Kiro-KitReferencePresets
sa
Solutions Architect kit for designing and documenting cloud architectures with 26 agents, 31 skills, 69 commands — draw.io + Mermaid diagrams, Word/PowerPoint deliverables, CloudFormation + Terraform IaC, Well-Architected reviews, and whole-repo deep security scanning
npx kiro-kit add sa
Solutions Architect kit for designing and documenting cloud architectures with 26 agents, 31 skills, 69 commands — draw.io + Mermaid diagrams, Word/PowerPoint deliverables, CloudFormation + Terraform IaC, Well-Architected reviews, and whole-repo deep security scanning
At a glance
| Artifact | Count |
|---|---|
| Commands | 69 |
| Agents | 26 |
| Skills | 31 |
| Workflows | 4 |
| Hook scripts | 11 |
| Native Kiro hooks | 8 |
| Files written in total | 401 |
Category: sa · Version: 1.0.0
Tags: docker, kubernetes, terraform, cicd, devops, infrastructure, cloud
Commands
| Command | Description |
|---|---|
ask | ⚡ Answer technical and architectural questions. |
bootstrap | Bootstrap the project from scratch with dependencies and infrastructure setup |
bootstrap/auto | ⚡⚡⚡⚡ Bootstrap a new project automatically |
bootstrap/auto/fast | ⚡⚡⚡ Quickly bootstrap a new project automatically |
brainstorm | ⚡⚡ Brainstorm a feature |
clean | Clean build artifacts, caches, and temporary files |
code | ⚡ Start coding & testing an existing plan |
content/cro | Analyze the current content and optimize for conversion |
content/enhance | Analyze the current copy issues and enhance it |
content/fast | Write creative & smart copy [FAST] |
content/good | Write good creative & smart copy [GOOD] |
cook | ⚡⚡⚡ Implement a feature [step by step] |
cook/auto | ⚡⚡ Implement a feature automatically ("trust me bro") |
cook/auto/fast | ⚡ No research. Only scout, plan & implement ["trust me bro"] |
debug | ⚡⚡ Debugging technical issues and providing solutions. |
design/figma | Extract design tokens and component specs from Figma |
design/system | Analyze and document the project design system |
design/wireframe | Create wireframe specifications for a feature or page |
devops/container | Build, scan, and manage container images |
devops/deploy | Deploy application to target environment using configured deployment strategy |
devops/infra | Manage infrastructure with Terraform (plan, apply, destroy) |
devops/monitor | Check monitoring status, alerts, and service health |
docs/architecture | Generate or update architecture documentation |
docs/init | ⚡⚡⚡⚡ Analyze the codebase and create initial documentation |
docs/summarize | Analyze the codebase and generate documentation summary |
docs/update | Update documentation to reflect recent code changes |
fix | ⚡⚡ Analyze and fix small issues [AUTO DETECT COMPLEXITY] |
fix/build | Diagnose and fix build failures |
fix/ci | ⚡ Analyze Github Actions logs and fix issues |
fix/fast | ⚡ Analyze and fix small issues [FAST] |
fix/hard | ⚡⚡⚡ Use subagents to plan and fix hard issues |
fix/lint | Auto-fix linting errors across the project |
fix/logs | ⚡ Analyze logs and fix issues |
fix/test | ⚡⚡ Run test suite and fix issues |
fix/tests | Diagnose and fix failing tests |
fix/types | ⚡ Fix type errors |
fix/ui | ⚡⚡ Analyze and fix UI issues |
git/branch | Create a new branch following naming conventions |
git/cm | Stage all files and create a commit. |
git/commit | Stage and commit changes with conventional commit message |
git/cp | Stage, commit and push all code in the current branch |
git/pr | Create a pull request with proper description |
iac/cloudformation | Author, lint, and manage CloudFormation stacks (scaffold, lint, deploy, drift) |
iac/terraform-module | Scaffold, validate, and document reusable Terraform modules |
iac/well-architected-review | Run a 6-pillar AWS Well-Architected review against a design or IaC directory |
journal | ⚡ Write some journal entries. |
lint | Run linting and validation checks across the project |
plan | ⚡⚡⚡ Intelligent plan creation with prompt enhancement |
plan/ci | Analyze Github Actions logs and provide a plan to fix the issues |
plan/cro | Create a CRO plan for the given content |
plan/fast | ⚡⚡ No research. Only analyze and create an implementation plan |
plan/feature | Create an implementation plan for a new feature |
plan/hard | ⚡⚡⚡ Research, analyze, and create an implementation plan |
plan/refactor | Plan a refactoring effort with risk assessment |
plan/two | ⚡⚡⚡⚡ Research & create an implementation plan with 2 approaches |
release | Prepare and execute a release with version bump and changelog |
review/code | Review recent code changes for quality and correctness |
