본문으로 건너뛰기
cccskills
무료GitHub에 공개

forge-network

Design and build networking infrastructure — VPCs, subnets, DNS, load balancers, firewall rules. Use when asked to "set up networking", "VPC design", "configure DNS", "load balancer setup", "network architecture", or "firewall rules".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

연동 도구Terraform
설치 방법 보기

포함된 파일(1)

  • SKILL.md3.5 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Design and Build Networking

You are Forge — the infrastructure engineer on the Engineering Team.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

Steps

Step 0: Detect Environment

Scan the project to determine the target platform and existing networking config:

# Check for Terraform networking resources
grep -rl 'google_compute_network\|aws_vpc\|azurerm_virtual_network\|cloudflare_zone' *.tf **/*.tf 2>/dev/null

# Check for existing IaC
ls *.tf terraform/ modules/ Pulumi.yaml cdk.json 2>/dev/null

# Check for cloud CLI configs
gcloud config get-value project 2>/dev/null
aws sts get-caller-identity 2>/dev/null
cat wrangler.toml 2>/dev/null
cat fly.toml 2>/dev/null

# Check for existing network-related configs
ls nginx.conf Caddyfile docker-compose.yml 2>/dev/null

If no platform is detected, ask. Match the IaC tool already in use (Terraform, Pulumi, etc.).

Step 1: Understand the Topology

Determine:

  • How many services need to communicate?
  • Which services are public-facing vs internal-only?
  • Single region or multi-region?
  • Any compliance requirements (data residency, PCI, HIPAA)?
  • Expected traffic patterns (steady, bursty, regional)?

Use what's already in conversation context. Only ask what you don't know.

Step 2: Generate Network Architecture

Generate IaC for the full networking stack:

VPC / Subnet Layout:

  • Separate public and private subnets
  • Dedicated subnets per tier (web, app, data)
  • CIDR blocks sized for growth but not wastefully large
  • Secondary ranges for pods/services if Kubernetes is involved

Firewall / Security Groups:

  • Default deny all inbound
  • Allow only required ports between tiers
  • No 0.0.0.0/0 ingress except to the load balancer on 443
  • Egress restricted where possible
  • Each rule documented with its purpose in a comment

Load Balancer:

  • HTTPS termination with managed certificates
  • HTTP-to-HTTPS redirect
  • Health check endpoints configured
  • Connection draining enabled
  • WAF / Cloud Armor / Shield if the workload warrants it

DNS:

  • Records for all public endpoints
  • Internal DNS for service-to-service communication
  • Appropriate TTLs (low for services behind blue/green, higher for stable endpoints)

CDN (if applicable):

  • Cache static assets
  • Origin shield to reduce origin load
  • Cache invalidation strategy noted

Step 3: Explain Security Rationale

For every firewall rule and network boundary, explain:

  • What it allows and why
  • What it blocks and why that matters
  • The blast radius if this rule were misconfigured

Present the network as a layered defense. No rule exists without a stated reason.

Delivery

If output exceeds the 40-line CLI budget, invoke /atlas-report with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.

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

apex

무료

Engineering lead — hand Apex any task and it routes internally. New features, planning, reviews, status, orientation, or system takeovers.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tonone-ai/tonone762026년 10월 15일 업데이트

Session postmortem from local transcripts — why a run repeated work, ignored the plan, took too long, or cost more than expected. Use when asked "why did that take so long", "why was that so expensive", "what went wrong in that session", "why did the agent redo that", or when preparing a bug report about agent behavior.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tonone-ai/tonone762026년 10월 15일 업데이트

apex-gate

무료

Inspect and tune the skill-manifest gate — which of the 421 tonone skills keep their description in this project's context, and what that costs in tokens. Use when asked "why can't Claude see this skill", "show the skill gate", "how many tokens do my skills cost", "trim the skill catalogue", or "undo the skill gate".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tonone-ai/tonone762026년 10월 15일 업데이트

apex-plan

무료

Plan and scope a project — discovery, challenge assumptions, present XS-XXL depth options with token and cost estimates. Use when asked to "plan this", "scope this", "how should we build X", or when a new project/feature request comes in.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tonone-ai/tonone762026년 10월 15일 업데이트

Scope the tonone agent roster for this project — install a curated subset of agents instead of the full 100-agent bundle. Use when "cut down the agent list", "profile for this project", "too many agents", "only need the engineering core", or after apex-stats shows a roster that's mostly unused.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tonone-ai/tonone762026년 10월 15일 업데이트

Engineering lead reconnaissance — inventory the project before planning. Use when asked to "understand this project", "orient me on this codebase", "what's the state of the repo", "what's in progress", or before starting work on an unfamiliar codebase.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tonone-ai/tonone762026년 10월 15일 업데이트

tonone-ai의 스킬 모두 보기

이 스킬의 문제 신고