Agent skill · Code Review & Quality

wafr-facilitator

Help a facilitator run a conversational Well-Architected Framework Review (WAFR) with a customer — generates tailored facilitator questions, probing follow-ups, and "things to look out for" per WA question and best practice, adapted to the workload context.

AWS Samples169★ · 1 repos on radarProfile →
claude-codeclinecodexcursorcopilotwindsurfMIT-0
Install
npx skills add aws-samples/sample-well-architected-skills-and-steering --skill wafr-facilitator --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 4
SKILL.md size: 20 KB
Bundled scripts: none
Version: 1.0.0
Path: skills/wafr-facilitator/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 233
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# WAFR Facilitator Guide You are a Well-Architected review facilitation coach. Your job is to help a facilitator prepare for and run a **conversational WAFR** with a customer — generating context-adapted questions, probing follow-ups, red flags to watch for, and guidance on interpreting answers. You do NOT perform the review yourself. You produce facilitator-ready material that a human uses in a live conversation with stakeholders. ## Step 1: Understand the workload context **IMPORTANT — DO NOT ask questions if context is already provided.** If the facilitator's message already includes workload details (name, tech stack, services, architecture description, or a diagram), **skip all discovery prompts** and proceed directly to Step 2 pre-assessment. Only use checkbox-style discovery when the initial message is vague and lacks workload context. Accept context in ANY of these forms — use whatever the facilitator provides: 1. **Architecture diagram** (image) — extract components, services, data flows, trust boundaries, and external dependencies directly from the diagram. Identify the workload type, tech stack, and potential risk areas from what you see. 2. **Text description** — worklo

What's inside
Steps it walks through
  1. Step 1: Understand the workload context
  2. Step 2: Architecture pre-assessment (per-pillar lenses)
  3. 2a. Data flow map
  4. 2b. Reliability — SEEMS + FMEA analysis
  5. 2c. Security — Threat surface walkthrough
  6. 2d. Operational Excellence — ORR readiness assessment
  7. 2e. Performance Efficiency — Bottleneck & mechanical sympathy analysis
  8. 2f. Cost Optimization — Cost signal analysis
  9. 2g. Sustainability — Utilization & efficiency audit
  10. 2h. How this feeds the review
  11. Step 3: Set up the facilitation session
  12. Step 4: Generate facilitator questions per WA question
  13. Step 5: Load reference material for depth
  14. Step 6: Handle "during the session" requests
Ships with 3 files
  • evals/evals.json
  • evals/triggering.json
  • metadata.json
More from sample-well-architected-skills-and-steering
All skills →
About this skill
What does the wafr-facilitator skill do?

Help a facilitator run a conversational Well-Architected Framework Review (WAFR) with a customer — generates tailored facilitator questions, probing follow-ups, and "things to look out for" per WA question and best practice, adapted to the workload context.

How do I install it?

Run `npx skills add aws-samples/sample-well-architected-skills-and-steering --skill wafr-facilitator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From aws-samples/sample-well-architected-skills-and-steering, a repository with 233 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going