Productivity

openwork-core

different-ai/openwork · updated Apr 8, 2026

$npx skills add https://github.com/different-ai/openwork --skill openwork-core
summary

openwork-core

skill.md

Quick Usage (Already Configured)

Orientation

  • Read AGENTS.md, VISION.md, PRINCIPLES.md, PRODUCT.md, and ARCHITECTURE.md before changing behavior.
  • Ensure vendor/opencode exists for self-reference.
  • Use the tauri-solidjs skill for stack-specific guidance.

Update the OpenCode mirror

git -C vendor/opencode pull --ff-only

Development workflow

pnpm tauri dev          # Desktop development
pnpm tauri ios dev      # iOS development
pnpm tauri android dev  # Android development

# Or run directly in the desktop package:
pnpm -C packages/desktop tauri dev

OpenCode Integration

Spawn OpenCode CLI

opencode -p "your prompt" -f json -q

Read OpenCode database

~/.opencode/opencode.db  # SQLite database

Key tables

  • sessions — Task runs
  • messages — Chat messages and tool calls
  • history — File change tracking

Common Gotchas

  • OpenWork must stay within OpenCode's tool surface; avoid inventing new capabilities.
  • Always expose plans, permissions, and progress for non-technical users.
  • Use Tauri commands for all system access (file, shell, database).
  • Keep UI at 60fps; avoid blocking the main thread.
  • Mobile builds require platform-specific setup (Xcode, Android Studio).

UI Principles

  • Slick and fluid: animations, transitions, micro-interactions.
  • Mobile-first: touch targets, gestures, adaptive layouts.
  • Transparency: show plans, steps, and tool calls.
  • Progressive disclosure: hide advanced controls until needed.

First-Time Setup (If Not Configured)

Clone the OpenCode mirror

git clone https://github.com/anomalyco/opencode vendor/opencode

Initialize Tauri project

pnpm create tauri-app . --template solid-ts

Add mobile targets

pnpm tauri ios init
pnpm tauri android init

Common Gotchas

  • OpenWork must stay within OpenCode’s tool surface; avoid inventing new capabilities.
  • Always expose plans, permissions, and progress for non-technical users.

First-Time Setup (If Not Configured)

Clone the OpenCode mirror

git clone https://github.com/anomalyco/opencode vendor/opencode
general reviews

Ratings

4.510 reviews
  • Shikha Mishra· Oct 10, 2024

    openwork-core is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Piyush G· Sep 9, 2024

    Keeps context tight: openwork-core is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Chaitanya Patil· Aug 8, 2024

    Registry listing for openwork-core matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Sakshi Patil· Jul 7, 2024

    openwork-core reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Ganesh Mohane· Jun 6, 2024

    I recommend openwork-core for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Oshnikdeep· May 5, 2024

    Useful defaults in openwork-core — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Dhruvi Jain· Apr 4, 2024

    openwork-core has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Rahul Santra· Mar 3, 2024

    Solid pick for teams standardizing on skills: openwork-core is focused, and the summary matches what you get after install.

  • Pratham Ware· Feb 2, 2024

    We added openwork-core from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

  • Yash Thakker· Jan 1, 2024

    openwork-core fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.