Map requirement acceptance to proportionate executable checks and real user journeys before implementation and completion.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Read the accepted requirement, relevant business journey, risks and project check commands. Maintain the existing test strategy with criterion → check → environment → owner mappings; identify uncovered criteria before dispatch.
Choose unit checks for logic, integration checks for seams, and journey checks for the actual user entrypoint. Include relevant negative, persistence, permission, recovery and regression cases. A direct API call cannot substitute for a changed browser interaction; a health response cannot establish user acceptance. Use owned manual checks when appropriate and report their result separately from automated coverage.
For planning-only assignments, return the coverage map and commands to the assigned worker; do not execute or create fixtures. When execution is authorised within your lane, run candidate checks and record command, revision, environment, outcome and limits. For new regression guards verify a representative defect makes the check fail in an isolated fixture; do not damage a shared working tree. Avoid tests that merely repeat wording or implementation. Return uncovered acceptance to product-owner and delivery-orchestrator; never weaken a requirement to make a suite pass.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Google ADK (Agent Development Kit) orchestration patterns — boundaries, agent composition, and tool seams. Trigger when designing or reviewing multi-agent systems built on ADK. Authoritative source: adk.dev.
日本語の概要は準備中です。原文の説明を表示しています。
JP's signature red-team pass — "how would I break this?" Argue against your own approach before proceeding. Trigger on any high-stakes decision, architecture choice, or before marking work complete.
日本語の概要は準備中です。原文の説明を表示しています。
Read-only SRE checkup of any GCP project: deterministic probes of the edge, Cloud Run services, 7-day error logs, Cloud Scheduler, alert policies and uptime checks, Secret Manager and IAM, the data stores and the machine's own scheduled jobs, audited into one fixed status table (LIVE / WARNING / RED / INCONCLUSIVE) with evidence, findings by severity, what could not be checked, and a single OVERALL line delivered as one notification. Parametrised by a per-project manifest, so the same routine runs on every project. Use when the operator says "cloud checkup", "SRE check", "is everything live", "what's healthy / warning / red", "any errors this week", "audit the infra", "weekly checkup", "set up the weekly checkup", before a deploy or demo, or after an incident. Cloud Run first; App Engine and GKE differ only in the serving probes.
日本語の概要は準備中です。原文の説明を表示しています。
Cloud guardrails for any vendor workload — Google Cloud (GCP, Vertex AI, GKE), AWS (IAM, EKS, Bedrock), Azure (Entra ID, Policy, AKS), Alibaba Cloud (RAM, mainland/international residency). Enforces identity least-privilege, mechanical policy, data boundaries, residency, cost caps, network egress and observability, with official-source validation before any claim. Trigger on any cloud infrastructure design, review, Terraform plan, or LLM/agent deployment; the-architect routes here.
日本語の概要は準備中です。原文の説明を表示しています。
LLM and cloud cost awareness — model tiering, token budgets, right-sizing, and when a cheaper model suffices. Trigger before finalising any architecture that calls LLMs, before scaling a workload, or when a cost estimate is needed.
日本語の概要は準備中です。原文の説明を表示しています。
Challenge vision alignment, value, cost, risk and operating ownership at material scope or release decisions.
日本語の概要は準備中です。原文の説明を表示しています。