writing-skills

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

2|Updated May 30, 2026
One-click install
npx skills add https://github.com/virahitvin8/crafty-gis --skill writing-skills-virahitvin8
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/virahitvin8/crafty-gis/tree/main/GIT_STAR/assignment-generator/antigravity-skills-main/antigravity-skills-main/skills/writing-skills
Command: npx skills add https://github.com/virahitvin8/crafty-gis --skill writing-skills-virahitvin8

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Writing effective agent skills without testing leads to documentation that agents ignore, misinterpret, or rationalize away under pressure, resulting in unreliable behavior in production. ## 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. - Discovery Optimization (CSO): Provides rules for writing descriptions, keywords, and names so future agents can find and correctly trigger the skill. - Rationalization Bulletproofing: Includes pressure-scenario testing methods, rationalization tables, and red-flag lists to close loopholes in discipline-enforcing skills. - Use Case: When creating a new skill that enforces a workflow rule (like mandatory code review), run baseline pressure scenarios with subagents first, document their excuses verbatim, then write the skill to explicitly counter each rationalization. ## Quick Start Use the writing-skills skill to create a new tested skill for enforcing test-driven development in my agent workflow.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I write an effective SKILL.md file for AI agents?

Write YAML frontmatter with name and description fields, where the description starts with "Use when" and lists triggering conditions only. Keep the body concise with an overview, quick reference, and one excellent example, and test it with subagents before deploying.

How do I test an agent skill before deployment?

Run pressure scenarios with subagents without the skill first to document baseline failures verbatim, then write the skill addressing those failures, and re-test until agents comply under combined pressures like time, sunk cost, and exhaustion.

What should go in a skill description field?

The description should only describe when to use the skill, starting with "Use when" plus specific triggering symptoms and situations. Never summarize the skill's workflow, because agents may follow the description shortcut instead of reading the full skill body.

When should I not create a new skill?

Skip skill creation for one-off solutions, standard practices already well-documented, project-specific conventions that belong in project config files, and mechanical constraints that can be enforced with automated validation instead of documentation.

Why do agents ignore or bypass skill rules?

Agents rationalize around rules under pressure using excuses like "spirit versus letter" or "being pragmatic." Counter this with explicit negations of each loophole, rationalization tables, red-flag lists, and foundational principles stated early in the skill.