design-md-enforcer
Design MD Enforcer
Purpose
The design-md-enforcer skill ensures that both human developers and AI agents follow a unified design system specification called DESIGN.md.
In traditional web development, design reasoning (style guides) and configuration values (like Tailwind config) are separated, leading to drift. This skill enforces a system where reasoning and raw values (hex codes, sizes) are bound together using token roles, and components reference these roles instead of hardcoding raw values.
Core Philosophy: Logic Meets Values
-
Tokens are Roles, Not Just Variables: A token is not just a hex code; it represents a specific purpose or role in the design system.
- Example:
primaryis not just#0A1F1C; it is the "main ink, text color" role. - Example:
body_mainis not just18px; it is the "default body copy" role.
- Example:
-
Components Reference Roles: UI components must never hardcode static hex values. They must reference the token roles. If the role's value changes, all components referencing it are automatically updated.
-
Reasoning is Required:
More from fatih-developer/fth-skills
task-decomposer
Break down large, complex, or ambiguous tasks into independent subtasks with dependency maps, execution order, and success criteria. Plan first, then execute step by step. Triggers on 'how should I do this', 'where do I start', 'plan the project', 'break it down', 'implement' or whenever a task involves multiple phases.
24multi-brain-debate
Two-round debate protocol where perspectives challenge each other before consensus. Round 1 presents independent positions, Round 2 allows counter-arguments and rebuttals. Produces battle-tested decisions for high-stakes choices.
20context-compressor
Compress long conversation histories, large code files, research results, and documents by 70% without losing critical information. Triggers when context window fills up, when summarizing previous steps in multi-step tasks, before loading large files into context, or on 'summarize', 'compress', 'reduce context', 'save tokens'.
18multi-brain-score
Confidence scoring overlay for multi-brain decisions. Each perspective rates its own confidence (1-10) with justification. Consensus uses scores as weights, flags low-confidence areas, and surfaces uncertainty explicitly.
16checkpoint-guardian
Automatic risk assessment before every critical action in agentic workflows. Detects irreversible operations (file deletion, database writes, deployments, payments), classifies risk level, and requires confirmation before proceeding. Triggers on destructive keywords like deploy, delete, send, publish, update database, process payment.
14multi-brain
Evaluate complex requests from 3 independent perspectives (Creative, Pragmatic, Comprehensive), reach consensus, then produce complete outputs. Use for architecture decisions, creative content, analysis, and any task where multiple valid approaches exist.
14