본문으로 건너뛰기
cccskills
무료GitHub에 공개

well-arch-reliability

Review local git changes or an architecture document against the Reliability pillar of Google's Cloud Well-Architected Framework. Identifies gaps across 8 principles (SLOs aligned to UX, recovery targets, HA via redundancy, horizontal scalability, observability, graceful degradation, tested recovery, postmortems), and for each non-trivial risk asks the user to decide Accept / Mitigate / Defer / Block — producing a documented risk register, not just a finding list. GCP-principle-based but cloud-agnostic. Use when the user asks for a reliability review, resilience / SRE review, SLO assessment, failure-mode analysis, or recovery readiness check. Trigger phrases include "well architected reliability", "GCP reliability review", "reliability pillar review", "SLO review", "resilience review", "信頼性レビュー", "Well-Architected 信頼性", "可用性レビュー", "障害耐性レビュー".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hideki5123/agent-skill-set
연동 도구Google Cloud

실행 점수 미검증

설치 방법 보기

포함된 파일(4)

  • SKILL.md5.6 KB
  • references/reliability-review-guide.md9.1 KB
  • references/report-template.md2.3 KB
  • references/risk-decision-protocol.md2.9 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Well-Architected Reliability Review

Review changes or an architecture doc against Google's Cloud Well-Architected Reliability pillar. Surface risks, then ask the user to make an explicit Accept / Mitigate / Defer / Block decision per risk.

Arguments

ArgumentDefaultDescription
--staged-onlyfalseReview only staged changes (git diff --cached)
--doc <path>noneReview an architecture document instead of git diff
--filenoneWrite report to well-arch-reliability-YYYY-MM-DD-HHmm.md

Workflow

1. Collect Input ──► 2. Read Context ──► 3. Pillar Analysis
                ──► 4. Risk Decision Loop ──► 5. Report

Phase 1: Collect Input

If --doc <path> is set, read the document. Otherwise gather local changes:

# Staged changes (always collected)
git diff --cached

# Unstaged changes (skip if --staged-only)
git diff

# Untracked files (skip if --staged-only)
git status --porcelain | grep '^??'

If all produce empty results (or the doc is empty / missing), inform the user "Nothing to review." and exit.

Phase 2: Read Context

For each changed file (or referenced section of the doc), read the full content. Skim related context that informs reliability: IaC files, service manifests, autoscaling / HPA config, retry / circuit-breaker libraries in use, observability config (dashboards, alerts), runbooks, and any existing SLO definitions.

Phase 3: Pillar Analysis

Walk the 8 principles in references/reliability-review-guide.md. For each principle, use the review questions to identify findings. Tag each finding with severity (Critical / Important / Nice-to-have) and an ID prefix R-:

  • Critical → R-C1, R-C2, ...
  • Important → R-I1, R-I2, ...
  • Nice-to-have → R-N1, R-N2, ...

Phase 4: Risk Decision Loop

Read references/risk-decision-protocol.md. For every Critical and Important finding, call AskUserQuestion with the 4-option decision: Accept / Mitigate / Defer / Block. Nice-to-have findings are listed in the report without prompting. Batch up to 4 findings per AskUserQuestion call.

Capture each decision and any free-text rationale into the risk register.

Phase 5: Report

Render the report from references/report-template.md. If --file is set, write to well-arch-reliability-YYYY-MM-DD-HHmm.md in the current working directory and confirm the path. Otherwise present the report inline.

The overall verdict is Hold if any Critical risk was Blocked, Proceed with caveats if any risk was Accepted or Deferred, otherwise Proceed.

