offsets between nodes), don't add fake platforms underneath.
  • Use edgeStyle=isometricEdgeStyle (with endArrow=block override for reliable arrowheads) instead of orthogonalEdgeStyle for connectors.
Edge Style — CRITICAL FOR CLEAN DIAGRAMS

Base edge style (all edges):

edgeStyle=orthogonalEdgeStyle;rounded=1;orthogonalLoop=1;jettySize=auto;html=1;strokeWidth=2;exitX=1;exitY=0.5;exitDx=0;exitDy=0;entryX=0;entryY=0.5;entryDx=0;entryDy=0;

Rules for edge labels:

  • Keep labels SHORT (1-2 words max). Use icon labels for detail, not edge labels.
  • On horizontal edges: position label ABOVE the line using verticalAlign=bottom; in the edge style
  • On vertical edges: position label to the LEFT using align=right; in the edge style
  • Always add labelBackgroundColor=#F5F5F5; so labels don't overlap lines
  • For edges WITHOUT labels: omit the value attribute entirely (don't use value="")

Edge label positioning (prevents overlap with icons):

xml
<mxCell value="Label" style="edgeStyle=orthogonalEdgeStyle;rounded=1;orthogonalLoop=1;jettySize=auto;html=1;strokeWidth=2;labelBackgroundColor=#F5F5F5;fontSize=11;" edge="1" source="a" target="b" parent="1">
  <mxGeometry relative="1" as="geometry" />
</mxCell>

For edges that go to services ABOVE or BELOW the main flow:

  • Use explicit exit/entry points to control routing:
    • Exit bottom: exitX=0.5;exitY=1;exitDx=0;exitDy=0;
    • Enter top: entryX=0.5;entryY=0;entryDx=0;entryDy=0;
    • Exit top: exitX=0.5;exitY=0;exitDx=0;exitDy=0;
    • Enter bottom: entryX=0.5;entryY=1;entryDx=0;entryDy=0;
  • This prevents draw.io from routing lines through other icons

Edge types:

  • Solid black (strokeWidth=2): primary data flow
  • Dashed black (strokeWidth=2;dashed=1;): optional/async path
  • Dashed red (strokeWidth=2;dashed=1;strokeColor=#DD344C;): error path

Edge attachment (CRITICAL — fixes "green cross" problem):

  • Every edge MUST have both source="<cell-id>" and target="<cell-id>" attributes referencing valid cell IDs
  • NEVER create floating/unattached edges — all edges must be bound to shapes at both ends
  • Always include exitX/exitY and entryX/entryY to define exact connection points on the shape perimeter
  • In draw.io, properly attached edges show a "blue dot" anchor; unattached edges show a "green cross"
  • If an edge connects to a child inside a container, reference the child's ID directly (not the container)
  • Cross-container edges: When source and target are in different containers, set the edge's parent="1" (root layer) so draw.io can route it across boundaries

When NOT to label edges:

  • If the flow is obvious from context (e.g., Lambda → DynamoDB doesn't need "Write")
  • If the icon labels already explain the relationship
  • Prefer fewer, more meaningful labels over labeling every edge
Visual Quality: straight arrows, no overlaps, professional layout

A diagram with correct icons but a messy layout still reads as unprofessional. Check every diagram against these rules before finishing — they're deliberately concrete/checkable, not vague "make it look nice" advice:

