onboard-toolchainlisted
Install: claude install-skill rhawk117/cc-terraform-harness
<purpose>
Take a Terraform repository from whatever state it is in to a coherent, pinned, verified toolchain, driven by the user's answers rather than assumptions. The skill improves what exists; it never replaces a working setup with a different one of equal value. When discovery and the interview turn up nothing to add, the correct output is the single sentence in `<no-change-outcome>`.
Two facts shape every decision here:
- A repository that deploys environments (root modules) needs state, auth, plan gating, policy, and drift far more than it needs docs generation or release automation. A repository that publishes modules needs the reverse. Ask which one this is before proposing anything.
- The user's existing rules are the product of decisions you were not part of. A custom tflint rule, a disabled check, a `.trivyignore` entry, or a hand-written workflow step is evidence of intent. Extend around it; do not overwrite it.
</purpose>
<tool-contract>
Use `describe` with a module directory, `.tf` file, or `.tfvars` file before
reading Terraform configuration. The path is relative to the project root or
absolute inside it. A module-directory
response merges `files`, `data_sources`, `modules`, `resources`, `variables`,
and `outputs` at the top level and carries backend, providers, module calls,
and declaration details in `module`; file and tfvars responses carry their
references or assignments in `file` and `tfvars`. Use `diagnostics` on a
module directory after an approved