writing-skills

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

Updated Sep 11, 2026
One-click install
npx skills add https://github.com/CYRUS-pinto/pi-bot --skill writing-skills-cyrus-pinto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/CYRUS-pinto/pi-bot/tree/main/.agents/skills/writing-skills
Command: npx skills add https://github.com/CYRUS-pinto/pi-bot --skill writing-skills-cyrus-pinto

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires graphviz, and includes references (resource) components.

What problem does it solve? Writing effective agent skills is hard because untested documentation often fails under real-world pressure—agents rationalize away rules, skip steps, or misinterpret guidance. This Skill applies test-driven development (RED-GREEN-REFACTOR) to skill authoring so you can verify agents actually comply before deployment. ## Core Features & Use Cases - TDD-Based Skill Authoring: Run baseline pressure scenarios with subagents (RED), write minimal skills addressing observed failures (GREEN), then close rationalization loopholes (REFACTOR). - Skill Discovery Optimization (SDO): Guidelines for writing descriptions, names, and keywords so future agents can find your skill, plus token-efficiency techniques. - Testing Methodology: Detailed guidance on pressure scenarios, rationalization tables, red flags lists, and micro-testing wording variants against no-guidance controls. - Use Case: You want to create a new discipline-enforcing skill (like mandatory code review). Use this Skill to design pressure scenarios, watch a subagent violate the rule without the skill, write the skill to counter those exact rationalizations, and verify compliance before deploying. ## Quick Start Ask the agent to help you create a new skill using the writing-skills TDD process, starting with a baseline pressure scenario test.

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 agent skill with SKILL.md?

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

How to test whether an agent skill actually works?

Use pressure scenarios with subagents combining 3+ pressures like time, sunk cost, and authority. Run scenarios without the skill to document baseline failures, then with the skill to verify compliance, and refactor to close any rationalization loopholes.

What should a skill description field contain?

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

When should I not create a new skill?

Skip skill creation for one-off solutions, standard practices already well-documented, project-specific conventions, and mechanical constraints that can be enforced with regex or validation automation instead of documentation.

Why do agents ignore skills under pressure?

Agents rationalize violations using excuses like sunk cost, time pressure, or "spirit versus letter" arguments. Counter this with explicit negations, rationalization tables, red flags lists, and foundational principles that close each specific loophole.