review/codebase | ⚡⚡⚡ Scan & analyze the codebase. |
review/security | Run security review on infrastructure and application code |
scout | Scout the codebase for files relevant to a task |
scout/ext | Scout codebase using external agentic tools for faster parallel search |
security/deep-scan | Whole-repository deep security scan (multi-agent pipeline, findings workspace) |
skill/add | Add new reference files or scripts to a skill |
skill/create | Create a new skill from template |
skill/fix-logs | Fix the agent skill based on logs.txt file. |
skill/optimize | Optimize an existing agent skill |
test | Run the test suite with coverage reporting |
use-mcp | Utilize tools of Model Context Protocol (MCP) servers |
watzup | ⚡ Review recent changes and wrap up the work |
Agents
| Agent | Description |
|---|---|
brainstormer | Use when you need to brainstorm infrastructure solutions, evaluate architectural approaches, or debate technical decisions before implementation begins. |
ci-cd-specialist | Use when you need to design, implement, or troubleshoot CI/CD pipelines (GitHub Actions, GitLab CI, Jenkins, ArgoCD), deployment strategies, or release automation workflows. |
code-reviewer | Use when you need code review, quality analysis, security audit, or feedback on infrastructure code (Terraform, Dockerfiles, Helm charts, CI pipelines) before merging or deploying. |
copywriter | Use when you need high-converting copy for marketing materials, social media posts, landing pages, email campaigns, or any content that must capture attention and drive action. |
database-admin | Use when you need database diagnostics, query optimization, schema design, index strategy, backup planning, replication setup, or performance troubleshooting. |
debugger | Use when you need to investigate issues, diagnose errors, analyze logs, trace execution flows, identify performance bottlenecks, or troubleshoot failing deployments and infrastructure. |
docs-manager | Use when you need to create, update, or organize technical documentation, synchronize docs with code changes, write product requirements, or maintain documentation standards. |
git-manager | Use when you need to stage, commit, push code changes, create pull requests, or manage git operations with conventional commit messages. |
infrastructure-engineer | Use when you need to design, implement, or modify cloud infrastructure using Terraform, CloudFormation, Pulumi, or other IaC tools. Covers VPCs, compute, storage, networking, IAM, and multi-cloud architectures. |
journal-writer | Use when significant technical difficulties occur -- repeated deployment failures, critical infrastructure bugs, failed migrations, security incidents, or architectural decisions that prove problematic in practice. |
mcp-manager | Use when you need to manage MCP (Model Context Protocol) server integrations, discover available tools and resources, execute MCP capabilities, or troubleshoot MCP connectivity issues. |
monitoring-engineer | Use when you need to design observability systems, configure monitoring and alerting, set up dashboards, implement logging strategies, or troubleshoot using metrics and traces. |
planner | Use when you need to research, analyze, and create comprehensive implementation plans for infrastructure changes, system architectures, or complex technical solutions before starting implementation. |
project-manager | Use when you need project oversight, progress tracking against implementation plans, status reporting, milestone management, or coordination across multiple workstreams. |
researcher | Use when you need to research technologies, find documentation, explore best practices, evaluate libraries, or gather technical information from multiple sources before making decisions. |
scout | Use when you need to quickly locate relevant files across a large codebase for a specific task, before starting implementation or debugging that spans multiple directories. |
scout-external | Use when you need to locate files across a large codebase using external agentic tools (Gemini, OpenCode) for faster parallel searching with large context windows. |
security-auditor | Use when you need security assessments of infrastructure, container images, CI/CD pipelines, IAM policies, network configurations, or compliance audits against standards like CIS, SOC2, or PCI-DSS. |
security-finder | Use during a deep security scan to hunt vulnerabilities inside one assigned partition of the attack surface. Traces data flow from user inputs to sensitive sinks and writes candidate findings incrementally to a partition file. |
