weft-models

Read when a program calls a language model and you need it to behave: whether it reasons before answering and how hard, what bounds a reply's length and why one comes back empty, what a class of model costs in time and money, and how prompt caching works across a chain of calls.

Jump to install Review files

Repository: WeaveMindAI/weft
Last source activity: October 19, 2026 at 06:52
Detected SKILL.md language: English
Stars: 2,025
Forks: 223

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/WeaveMindAI/weft/tree/main/tangle/gemini-cli/.gemini/skills/weft-models.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/WeaveMindAI/weft --skill weft-models

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

SKILL.md

Source instructions · Read-only preview

name	weft-models
description	Read when a program calls a language model and you need it to behave: whether it reasons before answering and how hard, what bounds a reply's length and why one comes back empty, what a class of model costs in time and money, and how prompt caching works across a chain of calls.

Back to search Back to installation

releasing

Shipping weft: merging into main through a PR, what the release workflow publishes, the record tags that decide which stores publish, and the store rules that have actually bitten us. Load before merging to main, bumping an extension version, or debugging a red publish job.

2026-11-10

weft-frontend

Read when the user wants a page, app or site for the program, and before dispatching the frontend-builder: the verified scaffold commands, the default stack (pnpm, SvelteKit, PostgreSQL, BetterAuth, shadcn-svelte), calling the program's own routes and signal doors, the three variables that say where the program is, one shared PostgreSQL, where the api token lives, pictures as links, the build and its Dockerfile, and the shape for a site whose people each bring their own accounts or settings (the manager routes, the instance header and token, the settings page).

2026-11-10

weft-instances

Read whenever part of a program must run as several separate copies, each under its own id, even with ONE user: a session per chat, a sandbox per job, a workspace per document, a bot per customer. `@per_instance` (a container each), `@instance_filled` (a value each, a connection included), which instance a run is for, the route shape that works (shared routes, the instance picked per call), instance tokens, costs, starting and stopping one instance's containers, and giving every instance an end. When the copies belong to several PEOPLE, also read `weft-members`.

2026-11-10

View all from this repository

weft-models

Source facts

Install options

Install with an AI assistant

Review the source files

More from this repository

Install with an AI assistant

More from this repository