Typescript Ai Native Terraform

Organization

vibevm

typescript-ai-native-terraform

Adopt the AI-Native discipline on an existing (brownfield) TypeScript codebase — inventory-not-gate, the three registries, characterization goldens, then card raids cell by cell. Use once per codebase (or to resume a partial adoption); the recurring counterpart is /typescript-ai-native-sweep.

Overview

Publisher	vibevm
Repository	`vibevm`
Skill name	`typescript-ai-native-terraform`
Stars	285
Forks	83
Bundled files	Instructions only
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by vibevm on GitHub. Read the source before you install it.

Installation

Install the Typescript Ai Native Terraform AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/vibevm/vibevm/tree/main/vibevm/vibepacks/org.vibevm.ai-native/typescript-ai-native-lang/v1.0.0/vibevm/vibespecs/skills/typescript-ai-native-terraform
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/vibevm/vibevm/tree/main/vibevm/vibepacks/org.vibevm.ai-native/typescript-ai-native-lang/v1.0.0/vibevm/vibespecs/skills/typescript-ai-native-terraform

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/vibevm/vibevm.git /tmp/vibevm
mkdir -p .claude/skills
cp -r /tmp/vibevm/vibevm/vibepacks/org.vibevm.ai-native/typescript-ai-native-lang/v1.0.0/vibevm/vibespecs/skills/typescript-ai-native-terraform .claude/skills/typescript-ai-native-terraform

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Typescript Ai Native Terraform in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Typescript Ai Native Terraform on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Typescript Ai Native Terraform is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Terraform a TypeScript codebase (brownfield adoption) {#root}

@fact:EXECUTING-THE-BROWNFIELD-PROTOCOL You are executing the BROWNFIELD protocol (spec://org.vibevm.ai-native/core-ai-native/mechanisms/BROWNFIELD-PROTOCOL-v0.1 — shipped copy under vibedeps/flow-core-ai-native/<version>/spec/mechanisms/; read it before the first phase, and skim 03-RAID-PLAYBOOK + 05-CAMPAIGN-FORM for the campaign machinery). @status:impl/done

@fact:founding-principles-lead The founding principles: @status:impl/done

@fact:PRINCIPLE-INVENTORY-NOT-GATE inventory, not gate (the only precondition is "the project type-checks or at least runs"); @status:impl/done
@fact:PRINCIPLE-ASPIRATION-MUST-BE-LABELED aspiration is legal only when labeled; @status:impl/done
@fact:PRINCIPLE-CONTRADICTION-IS-DATA contradiction is data; @status:impl/done
@fact:PRINCIPLE-CHARACTERIZATION-IS-THE-TRUTH-OF-RECORD characterization is the truth-of-record; @status:impl/done
@fact:PRINCIPLE-MONOTONE-UTILITY monotone utility. @status:impl/done

@fact:DO-NOT-BULLDOZE-AN-INHABITED-WORLD Do not bulldoze an inhabited world. @status:impl/done

@fact:TOOLCHAIN-INSTALL-OR-RUN-IN-PLACE Toolchain: typescript-ai-native (install once: cargo install --path vibedeps/<stack-slot>/crates/typescript-ai-native-cli, or run via cargo run --manifest-path vibedeps/<stack-slot>/Cargo.toml -p typescript-ai-native-cli --bin typescript-ai-native -- <args>). @status:impl/done

@fact:PROJECT-NEEDS-NODE-AND-ITS-OWN-TYPESCRIPT The project itself needs node ≥ 22.6 and its own typescript devDependency — the structural gate parses with the project's own compiler. @status:impl/done

Phase −1 — inventory (record reality; change nothing) {#phase-inventory}

@fact:INVENTORY-PRECONDITION Precondition: npx tsc --noEmit runs (errors are FINDINGS to record, not blockers) and the test runner starts. @status:impl/done
@fact:INVENTORY-INIT typescript-ai-native init — policies + empty registries. Nothing is gated yet, and that is correct. @status:impl/done
@fact:INVENTORY-TESTS-BASELINE Fill discipline/registry/tests-baseline.json with reality: run the suite once (node --test --test-reporter=tap), record every failing test as failing-known with a since date and a debt id — do NOT fix them now (drive-by repairs destroy the accounting). @status:impl/done
@fact:INVENTORY-HARVEST-INTENT Harvest intent into discipline/registry/intent.json: README roadmaps, TODO/FIXME that carry design, open issues you will honour. The carry-over guarantee: at exit every harvested intention is done | rescoped | rejected(reason) — zero unaccounted. @status:impl/done
@fact:INVENTORY-FILE-DEBT File debt into discipline/registry/debt.json: failing tests, the any/as/!/@ts-ignore hotspots typescript-ai-native health counts, missing runtime validation at erasure boundaries — each with severity, evidence, disposition, and touch: tripwires. @status:impl/done
@fact:INVENTORY-CHARACTERIZE Characterize currently-passing observable behavior (golden transcripts under discipline/golden/, normalized for volatile fields). A pinned bug is visible debt; an unpinned bug is a landmine. @status:impl/done
@fact:INVENTORY-SPECMAP typescript-ai-native specmap — mint the (initially small) index; commit the whole inventory as its own topic commits. @status:impl/done