security-judge | Use during a deep security scan, after validation, as the single SERIAL dedup pass over surviving findings. Classifies each as new / better-example-of-known / duplicate, fixes final severity, assigns slugs. |
security-recon | Use at the start of a deep security scan to map the attack surface of a repository and partition it into non-overlapping segments for parallel vulnerability finders. Produces scan-manifest.json. |
security-reporter | Use at the end of a deep security scan to write the findings workspace — report.md, per-finding reports, hardening recommendations, and the three JSON automation files (scan-manifest, findings, coverage). |
security-triage | Use in a deep security scan's optional Semgrep hybrid mode to classify a batch of SAST results as true positive, false positive, or hard-excluded, reading the flagged code with real context. |
security-validator | Use during a deep security scan to adversarially validate ONE candidate finding. Attempts to refute it, assigns confidence 1-10; findings below 8 are dropped. The false-positive filter of the pipeline. |
tester | Use when you need to validate code through testing -- running test suites, analyzing coverage, checking for regressions, validating infrastructure code, or verifying build processes after implementation changes. |
ui-ux-designer | Use when you need UI/UX design work including dashboard interfaces, monitoring views, admin panels, or design documentation and review. |
Skills
| Skill | Description |
|---|---|
ai-multimodal | Process and generate multimedia content using AI APIs. Use when working with images, audio, video, or document analysis. |
architecture-deck | Produce .pptx architecture presentations (title, context, component, sequence, deployment slides) with python-pptx. Use when the user asks for an architecture deck, solution presentation, design review slides, or any .pptx deliverable about a system design. |
architecture-doc | Produce .docx Solution Architecture Documents (SAD) with python-docx — context, requirements, views, decisions, NFRs. Use when the user asks for an architecture document, solution design document, HLD/LLD, or any .docx deliverable describing a system design. |
backend-development | Build backend systems with modern technologies, APIs, authentication, and security best practices. Use when implementing server-side logic or API endpoints. |
chrome-devtools | Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, or analyzing web performance. |
ci-cd-patterns | Design and implement CI/CD pipeline patterns for reliable, fast, and secure software delivery. Use when building or optimizing build and deployment pipelines. |
code-review | Systematic code review practices for receiving feedback, requesting reviews, and verification gates. Use when reviewing or receiving review feedback on code changes. |
container-security | Secure container images and runtime environments. Use when building Dockerfiles, scanning images, or hardening container deployments. |
databases | Work with databases (PostgreSQL, MySQL, MongoDB) for schema design, query optimization, migrations, and administration. Use when dealing with data layer concerns. |
debugging | Systematic debugging framework for investigating root causes before applying fixes. Use when encountering bugs, test failures, or unexpected behavior. |
deep-security-scan | Methodology, severity taxonomy, templates, and CI contract for a whole-repository deep security scan. Activate when running /security:deep-scan or when orchestrating the recon → find → validate → judge → report pipeline. |
devops | Deploy and manage cloud infrastructure with Docker, Kubernetes, Terraform, and CI/CD pipelines. Use when working with containers, orchestration, IaC, or cloud platforms. |
docs-seeker | Search technical documentation using automated scripts to find relevant library, framework, or tool documentation. Use when you need official docs for a specific technology. |
drawio-aws | Use 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. Builds with the declarative layout engine using ground-truth mxgraph.aws4 stencils, validates (stencils/colors/nesting/geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request. |
drawio-azure | Use when the user asks for an Azure architecture diagram — VNet/networking, App Service, AKS, landing zone, multi-region, or any diagram built with Azure service icons. Builds with the declarative layout engine using ground-truth Azure stencils, validates (stencils/colors/nesting/geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request. |