  • Align nodes to a consistent axis so edges are single, straight segments. Keep the horizontal or vertical delta between adjacent nodes in a flow constant (same lane y-coordinate, same column spacing) so connecting edges render as one clean line instead of a dogleg.
  • Align branch/secondary nodes on the exact same centerline as their parent. If a node branches off vertically (e.g. an auxiliary service below the main flow), its horizontal center must match its parent's horizontal center exactly — compute child.x = parent.center_x - child.width/2, don't eyeball it. A few pixels of misalignment turns a "straight down" edge into a visibly crooked diagonal.
  • One bend maximum per edge, ideally zero. If a computed edge path would need more than one bend to avoid an obstacle, the layout is wrong — move the node, don't add more bends to route around the problem.
  • No edge may cross through an unrelated icon's bounding box. Before finalizing coordinates, check each edge's path against every icon's (x, y, width, height) rectangle it isn't connected to. If it would cross one, move the node or add an explicit exit/entry point to route around it.
  • No two edges may run on top of each other or visually merge. If two edges would travel the same corridor (e.g. two parallel flows between the same pair of lanes), offset them — different exit/entry points, or an explicit waypoint — so there's a visible gap between them.
  • Minimize edge crossings overall. Order nodes in the direction the data actually flows so edges rarely need to cross each other. If a crossing is unavoidable (e.g. a feedback/response path), route it with a visible offset rather than letting it overlap another edge.
  • Keep spacing consistent, not just "enough." Use the same minimum step size between every pair of adjacent nodes in a flow — a diagram where some gaps are 400px and others are 250px reads as sloppy even if nothing technically overlaps.
  • Balance the composition on the canvas. Don't leave one half of the page dense and the other empty; size the canvas to the actual content plus a consistent margin.
  • Self-check before finishing: after placing every coordinate, mentally trace each edge from source to target and verify (1) it doesn't cross any icon, (2) it doesn't overlap another edge, (3) it has at most one bend, (4) its endpoints are flush with the icons it connects. Fix the layout, not just the intent, if any check fails.
Two Icon Patterns — CRITICAL

Pattern 1: Service-level (resourceIcon frame)

  • Style: sketch=0;outlineConnect=0;fontColor=#232F3E;fillColor=<CATEGORY_COLOR>;strokeColor=#ffffff;dashed=0;verticalLabelPosition=bottom;verticalAlign=top;align=center;html=1;fontSize=12;fontStyle=0;aspect=fixed;shape=mxgraph.aws4.resourceIcon;resIcon=mxgraph.aws4.<name>
  • MUST use strokeColor=#ffffff — without it, the white glyph disappears
  • MUST use fillColor=<color> — without it, icon renders as white/invisible square in PNG export
  • Size: 78x78

Pattern 2: Resource-level (standalone shape)

  • Style: sketch=0;outlineConnect=0;fontColor=#232F3E;fillColor=<CATEGORY_COLOR>;strokeColor=none;dashed=0;verticalLabelPosition=bottom;verticalAlign=top;align=center;html=1;fontSize=12;fontStyle=0;aspect=fixed;shape=mxgraph.aws4.<name>
  • MUST use strokeColor=none — using #ffffff breaks these
  • MUST use fillColor=<color> — same reason as above
  • Size: 78x78 or 48x48

Confusing these patterns guarantees broken icons.

Show full SKILL.md (879 more words)Show less
Icon Reference Files (load by category as needed)
  • references/aws-icons-compute.md — Lambda, EC2, ECS, EKS, Fargate
  • references/aws-icons-database.md — DynamoDB, RDS, Aurora, ElastiCache
  • references/aws-icons-integration.md — API Gateway, SQS, SNS, EventBridge, Step Functions
  • references/aws-icons-networking.md — CloudFront, Route 53, VPC, ELB
  • references/aws-icons-storage.md — S3, EFS, EBS, Glacier, Backup
  • references/aws-icons-security.md — IAM, Cognito, KMS, WAF, Shield
  • references/aws-icons-analytics-ml.md — Kinesis, Athena, Bedrock, SageMaker
  • references/aws-icons-common.md — Groups, general resources, edge styles, base template
  • references/aws-icons-3d.md — 3D/isometric diagrams: legacy aws3d icon library, coverage gaps, isometric edge style
  • references/aws-icons-allied-telesis.md — bonus isometric computer/server/network icons for 3D diagrams (fills aws3d gaps)

Always look up icons from reference files. Never guess icon names.

Fallback for unmapped services: If a service is NOT found in any reference file, use this generic AWS cloud icon with the service name as label:

sketch=0;outlineConnect=0;fontColor=#232F3E;fillColor=#232F3E;strokeColor=#ffffff;dashed=0;verticalLabelPosition=bottom;verticalAlign=top;align=center;html=1;fontSize=12;fontStyle=0;aspect=fixed;shape=mxgraph.aws4.resourceIcon;resIcon=mxgraph.aws4.general_AWScloud

Never render an unknown service as a plain colored rectangle with no label.

