writing-skills

Create and test agent skills using TDD methodology with pressure scenarios.

Updated Aug 3, 2026
One-click install
npx skills add https://github.com/Yvesdefaria/GymLab --skill writing-skills-yvesdefaria
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/Yvesdefaria/GymLab/tree/main/.opencode/skills/writing-skills
Command: npx skills add https://github.com/Yvesdefaria/GymLab --skill writing-skills-yvesdefaria

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Writing documentation for AI agents often fails because untested instructions get rationalized away under pressure. This Skill applies Test-Driven Development to skill authoring, ensuring new skills actually change agent behavior before deployment. ## Core Features & Use Cases - TDD-Based Skill Authoring: Run baseline pressure scenarios with subagents (RED), write the skill addressing observed failures (GREEN), then close rationalization loopholes (REFACTOR). - Skill Discovery Optimization: Guidance on writing descriptions, keywords, and naming so future agents can find and trigger the skill correctly. - Testing Methodology: Includes references for pressure scenario design, persuasion principles, and Anthropic's official authoring best practices. - Use Case: When creating a new discipline-enforcing skill like TDD or verification-before-completion, use this Skill to test it against combined pressures (time, sunk cost, authority) before deploying it. ## Quick Start Use the writing-skills skill to create a new agent skill and verify it works under pressure scenarios before deployment.

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. Run baseline pressure scenarios without the skill first, then write content addressing the specific failures you observed.

How do I test that a skill actually changes agent behavior?

Run pressure scenarios combining time, sunk cost, and authority pressures with subagents, first without the skill to capture baseline rationalizations, then with the skill to verify compliance. Iterate by closing loopholes until agents comply under maximum pressure.

What should go in a skill description field?

Write the description in third person starting with "Use when..." followed by specific triggering conditions and symptoms. Never summarize the skill's workflow, since agents may follow the description instead of reading the full skill body.

When should I not create a skill?

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

Why do agents ignore skills under pressure?

Agents rationalize away rules when facing time pressure, sunk costs, or authority conflicts. Counter this with explicit prohibition of specific workarounds, rationalization tables, red flag lists, and foundational principles like "violating the letter is violating the spirit."