drawio-gcp | Use when the user asks for a GCP or Google Cloud architecture diagram — VPC/networking, GKE, Cloud Run, landing zone, multi-region, or any diagram built with GCP service icons. Builds with the declarative layout engine using ground-truth GCP stencils, validates (stencils/colors/nesting/geometry), runs a render-based vision self-check. Default output is .drawio; PNG/SVG only on request. |
frontend-design | Create production-grade frontend interfaces with high design quality. Use when building dashboards, admin panels, or monitoring UIs. |
kubernetes-ops | Operate and troubleshoot Kubernetes clusters, workloads, and networking. Use when deploying, scaling, or debugging Kubernetes resources. |
mcp-builder | Guide for creating MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Use when building MCP integrations. |
mcp-management | Manage MCP servers -- discover, analyze, and execute tools from configured servers. Use when working with MCP integrations or discovering available capabilities. |
media-processing | Process multimedia files with FFmpeg and ImageMagick. Use when converting formats, encoding video, manipulating images, or optimizing media files. |
mermaid-diagrams | Author Mermaid diagrams for architecture work — C4 context/container/component, sequence, deployment, flowchart, and state diagrams with copy-paste examples and CLI validation. Use when the user wants a text-based diagram, a diagram embedded in Markdown, or a quick architecture sketch. |
planning | Plan technical solutions that are scalable, secure, and maintainable. Use when you need to create implementation plans or evaluate architectural approaches. |
problem-solving | Apply systematic problem-solving techniques for complexity spirals, innovation blocks, recurring patterns, and scale uncertainty. Use when stuck or facing non-obvious challenges. |
repomix | Package code repositories into single AI-friendly files for analysis. Use when you need to understand a codebase structure or prepare context for analysis. |
research | Research and analyze technical solutions, evaluate trade-offs, and synthesize findings from multiple sources. Use before making technology decisions. |
sequential-thinking | Apply structured, reflective problem-solving for complex tasks requiring multi-step analysis and revision. Use for complex decomposition or when you need to think step by step. |
skill-creator | Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. |
template-skill | Template for creating new skills. Copy this directory and customize for your specific use case. |
terraform-modules | Design and implement reusable Terraform modules with proper interfaces, testing, and documentation. Use when creating or refactoring infrastructure modules. |
web-frameworks | Build web applications with modern frameworks (Next.js, Express, Fastify). Use when implementing web services or server-side applications. |
Workflows
Hooks
Registered in settings.json:
| Event | Hook |
|---|---|
PreToolUse | scout-block |
PreToolUse | build-verify |
PostToolUse | modularization-hook |
PostToolUse | image-scan |
agentStop | discord-notify |
agentStop | telegram-notify |
Hook scripts shipped with this preset:
| Script |
|---|
build-verify |
container-scan |
cost-estimation |
discord-notify |
git-status-tracker |
image-scan |
modularization-hook |
pre-commit-lint |
scout-block |
telegram-notify |
terraform-plan-review |
Native Kiro Agent Hooks (ship disabled; enable them in Kiro's Agent Hooks panel):
| Native hook |
|---|
container-scan |
cost-estimate |
deep-scan-stale |
docs-drift-guard |
run-tests-on-save |
secret-scan-on-save |
spec-task-sync |
terraform-plan-review |
MCP servers
| Server |
|---|
fetch |
filesystem |
git |
playwright |
Kiro Powers
Recommended Kiro Powers for this preset. init
auto-wires the credential-free MCP-backed ones and scaffolds the credentialed
ones disabled.
| Tier | Power | Description | Auth | MCP-backed |
|---|---|---|---|---|
essential | AWS CDK | Define AWS infrastructure with code | apiKey | no |
essential | Terraform | Infrastructure as code across cloud providers | apiKey | no |
recommended | Context7 | Up-to-date library and framework documentation lookup | none | yes |
recommended | Figma | Design file access for diagrams and design handoff | apiKey | no |
optional | Datadog | Metrics, logs, traces, and dashboards | apiKey | no |
optional | Snyk | Dependency and container vulnerability scanning | apiKey | no |
Example specs
Fully-written requirements.md / design.md / tasks.md trios you can read
as worked examples.