opensite-ai/opensite-skills / aws-well-architected-review
aws-well-architected-review
VerifiedPerforms 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.
| File | Kind | Size |
|---|---|---|
| .aws-skill-metadata | other | 18 B |
| SKILL.md | skill md | 12.5 KB |
| assets/report-template.md | markdown | 6.6 KB |
| references/discovery-procedure.md | markdown | 3.5 KB |
| references/evaluation-procedure.md | markdown | 11.8 KB |
| references/lens-guidance.md | markdown | 2.1 KB |
| references/phase-live-inventory.md | markdown | 11.3 KB |
| references/review-modes.md | markdown | 3.1 KB |
| references/risk-assessment.md | markdown | 1.6 KB |
| references/security-considerations.md | markdown | 5.4 KB |
references/review-modes.md
View on GitHub# Review Modes — Mode Selection, Trigger Phrases, and Output Formats
Determine the review mode from the user's request before starting the evaluation.
## Full review
Default when the user says "WA review", "full review", "comprehensive":
- Evaluate every framework question in the frozen manifest produced by `ACQUIRE_CORPUS` (see [phase-live-inventory.md](phase-live-inventory.md)) — the enumeration is acquired and frozen once; do NOT re-fetch or rebuild the question/BP list during assessment
- Assess each pillar against its frozen-manifest BP set using the per-pillar pass pattern (see the evaluation procedure reference)
- Cite the specific canonical BP IDs from the frozen manifest in findings
## Quick review
When the user says "quick review", "high-level", "summary", or is time-constrained:
- Evaluate all framework questions at the QUESTION level only (do not fetch individual BP pages)
- Use the live Step 5a question inventory to assess each question based on what you find in the code
- Flag obvious gaps but do not exhaustively check every BP
- Faster, less detailed, still covers all pillars
- Prefix the output with the same `> **Classification: CONFIDENTIAL** — …` banner the full report template uses — a quick review still surfaces sensitive infrastructure detail and unremediated findings
## Pillar-scoped review
When the user asks for one or more specific pillars by name or by the documented scope of their questions:
- Evaluate ONLY the questions for the requested pillars
- Derive the requested pillars' questions and best practices from the frozen manifest (the `ACQUIRE_CORPUS` output), filtered by `pillar_id` — do NOT re-walk the documentation or use semantic search to re-enumerate them (that reintroduces the traversal-stall path the frozen-manifest redesign removed). Read an individual BP's detail page at its manifest `bp_url` only when the BP's title plus the workload evidence is insufficient to judge status; prefer `aws___read_documentation`, otherwise an HTTPS fetch of that `docs.aws.amazon.com` URL, otherwise internal knowledge with disclosure
- Apply full-review BP-level detail for those pillars
- Skip all other pillars entirely — do not comment on them unless a critical cross-pillar issue is obvious
- Produce a pillar-focused report whose scorecard categories come from the requested pillars' live question inventory
- Prefix the output with the same `> **Classification: CONFIDENTIAL** — …` banner the full report template uses — a pillar-scoped review still surfaces sensitive infrastructure detail and unremediated findings
After building the Step 5a inventory, map the user's phrasing to the discovered pillar names based on each pillar's live documented scope, questions, and keywords. If the request could map to multiple pillars, ask the user to confirm the intended scope.
## When the mode is unclear
Ask:
> Would you like a **full review** (deep BP-level analysis per question — thorough but longer), a **pillar-scoped review** (full BP-level detail for only the pillars you name), or a **quick review** (question-level assessment — faster)?
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 119k | Updated | Claude CodeCodex | Verified | Install |
| 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: 118k | Updated | Claude CodeCodex | Verified | Install |