Skip to content

opensite-ai/opensite-skills / aws-well-architected-review

aws-well-architected-review

Verified

Performs a full AWS Well-Architected Framework review evaluating every framework question across all pillars discovered from the live AWS documentation by analyzing code, IaC, and configurations to produce evidence-backed findings with Eisenhower-prioritized remediation. Supports full reviews (every framework best practice with BP ID citations), quick reviews (question-level), pillar-scoped reviews, and lens-specific reviews using lenses discovered from the live AWS documentation. Triggers on mentions of Well-Architected review, WA review, WAR, WAFR, pillar assessment, architecture review, workload assessment, or cloud readiness evaluation. Does not apply to learning WA concepts without assessing a workload, ADRs, or migration readiness assessments.

references/lens-guidance.md

View on GitHub
# Lens Guidance — Applying Well-Architected Lenses

Lenses are **additive** — they expand the core framework questions with domain-specific best practices. They do NOT replace the framework questions.

## When to apply a lens

- The workload clearly matches the documented scope of a lens discovered from the live AWS documentation
- The user explicitly asks for a lens-specific review

## How to apply

Use this retrieval ladder for every lens lookup:

1. Use `aws___search_documentation` / `aws___read_documentation` when the AWS MCP server is available.
2. Otherwise, use the environment's web-search or web-fetch tool only over HTTPS against `docs.aws.amazon.com`. Do not use plain HTTP or retrieve lens guidance from other domains.
3. If no documentation access exists, proceed from internal knowledge and disclose that limitation.

- First complete the core framework evaluation (every framework question)
- Then fetch the lens documentation at review time using the retrieval ladder. Search for `AWS Well-Architected {lens name} Lens`, read the lens's per-pillar best-practice pages, and evaluate the additional lens-specific best practices
- Report lens findings in a separate section after the core findings

**If the user ONLY asks for a named lens review**, that is also valid. Verify the lens name against the live documentation, then fetch only that lens's documentation and evaluate against it. Prefix the standalone lens report with the same `> **Classification: CONFIDENTIAL** — …` banner the other review modes use — a lens review still surfaces sensitive infrastructure detail and unremediated findings.

## Discover available lenses

Do not rely on a hardcoded lens inventory. At review time, use the retrieval ladder to search for `AWS Well-Architected Lenses` and locate the lenses landing page, then use the published documentation as the authoritative list of available lenses and their current names. If no documentation access exists, use internal knowledge and disclose that the available-lens list could not be verified live. Treat workload characteristics as signals to search for a relevant lens, not proof that a particular lens exists.
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 323kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall