Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/aws-samples/sample-well-architected-skills-and-steering/llms.txt

Use this file to discover all available pages before exploring further.

OpenClaw reads AGENTS.md from your project root as always-on steering context and discovers structured skills from the .agents/skills/ directory. Installing both gives OpenClaw continuous Well-Architected awareness plus 11 step-by-step assessment playbooks it can follow whenever you request a review or assessment.

​
What gets installed

AGENTS.md

Steering context that applies all six Well-Architected pillars, surfaces trade-offs explicitly, and routes structured assessment requests to the appropriate skill playbook.

.agents/skills/ directory

Eleven skill subdirectories, each containing a SKILL.md playbook. OpenClaw follows these step-by-step when you invoke a specific review or improvement plan.

​
Installation

1

Clone or download the source repo

If you haven’t already, clone the sample repository to a local path you can reference:
git clone https://github.com/aws-samples/sample-well-architected-skills-and-steering.git
2

Copy files into your project

Run the commands below from the root of your project directory, substituting path/to/this-repo with the actual clone location.
cp path/to/this-repo/adapters/openclaw/AGENTS.md ./AGENTS.md
mkdir -p .agents/skills
cp -r path/to/this-repo/skills/* .agents/skills/
3

Verify the layout

Your project should now contain:
AGENTS.md
.agents/
  skills/
    wa-review/SKILL.md
    security-assessment/SKILL.md
    reliability-improvement-plan/SKILL.md
    cost-optimization-review/SKILL.md
    performance-efficiency/SKILL.md
    sustainability-optimization/SKILL.md
    operational-excellence/SKILL.md
    migration-readiness/SKILL.md
    architecture-decision-record/SKILL.md
    wa-builder/SKILL.md
    wa-guardrails/SKILL.md

​
Install via script

If you prefer the one-command approach from a local clone, the install script handles directory creation and copying automatically: 
./install.sh ~/my-project --tool openclaw

​
Usage

With AGENTS.md in place, OpenClaw automatically applies Well-Architected principles to architecture conversations. Trigger a specific skill by describing what you need: 
Run a Well-Architected review of this architecture.
OpenClaw reads AGENTS.md at session start and loads the matching .agents/skills/{skill-name}/SKILL.md when a structured assessment is requested.
Findings are grouped by pillar with severity labels (🔴 High Risk, 🟡 Medium Risk, 🟢 Best Practice) as directed by the steering. Start with a quick scan to locate gaps, then dive deeper into specific pillars to stay within token budgets.

​
Available skills

SkillWhat it does
wa-reviewFull 6-pillar review with prioritized findings report
security-assessmentDeep-dive into IAM, detection, data protection, incident response
reliability-improvement-planFind SPOFs, assess recovery, produce remediation plan
cost-optimization-reviewIdentify waste, right-sizing, pricing model improvements
performance-efficiencyResource selection, scaling, caching, optimization
sustainability-optimizationUtilization, architecture efficiency, carbon reduction
operational-excellenceCI/CD, observability, incident management, operational maturity
migration-readiness7 Rs assessment, dependency analysis, migration plan
architecture-decision-recordADR with WA pillar impact analysis
wa-builderLearn WA for your workload and generate visual artifacts
wa-guardrailsGenerate preventive controls (Config rules, SCPs, CI checks)

Build docs developers (and LLMs) love

Get started for freeTalk to us