ad-philosophy
CommunityThink-first guardrails for safe, surgical changes.
Software Engineering#documentation#verification#guardrails#think-before-code#ground-before-code#non-trivial-work
Authoralexandremendoncaalvaro
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Universal agent guardrails enforce deliberate thinking, grounding in real patterns, and verifiable outcomes to reduce risk during non-trivial work.
Core Features & Use Cases
- Think-before coding: prompts explicit thinking, surface ambiguities, and surface trade-offs.
- Ground Before Coding: invokes a research pass to anchor decisions in real patterns and references.
- Documentation discipline: ensures definitions, decisions, and audits are captured without leakage of implementation details.
- Minimalism and surgical changes: encourage minimal, well-scoped changes with clear justification.
Quick Start
Apply these guardrails to any non-trivial task by surfacing assumptions, grounding decisions, and verifying outcomes before acting.
Dependency Matrix
Required Modules
None requiredComponents
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: ad-philosophy Download link: https://github.com/alexandremendoncaalvaro/CorridorKey-Runtime/archive/main.zip#ad-philosophy Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.