Behavior Scenarios

Scenario: Git mode review with risk prompts
  Given the user has local changes
  When /well-arch-reliability is invoked
  Then changes are analyzed against the 8 reliability principles
  and the user is asked Accept/Mitigate/Defer/Block per Critical or Important risk
  and a report with a populated risk register is presented

Scenario: Architecture document review
  Given the user has an architecture doc at docs/architecture.md
  When /well-arch-reliability --doc docs/architecture.md is invoked
  Then the document is analyzed against the 8 reliability principles
  and the same risk decision loop and report flow runs

Scenario: Staged-only review
  Given the user has staged changes ready to commit
  When /well-arch-reliability --staged-only is invoked
  Then only staged changes are analyzed

Scenario: Write report to file
  Given the user wants a persistent record
  When /well-arch-reliability --file is invoked
  Then the report is written to well-arch-reliability-YYYY-MM-DD-HHmm.md
  and the file path is confirmed

Scenario: All risks accepted
  Given findings exist and the user selects Accept for every risk
  When the report is rendered
  Then the verdict is "Proceed with caveats"
  and each accepted risk is captured in the risk register

Scenario: One risk blocked
  Given the user selects Block on at least one Critical finding
  When the report is rendered
  Then the verdict is "Hold"

Scenario: Nothing to review
  Given no local changes and no --doc argument
  When /well-arch-reliability is invoked
  Then the user is told "Nothing to review." and the skill exits

References

  • references/reliability-review-guide.md — 8 reliability principles with focus, review questions, output format, and severity guidance per principle
  • references/risk-decision-protocol.md — how to drive AskUserQuestion per risk and capture decisions into the register
  • references/report-template.md — exact markdown format including the risk register and overall verdict

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

adversarial-panel

무료

Run a multi-model adversarial mutual review with facilitator synthesis: 2+ panelists (different model families where possible — use codex-server / codex-cli for the external-family seat) independently answer, adversarially critique each other across rounds, and the main session acts as facilitator, synthesizing agreements, live disagreements, and calibrated confidence into one answer. Use ONLY on high-stakes, hard-to-reverse claims, designs or decisions, and only when the user EXPLICITLY asks to debate or adversarially review with multiple models — "discuss with Opus and Codex", "red-team this", "devil's advocate", 敵対的レビュー, 相互レビュー, 多モデル討論, 議論させて. A full run costs ~6 subagent/CLI dispatches: state the panel size and round count and get a go-ahead before launching. Where the Workflow tool is available, run the panel as a Workflow (judge-panel / adversarial-verify) instead of ad-hoc fan-out. Do NOT self-trigger on a bare "are you sure?" — that is a cue to OFFER the panel, not to run it.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hideki5123/agent-skill-set22026년 10월 21일 업데이트

agent-swarm

무료

Orchestrate multiple coding-agent sessions (Claude Code, Codex, Gemini) over the mcp_agent_mail MCP server, observe their progress on a recurring auto-loop, and prevent inconsistencies (file/edit conflicts and contradictory decisions) between concurrent tasks. Auto-manages the agent-mail server, derives the shared room key from the git repo, and runs either as the orchestrator/observer or as a participating worker. Handles the operational details (server startup, room key, reservation conventions) so the user does not have to remember them. Use when coordinating several agent sessions on different tasks at once, watching a swarm of sessions for conflicts, or wiring already-running sessions into a shared coordination room. Trigger phrases: "agent-swarm", "/agent-swarm", "orchestrate agents", "orchestrate multiple claude sessions", "coordinate sessions", "watch for conflicts between agents", "observe the swarm", "prevent inconsistency between sessions", "multi-agent observe", "複数セッションを協調", "エージェント協調", "セッション間の不整合監視", "スウォーム監視", "複数のClaudeを束ねて".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hideki5123/agent-skill-set22026년 10월 21일 업데이트

agents-init

무료

Generate AGENTS.md (cross-tool agent context — Codex CLI, Aider, Cursor, etc.) and wire CLAUDE.md as a symlink so Claude Code reads the same file. Delegates content generation to Claude's built-in /init when needed, then renames + symlinks. Idempotent. Triggers — /agents-init, "generate agents.md", "create agents.md", "share claude and codex context", "set up agents file", "init agents", "agents-init", "cross-tool agent context", "wire claude and agents".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hideki5123/agent-skill-set22026년 10월 21일 업데이트

