governance-constraint-design
OfficialTurn governance language into falsifiable constraints
System Documentation
What problem does it solve?
Governance requirements are often written as high-level policy language that cannot be directly enforced or audited; this Skill converts ambiguous governance phrasing into operational, testable constraints with clear pass/fail criteria, evidence expectations, and failure actions.
Core Features & Use Cases
- Falsifiability guidance: Teaches the three-question falsifiability test (what to verify, what counts as evidence, what happens on failure).
- Three-frame translation: Aligns engineering, compliance, and AI-system interpretations to prevent semantic divergence.
- Templates and promotion path: Provides a governance constraint template and guidance on promoting constraints from unverified to agent or deterministic enforcement.
- Use Case: Convert a policy requirement like "ensure human oversight" into a HARNESS.md constraint that specifies observable verification steps, required audit artifacts, and merge-blocking failure actions.
Quick Start
Write a governance constraint for HARNESS.md that translates "ensure human oversight" into a falsifiable verification slot specifying the observable checks, required evidence artifacts, verification method, and failure action.
Dependency Matrix
Required Modules
None requiredComponents
💻 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: governance-constraint-design Download link: https://github.com/Habitat-Thinking/ai-literacy-superpowers/archive/main.zip#governance-constraint-design 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 471,000+ vetted skills library on demand.