跳到正文
cccskills
免费在 GitHub 公开

terrashark

Prevent Terraform/OpenTofu hallucinations by diagnosing and fixing failure modes: identity churn, secret exposure, blast-radius mistakes, CI drift, and compliance gate gaps. Use when generating, reviewing, refactoring, or migrating IaC and when building delivery/testing pipelines.

中文简介正在准备中。当前显示原文说明。

集成工具Terraform
查看安装方法

包含的文件(73)

  • SKILL.md3.3 KB
  • .claude-plugin/marketplace.json371 B
  • .claude/settings.local.json66 B
  • .github/CODEOWNERS16 B
  • .github/dependabot.yml346 B
  • .github/FUNDING.yml23 B
  • .github/PULL_REQUEST_TEMPLATE.md1007 B
  • .github/workflows/deploy-docs.yml1.1 KB
  • .github/workflows/stale.yml1.4 KB
  • .github/workflows/validate.yml2.9 KB
  • .gitignore27 B
  • assets/logo.png193.3 KB
  • CHANGELOG.md18 B
  • CODE_OF_CONDUCT.md943 B
  • CONTRIBUTING.md1.7 KB
  • docs/.gitignore21 B
  • docs/advanced/comparison.md3.6 KB
  • docs/advanced/token-efficiency.md3.1 KB
  • docs/architecture/backend-state-safety.md4.5 KB
  • docs/architecture/coding-standards.md3.6 KB
  • docs/architecture/module-architecture.md3.0 KB
  • docs/architecture/structure-and-state.md2.1 KB
  • docs/book.json660 B
  • docs/changelog.md837 B
  • docs/contributing.md2.1 KB
  • docs/core-concepts/failure-modes.md4.9 KB
  • docs/core-concepts/philosophy.md6.4 KB
  • docs/core-concepts/workflow.md4.9 KB
  • docs/examples/bad-patterns.md2.7 KB
  • docs/examples/do-dont-checklist.md3.3 KB
  • docs/examples/good-patterns.md3.5 KB
  • docs/examples/neutral-patterns.md1.9 KB
  • docs/failure-modes/blast-radius.md2.3 KB
  • docs/failure-modes/ci-drift.md3.9 KB
  • docs/failure-modes/compliance-gates.md3.4 KB
  • docs/failure-modes/identity-churn.md4.0 KB
  • docs/failure-modes/secret-exposure.md2.9 KB
  • docs/getting-started/installation.md4.0 KB
  • docs/getting-started/quick-start.md2.4 KB
  • docs/guides/ci-delivery.md4.8 KB
  • docs/guides/migration-playbooks.md2.7 KB
  • docs/guides/quick-ops.md3.5 KB
  • docs/guides/security-governance.md2.0 KB
  • docs/guides/testing.md3.5 KB
  • docs/integrations/mcp-integration.md1.4 KB
  • docs/package-lock.json101.3 KB
  • docs/package.json323 B
  • docs/README.md3.3 KB
  • docs/SUMMARY.md1.7 KB
  • LICENSE1.1 KB
  • PHILOSOPHY.md9.6 KB
  • README.md22.6 KB
  • references/blast-radius.md1.8 KB
  • references/ci-delivery-patterns.md5.0 KB
  • references/ci-drift.md3.6 KB
  • references/coding-standards.md3.5 KB
  • references/compliance-gates.md3.0 KB
  • references/conditional/backend-state-safety.md4.7 KB
  • references/conditional/trusted-modules.md4.8 KB
  • references/do-dont-patterns.md3.1 KB
  • references/examples-bad.md2.2 KB
  • references/examples-good.md3.2 KB
  • references/examples-neutral.md1.6 KB
  • references/identity-churn.md3.8 KB
  • references/mcp-integration.md1.4 KB
  • references/migration-playbooks.md2.5 KB
  • references/module-architecture.md2.5 KB
  • references/quick-ops.md3.9 KB
  • references/secret-exposure.md2.5 KB
  • references/security-and-governance.md1.7 KB
  • references/structure-and-state.md1.9 KB
  • references/testing-matrix.md3.4 KB
  • references/token-balance-rationale.md713 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Terrashark: Failure-Mode Workflow for Terraform/OpenTofu

Run this workflow top to bottom.

1) Capture execution context

Record before writing code:

  • runtime (terraform or tofu) and exact version
  • provider(s), target platform, and state backend
  • execution path (local CLI, CI, HCP Terraform/TFE, Atlantis)
  • environment criticality (dev/shared/prod)

If unknown, state assumptions explicitly.

2) Diagnose likely failure mode(s)

Select one or more based on user intent and risk:

  • identity churn: resource addressing instability, refactor breakage
  • secret exposure: secrets in state, logs, defaults, artifacts
  • blast radius: oversized stacks, weak boundaries, unsafe applies
  • CI drift: version mismatch, unreviewed applies, missing artifacts
  • compliance gate gaps: missing policies/approvals/audit controls

3) Load only the relevant reference file(s)

Primary references:

  • references/identity-churn.md
  • references/secret-exposure.md
  • references/blast-radius.md
  • references/ci-drift.md
  • references/compliance-gates.md

Supplemental references (only when needed):

  • references/testing-matrix.md
  • references/quick-ops.md
  • references/examples-good.md
  • references/examples-bad.md
  • references/examples-neutral.md
  • references/coding-standards.md
  • references/module-architecture.md
  • references/ci-delivery-patterns.md
  • references/security-and-governance.md
  • references/do-dont-patterns.md
  • references/mcp-integration.md

Conditional references (CRR; load only on detected signals):

  • references/conditional/backend-state-safety.md (backend is s3, azurerm, gcs, remote, cloud, pg, consul, or local, or task mentions backend migration, locking, state backup, or restore)
  • references/conditional/trusted-modules.md (provider is aws, azurerm, google, oci, or ibm)

Do not load multiple conditional references unless the task spans multiple detected backends, providers, or tools.

4) Propose fix path with explicit risk controls

For each fix, include:

  • why this addresses the failure mode
  • what could still go wrong
  • guardrails (tests, approvals, rollback)

5) Generate implementation artifacts

When applicable, output:

  • HCL changes (typed vars, stable keys, bounded versions)
  • migration blocks (moved, import strategy)
  • CI pipeline updates (plan/apply separation, artifacts, policy checks)
  • compliance controls (approvals, policy rules, evidence paths)

When a trusted registry module covers the requested resource and the user has not asked for raw HCL, default to that module with an exact version pin (see references/conditional/trusted-modules.md).

6) Validate before finalize

Always provide command sequence tailored to runtime and risk tier. Never recommend direct production apply without reviewed plan and approval.

7) Output contract

Return:

  • assumptions and version floor
  • selected failure mode(s)
  • chosen remediation and tradeoffs
  • validation/test plan
  • rollback/recovery notes for destructive-impact changes

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

报告此技能的问题