Group Boundaries
  • AWS Cloud: shape=mxgraph.aws4.group;grIcon=mxgraph.aws4.group_aws_cloud_alt;strokeColor=#232F3E;fillColor=none;container=1;dropTarget=1;
  • Account: shape=mxgraph.aws4.group;grIcon=mxgraph.aws4.group_account;strokeColor=#CD2264;fillColor=none;container=1;dropTarget=1;
  • On-premise: shape=mxgraph.aws4.group;grIcon=mxgraph.aws4.group_on_premise;strokeColor=#5A6C86;fillColor=none;container=1;dropTarget=1;
  • VPC: shape=mxgraph.aws4.group;grIcon=mxgraph.aws4.group_vpc2;strokeColor=#8C4FFF;fillColor=none;container=1;dropTarget=1;
  • Subnet (public): shape=mxgraph.aws4.group;grIcon=mxgraph.aws4.group_security_group;strokeColor=#7AA116;fillColor=none;container=1;dropTarget=1;
  • Subnet (private): shape=mxgraph.aws4.group;grIcon=mxgraph.aws4.group_security_group;strokeColor=#147EBA;fillColor=none;container=1;dropTarget=1;
  • Logical groups: Simple dashed boxes: whiteSpace=wrap;html=1;fillColor=none;dashed=1;dashPattern=8 8;container=1;dropTarget=1;
  • NO colored backgrounds on group boxes — always fillColor=none

Container nesting (CRITICAL for grouping):

  • ALL boundary/group shapes MUST include container=1;dropTarget=1; in their style
  • Child cells inside a boundary MUST set parent="<boundary-cell-id>" instead of parent="1"
  • This ensures moving a boundary moves all its children together
  • Example:
xml
<mxCell id="vpc1" value="VPC" style="shape=mxgraph.aws4.group;grIcon=mxgraph.aws4.group_vpc2;strokeColor=#8C4FFF;fillColor=none;container=1;dropTarget=1;" vertex="1" parent="1">
  <mxGeometry x="100" y="100" width="800" height="500" as="geometry" />
</mxCell>
<mxCell id="lambda1" value="Lambda" style="shape=mxgraph.aws4.resourceIcon;resIcon=mxgraph.aws4.lambda;strokeColor=#ffffff;" vertex="1" parent="vpc1">
  <mxGeometry x="50" y="50" width="78" height="78" as="geometry" />
</mxCell>

Note: child geometry coordinates are relative to the parent container, not the canvas.

PNG Export Background Fix

Place a full-canvas rectangle as the FIRST element (lowest z-order):

xml
<mxCell value="" style="rounded=0;whiteSpace=wrap;html=1;fillColor=#F5F5F5;strokeColor=none;" vertex="1" parent="1">
  <mxGeometry x="0" y="0" width="2400" height="1400" as="geometry" />
</mxCell>

This prevents black background on PNG export. Use strokeColor=none (not E0E0E0).

Multi-page Diagrams

For complex architectures, use multiple pages (tabs) in one .drawio file:

xml
<mxfile>
  <diagram id="overview" name="Overview">...</diagram>
  <diagram id="networking" name="Networking Detail">...</diagram>
  <diagram id="data-flow" name="Data Flow">...</diagram>
</mxfile>
  • Page 1: High-level overview (service-level icons only)
  • Page 2+: Detail views (resource-level icons, subnet layouts, etc.)
Edge Legend (optional, for complex diagrams)

Place below the title block if the diagram has multiple edge types:

  • Solid line: primary data flow
  • Dashed line: optional/async
  • Red dashed: error path
File Splitting

Since draw.io XML can be large, split creation across multiple tool calls:

  1. Header + left side (frontend, delivery layer)
  2. Middle (processing lambdas, database)
  3. Right side (ingest, messaging, data sources)
  4. Bottom (optional/outbound flows) + close XML
Audience Mode

Before generating, assess the target audience:

  • Technical: Use service names, protocol labels (HTTPS, gRPC), CIDR blocks, instance types
  • Non-technical: Use action labels ("Store Data", "Send Notification"), hide implementation details, use numbered flow (① ② ③)

If unclear, ask: "Technical audience or executive/non-technical?"

Numbered Flow Edges (for non-technical mode)

Instead of technical labels, show flow order with circled numbers:

  • Flow A: ① → ② → ③ → ④ (white circled numbers)
  • Flow B: ❶ → ❷ → ❸ → ❹ (black circled numbers for second flow)

Use edge labels: value="①" with fontSize=14;fontStyle=1;labelBackgroundColor=#ffffff;

Companion Guide

After generating the .drawio file, also generate a markdown guide:

  • Same filename with .md extension (e.g., serverless-api.drawio + serverless-api.md)
  • Contents: diagram title, flow description (numbered steps matching edge labels), service list with purpose, key design decisions
Two-Step Edit Approach

After generating the initial .drawio file:

  1. Export to PNG using the draw.io CLI (see Output section)
  2. Review the PNG visually — check for empty/broken icons, overlapping edges, misaligned labels
  3. Fix issues in the .drawio XML and re-export

This catches rendering problems (wrong stencil names, broken styles) that are invisible in raw XML.

