Why it is worth attention

This repository packages a complete autonomous software factory loop—spec writing, parallel implementation, visual review, and spec archival—that ran unattended for over a day and a half on one goal, demonstrating sustained agent-driven development.

Who it is for

Developers experimenting with AI coding agents (Claude Code, Codex, Cursor, etc.)
Engineering teams wanting to automate multi-step feature delivery with built-in verification
Agent workflow builders seeking reusable, domain-agnostic skill primitives

Use cases

Break a large feature into independently verifiable slices and have an agent build them one by one
Run an autonomous agent loop overnight to implement a spec with automatic code review and screenshot comparison
Adopt individual skills (e.g., write-spec, code-review, screenshot-critique) in any existing AI workflow

Strengths

Composable skills that work with 70+ harnesses (Claude Code, Codex, opencode, Cursor, etc.)
Proven autonomous loop: a single unattended Codex run lasted 1 day 16 hours building toward one goal
Includes visual verification skills (screenshot comparison, critique) so agents inspect visual output, not just code
Skills are independently usable and hackable—each can be invoked manually or integrated into any skills directory

Considerations

Requires a compatible agent harness that supports skills (e.g., Claude Code, Codex)—not a standalone tool
The 'fog of war' and slice-graph workflow may have a steep learning curve for conventional development teams
Skills are primarily designed for the author's personal use; community contributions and documentation are limited to the README

README quick start

Skills

AI skills for building software factories. My personal library of domain-agnostic agent skills, reused across every project. Small, composable, and hackable — works with any harness that supports skills: Claude Code, Codex, opencode, Cursor, duet, and 70+ others.

npx skills add dzhng/skills

Add --list to pick individual skills, or copy any skills/// folder into your harness's skills directory (e.g. .claude/skills/).

Why

Software is moving from tasks to factories: agents that pursue a goal autonomously until the output can be trusted. The hard part isn't breaking the goal into tasks — it's breaking it into independently verifiable pieces, and knowing where the pieces even are.

These skills run that loop. Treat the unknown as fog of war: map the terrain, carve it into territories that build and verify in isolation, and recursively re-slice whatever hides more map. And re-planning doesn't stop when planning ends — the spec is a living document, updated and re-sliced mid-implementation whenever the work teaches the agent that the plan is stale. Every piece must prove itself — architecture review, code review, and visual review against a baseline — before the loop moves on. Each iteration gets less wrong, until the goal is done.

Proof: one unattended Codex run pursuing a single goal for 1d 16h on top of these skills, slicing and iterating until done.

How to use

Plan. Ask your agent to /write-spec the goal. It interviews you, researches the unknowns, and materializes a spec under specs// — a slice graph where every slice is independently verifiable.
Build. Kick off the loop:
```
/goal /implement-spec specs/
```
Add whatever framing fits: on the xyz branch, or using /codex as the implementer while you stay the parent orchestrator and reviewer.
The rest fires on its own. The spec tells the loop when to call the other skills — a /review pass at the end of every slice, /screenshot-critique and /compare-screenshots on anything visual, /close-spec when the last slice lands — and to update and re-slice the plan whenever implementation proves it stale. Every skill is also independently useful: invoke any of them manually whenever y

Related repositories

Similar projects matched by category, topics, and programming language.

react

Featured

react

React is a JavaScript library for building user interfaces with declarative, component-based, and cross-platform design.

Web DevelopmentFrontend Frameworks

246,741

tandpfun

Featured

wardrobe

A GPT‑image powered app that extracts individual garment cutouts from photos, organizes them into a digital wardrobe, and generates modeled outfit previews.

JavaScript

1,570

mshumer

Featured

Claude-of-Duty

A browser-based first-person shooter built entirely with procedural generation and orchestrated AI agents, featuring 55k lines of Three.js/WebGL2 code and no art assets.

AI & Machine LearningAI Agents

1,234