aming-claw

Coordinate backlog, graph, and semantic reconciliation for AI-driven code reviews.

26|5|Updated Feb 28, 2026
One-click install
npx skills add https://github.com/amingclawdev/aming-claw --skill aming-claw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: aming-claw
Source: https://github.com/amingclawdev/aming-claw/tree/main/skills/aming-claw
Command: npx skills add https://github.com/amingclawdev/aming-claw --skill aming-claw

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Aming Claw provides a graph-first governance framework to manage code changes, backlog, and semantic reconciliation, ensuring safe, auditable collaboration in AI-guided reviews.

Core Features & Use Cases

  • Graph-first discovery and governance surface: inspect project graph, backlog, and semantic queues to plan changes before mutation.
  • Backlog-driven workflow: generate and manage backlog rows with evidence and acceptance criteria tied to graph state.
  • Semantic enrichment guardrails: queue, review, and project-projected memory, with strict gating and reconcile.
  • Dashboard-backed collaboration: shared view for projects, graph, inspector, and queues across humans and AI.

Quick Start

Initialize a session by loading the Aming Claw context and graph-first resources, then begin governed review via the dashboard.

Frequently Asked Questions about aming-claw

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How does graph-first governance work for AI-driven code reviews?

Graph-first governance enforces the active project graph as the single source of truth, coordinating backlog tracking and semantic reconciliation before allowing code mutations during AI-driven reviews.

How do I track backlog items with evidence before applying code mutations?

Generate and manage backlog rows with explicit evidence and acceptance criteria tied to graph state, ensuring all code changes are planned and auditable before any mutations occur.

Can I use MCP-led operations for post-commit runtime checks?

Yes, MCP-led operations apply post-commit runtime checks, providing guardrails for safe, auditable changes and governing approvals across your project.

Does semantic enrichment queue projected memory with strict gating?

Yes, semantic enrichment guardrails queue, review, and project projected memory with strict gating and reconcile mechanisms to ensure safe semantic reconciliation.

What is the best way to coordinate graph discovery and code review queues for human and AI collaboration?

A dashboard-backed collaboration surface inspects project graph, backlog, and semantic queues, providing a shared view for humans and AI to govern reviews.