Phase 0 — the first spec units + the tsconfig floor {#phase-first-spec-units}

@fact:PHASE-ZERO-FIRST-SPEC-DOCUMENTS Write the project's first spec/ documents for the subsystems you will touch first: anchored headings ({#req-…}), kind lines (`req r1`). Tag implementing exports as you go (/** @implements spec://<ns>/… */, or a file-level @scope); typescript-ai-native specmap after each batch keeps the index green. @status:impl/done
@fact:PHASE-ZERO-RAISE-THE-TSCONFIG-FLOOR Raise tsconfig.json toward the GUIDE §1 floor (strict, noUncheckedIndexedAccess, exactOptionalPropertyTypes, erasableSyntaxOnly) — one flag at a time; each flag's fallout is inventory (debt entries), not a fix-everything-now mandate. @status:impl/done

Phases 1…N — card raids, cell by cell {#card-raids}

@fact:raid-one-directory-at-a-time-lead Per the Raid Playbook skeleton (scope & freeze → card order → phases → acceptance), raid one directory-at-a-time toward the cell layout: @status:impl/done

@fact:RAID-CARVE-THE-CELL-LAYOUT carve src/cells/<name>/ with index.ts seams; imports cross seams only (ts-cell-isolation starts enforcing the moment cells_dir is set in conform.toml); @status:impl/done
@fact:RAID-BRAND-PRIMITIVES-AT-SEAMS brand meaning-bearing primitives at the seams (card B); validate external data at erasure boundaries through a single-source schema; @status:impl/done
@fact:RAID-DRAIN-THE-UNSAFE-SET drain the unsafe set (any → unknown+narrowing, checked as, assertion functions for !), recording the irreducible remainder as reasoned @ts-expect-error testimony; @status:impl/done
@fact:RAID-FREEZE-ONCE-PER-LANDING typescript-ai-native conform freeze once per raid landing, then the ratchet only shrinks; @status:impl/done
@fact:RAID-KEEP-THE-FLOOR-GREEN keep typescript-ai-native floor green at every raid boundary — that is the campaign's safe-stop invariant. @status:impl/done

Exit {#exit}

@fact:EXIT-CRITERIA The BROWNFIELD §8 carry-over reconciliation (zero unaccounted intent), the floor green with every step armed (an empty floor_disable), and the sweep skill (/typescript-ai-native-sweep) taking over as the recurring posture. @status:impl/done

The generation-time assistant during raids {#generation-time-assistant}

@fact:RAIDS-ARE-WHERE-THE-ORACLE-PAYS Card raids rewrite cells wholesale — exactly where the oracle pays for itself. @status:impl/done

@fact:VALIDATE-THE-DRAFT-BEFORE-IT-LANDS While drafting a cell replacement, validate the draft BEFORE it lands: vibe bin exec typescript-ai-native-tcg -- validate <file> --content-from - (or the tcg_validate MCP tool with content). @status:impl/done

@fact:NON-BASELINED-FINDING-IS-THE-RATCHET-EARLY A non-baselined ts-unsafe-in-domain or ts-cell-isolation finding in the answer is the ratchet telling you early; tcg_scope lists the branded types at the seams you are about to cross. @status:impl/done

@fact:SAFE-STOP-INVARIANT-IS-UNCHANGED The raid's safe-stop invariant is unchanged — the floor gates the landing; the oracle just makes the landing green on the first attempt. @status:impl/done

Frequently asked questions

What does the Typescript Ai Native Terraform AI skill do?

Why use Typescript Ai Native Terraform on TypingMind?

Because you install it once and use it with any model. Typescript Ai Native Terraform is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Typescript Ai Native Terraform in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vibevm/vibevm/tree/main/vibevm/vibepacks/org.vibevm.ai-native/typescript-ai-native-lang/v1.0.0/vibevm/vibespecs/skills/typescript-ai-native-terraform. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Typescript Ai Native Terraform?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Typescript Ai Native Terraform?

As many as you like. As long as a model supports skills, you can use Typescript Ai Native Terraform with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Typescript Ai Native Terraform AI skill free?

It is published on GitHub by vibevm. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Openclaw Ci Limits

openclaw

OrganizationPopular

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

Openclaw Debugging

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored…

Openclaw Live Updater

openclaw

OrganizationPopular

Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation. Use for fast-forward update…

Openclaw Pr Maintainer

openclaw

OrganizationPopular

Review, triage, repair, or land OpenClaw issues and pull requests with current-source evidence and the native maintainer workflow.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Terraform a TypeScript codebase (brownfield adoption) {#root}

Phase −1 — inventory (record reality; change nothing) {#phase-inventory}

Phase 0 — the first spec units + the tsconfig floor {#phase-first-spec-units}

Phases 1…N — card raids, cell by cell {#card-raids}

Exit {#exit}

The generation-time assistant during raids {#generation-time-assistant}

Frequently asked questions

Related AI Skills

Set up your own AI workspace now