chrome-use

무료

Drive an already-running, LOGGED-IN Chromium browser on macOS via AppleScript — navigate, click, fill forms, scroll, and extract page content from the user's REAL session, with the browser left open and NO profile copy and NO restart. Use when the task needs the existing logged-in session (cookies, auth, current tabs) reused as-is. Trigger phrases: "chrome-use", "ブラウザから取得", "ログイン済みの Chromeで", "ブラウザを操作して", "このページ読んで", "Xのスレッド読んで", "ログインしたまま取得", "自分のセッションでスクレイプ", "read this page in my browser", "scrape with my session", "drive my chrome", "execute JS in my (logged-in) browser", "automate my logged-in browser". Chromium family (Chrome default; Brave/Edge/Arc/Vivaldi via --app). NOT for isolated/throwaway automation where login reuse is unneeded — use playwright-cli for that. macOS only.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hideki5123/agent-skill-set22026년 10월 21일 업데이트

codex-cli

무료

Run OpenAI Codex CLI from the terminal for batch / one-shot `codex exec` invocations with output captured to an `-o` file. Use for fire-and-forget runs, scripted CI, code review batches (`codex review`), and resuming a specific session by id (`codex exec resume`). Always use this skill instead of `mcp__codex__codex` and `mcp__codex__codex-reply` MCP tools — CLI is faster and more capable. For streaming UX, multi-turn dialogues that need live state, structured (JSON schema) output, attaching images, or programmatic event handling → **use codex-server instead**. codex-server uses the user's ChatGPT subscription via Codex App Server and decoupled async invocation that bypasses the Bash 2-minute timeout entirely. Trigger patterns (batch-only — chat/streaming triggers belong to codex-server): codex-cli / codex CLI / codex exec / codex review / codex resume / codex fork / batch + {codex, gpt} / one-shot + {codex, gpt} / non-interactive + codex / codex {to a file, -o, output file, captured output} / CI + {codex, gpt} / scripted + {codex, gpt} / fork codex session / resume codex session by id

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hideki5123/agent-skill-set22026년 10월 21일 업데이트

codex-server

무료

Run OpenAI Codex via the Codex App Server (JSON-RPC-over-stdio) for streaming multi-turn chat sessions with persistent threads, structured output, image input, and rich event streams. Default entry point for ChatGPT/GPT/Codex-like conversations from the terminal. Uses the user's ChatGPT subscription (Plus / Pro / Team) exclusively via `codex login` — never consumes OPENAI_API_KEY billing, by design. Implementation: TypeScript on deno with npm:@openai/codex-sdk; spawns the existing system codex binary. Decoupled async invocation: every turn returns turn-id in <1 s; the actual SDK work runs in a detached worker that streams to per-turn files under ~/.codex-server/turns/<turn-id>/ — Bash's 2-min timeout never applies. Prefer this over codex-cli for streaming UX, multi-turn dialogues that need live state, structured (JSON schema) output, attaching images, or programmatic event handling. Use codex-cli only for one-shot batch invocations that pre-capture to an -o file. For OpenAI Platform API calls specifically (embeddings, image generation, audio, moderation, batches, files) — not open-ended chat — use openai-cli instead; that path bills OPENAI_API_KEY, this one uses the ChatGPT subscription. Trigger patterns (match any variation): codex / codex-server / codex app server / codex app-server / openai / open ai / OpenAI / chatgpt / chat gpt / ChatGPT / GPT / ask gpt / chat with gpt / gpt session / codex session / streaming chat / multi-turn chat / multi turn chat / second opinion / cross-check / cross check / ai pair programming / another AI / external AI / ask another model / get GPT's take / what does openai think / show me what gpt thinks / structured output from gpt / json schema gpt / resume codex thread / continue codex conversation / continue codex session / /codex-server

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hideki5123/agent-skill-set22026년 10월 21일 업데이트

hideki5123의 스킬 모두 보기

이 스킬의 문제 신고