Haaaiawd/ANWS

🚀 A spec-driven workflow framework for AI-assisted development. Empowers prompt engineers to build production-ready software through structured PRD → Architecture → Task decomposition. Designed for Antigravity to enforce design-first principles and prevent architectural drift in vibe coding.🗺️Antigravity-Workflow-System

142Stars on the repository
18Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

anws-system

01

Haaaiawd/ANWS

Skill Claude CodeCodex

A routing guide for choosing the right ANWS workflow for a software task. ANWS is a set of workflows covering project discovery, design, planning, implementation, review, and upgrades.

not rated 142 3mo ago A 57 tokens original MIT

code-reviewer

02

Haaaiawd/ANWS

Skill Claude CodeCodex

A static code-review skill that checks whether an implementation matches its product requirements, architecture documents, task lists, and verification plans. Static review means it examines readable files and code without running the project or connecting to outside services.

not rated 142 3mo ago A 104 tokens original MIT

concept-modeler

03

Haaaiawd/ANWS

Skill Claude CodeCodex

An interactive method for turning a vague software request into a clear model of its concepts, entities, processes, terms, and missing pieces. It records the result as structured JSON for later planning and specification work.

not rated 142 3mo ago A 89 tokens original MIT

craft-authoring

04

Haaaiawd/ANWS

Skill Claude CodeCodex

A writing framework for creating workflows, skills, and prompts with reusable structures and quality checks. It emphasizes clear decisions, short steps, and verifiable results.

not rated 142 3mo ago A 38 tokens original MIT

design-reviewer

05

Haaaiawd/ANWS

Skill Claude CodeCodex

A design review guide for checking system design documents before implementation. It examines boundaries, interfaces, states, timing, and failure behaviour using evidence that can be traced back to specific document sections.

not rated 142 3mo ago A 72 tokens original MIT

e2e-testing-guide

06

Haaaiawd/ANWS

Skill Claude CodeCodex

A guide for writing human-led end-to-end testing documents. End-to-end testing checks a product from the user’s point of view across complete tasks, while manual verification means a person performs the checks.

not rated 142 3mo ago A 106 tokens original MIT

nexus-mapper

07

Haaaiawd/ANWS

Skill Claude CodeCodex

Generate a persistent .nexus-map/ knowledge base that lets any AI session instantly understand a codebase's architecture, systems, dependencies, and change hotspots. Use when starting work on an unfamiliar repository, onboarding with AI-assisted context, preparing for a major refactoring initiative, or enabling…

not rated 142 3mo ago A 118 tokens original MIT

nexus-query

08

Haaaiawd/ANWS

Skill Claude CodeCodex

Precise, instant code structure queries for active development — answer 'who depends on this interface before I refactor it', 'how many modules break if I change this', 'what is the real impact radius of this feature change', 'which module is the true high-coupling hotspot in this legacy codebase'. Essential before…

not rated 142 3mo ago A 119 tokens original MIT

output-contract

09

Haaaiawd/ANWS

Skill Claude CodeCodex

A set of rules for saving reports and coordinating work between coding-agent sessions. It defines how to record evidence, avoid repeated explanations, and control which session writes each file.

not rated 142 3mo ago A 63 tokens original MIT

runtime-inspector

10

Haaaiawd/ANWS

Skill Claude CodeCodex

A static inspection guide for finding how a program starts, creates other processes, communicates between them, and handles failures. It reports evidence about process boundaries, communication channels, message contracts, lifecycles, and security risks without changing or continuously running the code.

not rated 142 3mo ago A 51 tokens original MIT

sequential-thinking

11

Haaaiawd/ANWS

Skill Claude CodeCodex

A structured method for working through difficult problems in ordered steps while keeping the problem boundary clear and revising earlier conclusions when new evidence appears.

not rated 142 3mo ago A 46 tokens original MIT

spec-writer

12

Haaaiawd/ANWS

Skill Claude CodeCodex

A guide for investigating unclear product requirements and writing a structured product requirements document, or PRD. A PRD records what a product should do, why it is needed, and what is out of scope.

not rated 142 3mo ago A 83 tokens original MIT

system-architect

13

Haaaiawd/ANWS

Skill Claude CodeCodex

A workflow step for turning a product brief and technical decisions into a system architecture overview. It identifies separate systems, their boundaries, dependencies, and the source-code directories they map to.

not rated 142 3mo ago A 91 tokens original MIT

system-designer

14

Haaaiawd/ANWS

Skill Claude CodeCodex

A workflow for turning an approved high-level architecture into a detailed design for one system. The document covers boundaries, connections, data, trade-offs, and testing.

not rated 142 3mo ago A 73 tokens original MIT

task-planner

15

Haaaiawd/ANWS

Skill Claude CodeCodex

A planning method that breaks a system design into a work breakdown structure, meaning a hierarchy of concrete tasks and dependencies. It produces an execution checklist and a separate verification plan in Chinese-language project documents.

not rated 142 3mo ago A 51 tokens original MIT

task-reviewer

16

Haaaiawd/ANWS

Skill Claude CodeCodex

A structured review process for checking task and verification-plan documents against project requirements. It models requirements, user stories, tasks, contracts, and the evidence needed to show that work is complete.

not rated 142 3mo ago A 83 tokens original MIT

tech-evaluator

17

Haaaiawd/ANWS

Skill Claude CodeCodex

A technical evaluation method for comparing candidate technology stacks using architecture trade-off analysis and a weighted 12-part scoring matrix.

not rated 142 3mo ago A 82 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: