# weft-ai-language

Teaches coding assistants to write Weft workflows, connect typed LLM nodes, and manage human checkpoints with Restate.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 418 installs · ★ 88
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/weft-ai-language/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/weft-ai-language

## What it does

This skill equips your coding agent to build programs in Weft. Written in Rust, Weft treats language models, human input, APIs, and databases as native nodes. The compiler verifies every typed port connection before execution starts.

Workflows run on top of Restate for durable checkpoints. Crashes or multi-day pauses inside `HumanQuery` steps will not wipe running state. The local environment includes a SvelteKit dashboard accessible at `http://localhost:5173` alongside the backend services.

Running the stack requires Docker for PostgreSQL, plus Bash 4 or newer on macOS. Environment tokens like `OPENROUTER_API_KEY` live in `.env`. They are not checked on boot, so missing tokens only break execution once that specific node runs.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill weft-ai-language -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/weft-ai-language/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/weft-ai-language/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill weft-ai-language -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/weft-ai-language/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill weft-ai-language -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/weft-ai-language/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/trending-skills weft-ai-language
```

2. **Manually: put the files in place**
- File: `.github/skills/weft-ai-language/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill weft-ai-language -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/trending-skills --path skills/weft-ai-language
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/weft-ai-language/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill weft-ai-language -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/weft-ai-language/SKILL.md

## When to use it
- write typed Weft workflow pipelines with LLM nodes
- configure human-in-the-loop approvals that survive system restarts
- set up the Weft local backend and SvelteKit interface via `dev.sh`
- route outputs conditionally using `Gate` nodes

## Example prompts
- Help me build a Weft pipeline that requires human sign-off before posting to Discord.
- Show me how to connect an LlmConfig node to LlmInference in Weft.
- Configure the .env variables and run the Weft local dev environment.

## Similar
- [Large Language Models Security Specialist](https://affpapa.org/en/nevibecode/prompts/large-language-models-security-specialist.md) — prompt · ★ 174676
- [tao-run-automl](https://affpapa.org/en/nevibecode/skills/tao-run-automl.md) — skill · 1600 installs
- [zener-language](https://affpapa.org/en/nevibecode/skills/zener-language.md) — skill · 1700 installs
- [blip-2-vision-language](https://affpapa.org/en/nevibecode/skills/blip-2-vision-language.md) — skill · 944 installs
- [swift-language](https://affpapa.org/en/nevibecode/skills/swift-language.md) — skill · 4000 installs
- [langchain-development](https://affpapa.org/en/nevibecode/skills/langchain-development.md) — skill · 681 installs

From the same set: [reason-machines/trending-skills](https://affpapa.org/en/nevibecode/by/reason-machines/trending-skills.md) — 186 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md