Icon Name Gotchas — CRITICAL

draw.io stencil names do NOT always match current AWS service names. Services that were renamed keep their legacy stencil names:

AWS Service Namedraw.io resIcon nameWhy
Amazon OpenSearch Serviceelasticsearch_serviceRenamed from Elasticsearch in 2021; opensearch_service also works
Amazon EventBridgeeventbridgeWas CloudWatch Events
AWS FargatefargateCorrect
VPC PeeringpeeringResource-level: shape=mxgraph.aws4.peering;strokeColor=none — NOT vpc_peering or peering_connection (those render as blank squares)
Amazon MSKmanaged_streaming_for_kafkaNOT msk (renders as blank square)
IAM Identity Centersingle_sign_onNOT iam_identity_center (renders as blank square)

Rule: Always verify icon names from the reference files. If a service icon renders as an empty box, the stencil name is wrong. Check the draw.io source at src/main/webapp/js/diagramly/sidebar/Sidebar-AWS4.js for the canonical name (or Sidebar-AWS3D.js for the legacy 3D/isometric library, or Sidebar-AlliedTelesis.js for the generic hardware image library — note the 3D library's shape names are camelCase, e.g. dynamoDb not dynamodb).

Validation Step

After generating XML, mentally verify:

  1. Every resIcon= value exists in the reference files
  2. Service-level icons have strokeColor=#ffffff
  3. Resource-level icons have strokeColor=none
  4. No XML comments present
  5. All cell IDs are unique
  6. Every edge has <mxGeometry relative="1" as="geometry" />
  7. No icon uses a guessed stencil name — all verified against reference files
  8. Every edge has both source and target attributes referencing valid cell IDs (no floating edges)
  9. All group/boundary shapes include container=1;dropTarget=1; in their style
  10. Children inside boundaries use parent="<boundary-id>" (not parent="1")
Output
  • Save with descriptive filename ending in .drawio
  • Open with open command (macOS) or xdg-open (Linux) after creation
  • For PNG/SVG/PDF export, use draw.io CLI:
    • macOS: /Applications/draw.io.app/Contents/MacOS/draw.io -x -f png -e -b 10 -o output.drawio.png input.drawio
    • Linux: drawio -x -f png -e -b 10 -o output.drawio.png input.drawio Flags: -x export, -f format, -e embed diagram XML, -b 10 border
  • Exported files use double extension: name.drawio.png (signals embedded XML, re-editable in draw.io)
XML Well-formedness (CRITICAL)
  • NEVER include XML comments (<!-- -->) — they cause parse errors
  • Escape special characters in values: &amp; &lt; &gt; &quot;
  • Always use unique id values for each mxCell
  • Every edge MUST have <mxGeometry relative="1" as="geometry" /> as child element
  • Basic structure must include root cells id="0" and id="1" (parent="0")
Official Reference

© vidanov, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in kiro of vidanov/aws-architecture-diagram-skill.

Open the folder on GitHubat commit d0f8550

Compare with similar skills

AWS Architecture Diagram next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

AWS Architecture Diagram compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AWS Architecture Diagram this skillvidanov/aws-architecture-diagram-skill159—~4.9kAutomated safety check: PassMIT
AWS Architecture Diagramawslabs/agent-plugins916—~3.8kAutomated safety check: NotesApache-2.0
Drawio AWSsparklabx/drawio-ai-kit655—~1.6kAutomated safety check: PassMIT
AWS DrawIO Diagram Generatora5c-ai/babysitter1.8k—~4.2kAutomated safety check: PassMIT
AWS Drawio Architecture Diagramsgiuseppe-trisciuoglio/developer-kit357—~3.1kAutomated safety check: NotesMIT
GCP DrawIO Diagram Generatora5c-ai/babysitter1.8k—~3.7kAutomated safety check: PassMIT

Similar skills

  • AWS Architecture Diagram

    awslabs/agent-plugins

    Official

    Generate validated AWS architecture diagrams as draw.io XML using official AWS4 icon libraries.

