More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    AWS Well-Architected Report Agent Team

    0

    Read-only AWS scan by a Claude Code agent team → four-pillar Well-Architected report, written in Traditional Chinese.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    AWS Well-Architected Report Agent Team

    Example session with this skill installed

    /report-aws 2026-06

    • Read your context and instructions
    • Compiled the aws well-architected report
    • Generated the document

    /report-aws 2026-06 完成

    全程唯讀、無人值守跑完六個階段(掃描 → 四支柱並行 → 彙整 → HTML → 連結檢查 → 存檔)。

    以下為遮罩示意版:帳號 ID 已遮罩,資源名稱與網域已替換為示意名稱。

    • 期別:2026-06(成本窗 2026-04 ~ 2026-06,MONTHLY)
    • 帳號:1234****5678 區域:us-east-1(全域資源另以 global 擷取)
    • 掃描日期:2026-07-24

    四支柱評分

    支柱分數高中低
    安全性 Security2 / 5562
    可靠性 Reliability3 / 5132
    效能效率 Performance4 / 5013
    成本最佳化 Cost2 / 5154
    合計71511

    最優先處理的五件事

    關閉正式資料庫的公網暴露(SEC-03、SEC-11):app-db-prd 設為 PubliclyAccessible,所在的「private」子網實際有 0.0.0.0/0 → IGW 路由(由 network-facts.py 確定性算出)。
    2. 封鎖 S3 資料桶公開存取(SEC-04):3 個 bucket 的 Public Access Block 四項全關。
    3. root 與所有使用者啟用 MFA、開啟 CloudTrail(SEC-01、SEC-02):帳號零稽核軌跡。
    4. 建立監控告警(REL-01):全帳號零 CloudWatch 告警、零 SNS 主題。
    5. 整併重複的 ALB 並清理孤兒資源(COST-01、COST-07):6→2 台 ALB +刪除 2 個孤兒 WAF ACL,約省 $76/月。

    成本

    已盤點結構性節省約

    $126/月(約佔月均帳單 36%);另有 RDS RI/Savings Plan 空間待 Cost Explorer 核實。覆蓋率自檢標出 cloudformation/glue/servicediscovery 有計費但未掃明細。

    連結檢查

    每項建議都附 AWS 官方文件連結,由 check-links.sh 驗證;若有失效連結會在此列出並提示更新 references/ 目錄檔。

    產出檔

    • report/aws-report.html(確定性 HTML,版型逐月固定)
    • report/AWS架構報告.md、report/report-data.json
    • 已存檔至 archive/2026-06/

    下一步:對外分享請執行 node .claude/skills/report-aws/scripts/build-report.js --masked(殘留帳號 ID、金鑰、ARN、私有 IP、Email 即拒絕輸出);需要架構圖可再跑 /aws-diagram。

    shot-overview

    aws-report.html

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Output language: Traditional Chinese (AWS service names kept in English).

    Type /report-aws in Claude Code and a team of six agents scans your real AWS account, analyzes it against the four AWS Well-Architected pillars, and writes a Markdown + HTML architecture report — unattended, from start to finish.

    • Read-only guarantee — only describe-* / list-* / get-* APIs. Designed for an IAM identity with ReadOnlyAccess, backed by a deny list for write verbs and a PreToolUse hook that blocks aws commands with shell expansions.
    • Evidence-driven — every finding cites the actual scan data. Cross-file facts (e.g. whether RDS sits in a subnet routed to an IGW) are computed by scripts, not guessed by the LLM. A coverage self-check flags services you are billed for but that were not scanned.
    • Four pillars in parallel — Security, Reliability, Performance Efficiency, and Cost Optimization agents run concurrently; a report-writer agent consolidates them. Every recommendation links to official AWS documentation, and links are validated by script.
    • Deterministic HTML — the HTML report is rendered from a frozen template + structured data without an LLM, so layout and sections are identical every month and reports are comparable over time. Swappable color themes.
    • Masked report for sharing — reports are unmasked by default for internal use; --masked builds an external-sharing version and refuses to output it if any 12-digit account ID, access key, ARN, private IP, or email address slips through.
    • Optional draw.io architecture diagram — /aws-diagram turns the same scan data into a multi-page, subnet-level .drawio topology, deterministically generated with count assertions.
    • Period archive — each report is archived per period for cross-period regression comparison.

    Requirements

    • Claude Code
    • AWS CLI v2, jq, python3, Node.js
    • AWS credentials — an IAM identity with ReadOnlyAccess is strongly recommended
    • Install the whole project (.claude/ + CLAUDE.md) at the project root — this is a multi-agent project, not a single skill. See README.en.md.

    Reports are generated in Traditional Chinese only. Built for Claude Code (relies on subagents, settings.json permissions and a PreToolUse hook); other agents may not support these. Requires AWS CLI credentials, ideally ReadOnlyAccess. Diagrams are script-generated; manual edits to output files are overwritten on rerun.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 26 days ago

    Requires

    Amazon
    Claude Code
    AWS CLI v2
    jq
    python3
    Node.js
    Git

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables

    Allowed Hosts

    aws.amazon.com

    Shell: runs read-only AWS CLI calls (describe/list/get only) plus local jq/python3/node scripts. Network: AWS APIs and an AWS docs link check. Files: writes only to data/, findings/, report/, archive/ inside the project. Use AWS credentials with the ReadOnlyAccess policy.

    Listed26 days ago

    What's inside

    Frequently Asked Questions

    Claude Code, AWS CLI v2, jq, python3 and Node.js, plus AWS credentials. An IAM identity with the ReadOnlyAccess managed policy is strongly recommended — the read-only guarantee is enforced at the IAM layer, and the project's deny list and hook are extra safeguards.

    The diagram is generated by a deterministic script, not drawn by the LLM: the same scan data always produces the same .drawio file, and a built-in assertion checks that the number of shapes drawn equals the number of resources in the source JSON.

    Yes, the agent supports cross-region scanning. It can aggregate metadata for VPCs, EC2, RDS, and other resources across multiple regions to provide a consolidated Well-Architected report and a multi-page diagram.

    The complete project: 6 agent definitions, the /report-aws and /aws-diagram skills, scan/digest/report/diagram scripts, the frozen HTML template and color themes, verified AWS documentation link catalogs, settings.json with allow/deny lists and the PreToolUse hook, CLAUDE.md, and English + Traditional Chinese READMEs.

    Scanning is read-only and raw scan data stays in the local data/ folder (gitignored). The creator never receives your data; scan output is only read by Claude within your own Claude Code session. Use --masked to produce a sanitized report before sharing externally.

    While the report generation is automated, the findings are exported in standard Markdown and HTML formats. This allows your team to easily add manual annotations, executive summaries, or custom business context before presenting to stakeholders.

    New in DevOps & Cloud