writing-skills

Create and test agent skills using test-driven development methodology.

Updated Jan 12, 2025
One-click install
npx skills add https://github.com/rinbarpen/NeuroTrain --skill writing-skills-rinbarpen
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/rinbarpen/NeuroTrain/tree/main/.cursor/commands/writing-skills
Command: npx skills add https://github.com/rinbarpen/NeuroTrain --skill writing-skills-rinbarpen

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires graphviz.

What problem does it solve? Writing documentation-style skills for AI agents often produces untested instructions that agents ignore or misinterpret under pressure, leading to unreliable behavior in production workflows. ## Core Features & Use Cases - TDD-Based Skill Authoring: Applies the RED-GREEN-REFACTOR cycle to skill creation, requiring baseline failure tests with subagents before writing any skill content. - Rationalization Bulletproofing: Provides pressure-scenario testing methods, rationalization tables, and red-flag lists to close loopholes agents exploit. - Discovery Optimization: Guides Claude Search Optimization (CSO) with rules for descriptions, naming, keyword coverage, and token efficiency. - Use Case: When creating a new discipline-enforcing skill like TDD or verification-before-completion, run baseline pressure scenarios with subagents, document their exact rationalizations, then write a minimal skill that counters those specific failures. ## Quick Start Ask the agent to help you create a new skill by first running baseline pressure scenarios without the skill, then writing the SKILL.md to address the observed failures.

Frequently Asked Questions about writing-skills

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a new skill for Claude agents?▼

Create a directory with a SKILL.md file containing YAML frontmatter with name and description fields, followed by markdown instructions. Follow the TDD cycle: run baseline pressure scenarios without the skill first, then write minimal content addressing observed failures.

How to test agent skills before deployment?▼

Use pressure scenarios with subagents that combine 3+ pressures like time constraints, sunk cost, and authority. Run scenarios without the skill to capture baseline rationalizations, then verify agents comply once the skill is present.

What should a SKILL.md description field contain?▼

The description should start with "Use when..." and describe only triggering conditions and symptoms, never summarizing the skill's workflow. Write in third person, keep it under 500 characters, and include searchable keywords like error messages and symptoms.

Why do agents ignore skills under pressure?▼

Agents rationalize violations when facing time pressure, sunk costs, or authority conflicts. Counter this by documenting exact rationalizations verbatim, adding explicit negations for each loophole, and building rationalization tables with red-flag lists.

When should I not create a skill?▼

Skip skill creation for one-off solutions, project-specific conventions better placed in CLAUDE.md, well-documented standard practices, and mechanical constraints that can be enforced with automated validation instead of documentation.