Skill Authoring Guide

Skill Authoring Guide

When NOT To Use

• Scoring a skill that already exists (use abstract:skills-eval)
• Authoring a hook (use abstract:hook-authoring)
• Verifying the skill fires (use abstract:subagent-testing)

Overview

Writing effective Claude Code skills requires Test-Driven Development (TDD) and persuasion principles from compliance research. We treat skill writing as process documentation that needs empirical validation rather than just theoretical instruction. Skills are behavioral interventions designed to change model behavior in measurable ways.

By using TDD, we ensure skills address actual failure modes identified through testing. Optimized descriptions improve discovery, while a modular structure supports progressive disclosure to manage token usage. It states intent, constraints and exit criteria, and leaves the path between them to the session doing the work. modules/persuasion-principles.md carries the strength budget that decides which of the three each statement is.

The Iron Law

NO SKILL WITHOUT A FAILING TEST FIRST

Every skill must begin with documented evidence of Claude failing without it. This validates that you are solving a real problem. No implementation should proceed without a failing test, and no completion claim should be accepted without evidence. Detailed enforcement patterns for adversarial verification and coverage gates are available in imbue:proof-of-work.

Skill Types

We categorize skills into three types: Technique skills for specific methods, Pattern skills for recurring solutions, and Reference skills for quick lookups and checklists. This helps organize interventions into the most effective format for the task.

Quick Start

Skill Analysis

```bash

Analyze skill complexity

python scripts/skill_analyzer.py

Estimate tokens

python scripts/token_estimator.py ```

Validation

```bash

Validate skill structure

python scripts/abstract_validator.py --check ```