    916 GitHub stars~3.8k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes
  • Drawio AWS

    sparklabx/drawio-ai-kit

    A skill your agent uses when the user asks for an AWS architecture diagram — VPC/networking, event-driven, landing zone, multi-AZ, serverless pipeline, or any diagram built with AWS service icons.

    655 GitHub stars~1.6k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Creates and edits AWS architecture diagrams as DrawIO XML, converting a text description or an image and reading existing files back into shapes.

    1.8k GitHub stars~4.2k tokensUpdated 24 days ago
    DevelopmentAuto-check passed
  • AWS Drawio Architecture Diagrams

    giuseppe-trisciuoglio/developer-kit

    Creates professional AWS architecture diagrams in draw.io XML format (.drawio files) using official AWS Architecture Icons (aws4 library).

    357 GitHub stars~3.1k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes
  • Creates DrawIO XML diagrams of Google Cloud architectures from text or images, and analyzes existing .drawio files to list their GCP components.

    1.8k GitHub stars~3.7k tokensUpdated 24 days ago
    DevOps & CloudAuto-check passed
  • Official

    Compare a Draw.io Azure architecture diagram against a live Azure environment to detect drift.

    101 GitHub stars~3.7k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed

More from vidanov/aws-architecture-diagram-skill

  • AWS Architecture Diagram

    vidanov/aws-architecture-diagram-skill

    Always use when user asks to create, generate, or build an AWS architecture diagram, cloud infrastructure diagram, or system diagram with AWS services.

    159 GitHub stars~4.4k tokensUpdated 6 days ago
    Auto-check passed

Questions about AWS Architecture Diagram

What does AWS Architecture Diagram do?

Generate AWS architecture diagrams in draw.io format. An agent skill from vidanov/aws-architecture-diagram-skill. AWS Architecture Diagram is an agent skill from vidanov/aws-architecture-diagram-skill.io format.

When should I use AWS Architecture Diagram?

AWS Architecture Diagram fits situations like: build an architecture diagram; draw.io diagram for AWS services.

How do I install AWS Architecture Diagram in Claude Code?

Run `npx skills add vidanov/aws-architecture-diagram-skill --skill aws-architecture-diagram -a claude-code`. Or copy the skill folder (kiro in vidanov/aws-architecture-diagram-skill) into .claude/skills/aws-architecture-diagram in your project. Claude Code loads it when a task matches its description.

How do I install AWS Architecture Diagram in Codex?

Run `npx skills add vidanov/aws-architecture-diagram-skill --skill aws-architecture-diagram -a codex`. Or copy the skill folder (kiro in vidanov/aws-architecture-diagram-skill) into .agents/skills/aws-architecture-diagram in your project. Codex loads it when a task matches its description.

Can I use AWS Architecture Diagram in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vidanov/aws-architecture-diagram-skill --skill aws-architecture-diagram -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/aws-architecture-diagram, .gemini/skills/aws-architecture-diagram, .github/skills/aws-architecture-diagram and .opencode/skills/aws-architecture-diagram in your project.

What does AWS Architecture Diagram need to run?

SKILL.md names no scripts, command-line tools or credentials: AWS Architecture Diagram is instructions for the agent only.

Does AWS Architecture Diagram access the network?

SKILL.md names 2 domains. As links in the text: raw.githubusercontent.com and aws.amazon.com. This is read from the text; nothing was executed.

Is AWS Architecture Diagram safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does AWS Architecture Diagram use?

AWS Architecture Diagram is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does AWS Architecture Diagram use?

About 4.9k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to AWS Architecture Diagram?

Skills that share tags, products or a category with AWS Architecture Diagram: AWS Architecture Diagram (awslabs/agent-plugins, 916 stars), Drawio AWS (sparklabx/drawio-ai-kit, 655 stars), AWS DrawIO Diagram Generator (a5c-ai/babysitter, 1.8k stars) and AWS Drawio Architecture Diagrams (giuseppe-trisciuoglio/developer-kit, 357 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AWS Architecture Diagram?

vidanov (a GitHub user) maintains it in vidanov/aws-architecture-diagram-skill, which has 159 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 4, 2026.

Source: vidanov/aws-architecture-diagram-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.