declaring-intent

Community

Declare intent before critical actions for review.

AuthorFlyFission
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Declares the intended action and reasoning before critical or irreversible actions, so reviewers can challenge the thinking and not just the result. The declaration also forces the actor to make the "why" and the "how will I know" explicit. For an agent, the stated intent is a proposal to be reviewed, never evidence that the agent understood.

Core Features & Use Cases

  • Provides an explicit intent document before irreversible actions such as deploys, migrations, data changes, public claims, or model swaps.
  • Includes clear abort criteria and a verified rollback to ensure reversibility or safe halting.
  • Enables a reviewer to challenge the reasoning and verify preconditions before action.

Quick Start

Declare intent before an irreversible action by stating the action, target, reasoning, abort criteria, and rollback, and await review.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: declaring-intent
Download link: https://github.com/FlyFission/nuclear-grade-context-engineering/archive/main.zip#declaring-intent

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.