skills.rest
NT-boop-star
NT-boop-starCOMMUNITY
Explore all skills by this author →
GitHub

writing-skills

Create and test agent skills using test-driven development with subagent pressure scenarios.

Updated Apr 7, 2026
Search Tags:#documentation#prompt engineering#test-driven development#skill authoring#red-green-refactor#subagent#agent testing
One-click install
npx skills add https://github.com/NT-boop-star/BRMV-tract --skill writing-skills-nt-boop-star
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/NT-boop-star/BRMV-tract/tree/main/antigravity/skills/writing-skills
Command: npx skills add https://github.com/NT-boop-star/BRMV-tract --skill writing-skills-nt-boop-star

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Writing documentation-style skills for AI agents often produces untested instructions that agents ignore or rationalize away under pressure. This Skill applies test-driven development to skill authoring so you verify agents actually comply before deploying. ## 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). - Discovery optimization: Guidance for writing descriptions, keywords, and naming so future agents find the skill via Claude Search Optimization. - Testing methodology: Includes pressure scenario design, rationalization tables, red flag lists, and meta-testing techniques for bulletproofing discipline-enforcing skills. - Use Case: You want to create a new skill enforcing code review before merging. You run a scenario with time and sunk-cost pressure without the skill, watch the agent skip review, then write the skill countering those exact rationalizations and re-test until compliant. ## Quick Start Ask the agent to help you create a new skill by first running a baseline pressure scenario with a subagent, then drafting the SKILL.md and verifying compliance.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I test an agent skill before deploying it?▼

Run pressure scenarios with subagents without the skill first to document baseline failures verbatim, then write the skill addressing those failures and re-test with the skill present. Combine three or more pressures like time, sunk cost, and exhaustion for realistic testing.

What should go in a SKILL.md description field?▼

The description should start with "Use when..." and describe only triggering conditions and symptoms, never the skill's workflow. Write in third person, keep it under 500 characters, and include concrete keywords agents would search for.

Why do agents ignore skills under pressure?▼

Agents rationalize violations using excuses like sunk cost, pragmatism, or spirit-versus-letter arguments. Skills must explicitly close each loophole with negations, rationalization tables, and red flag lists discovered through baseline testing.

When should I not create a new skill?▼

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

How long should a SKILL.md file be?▼

Keep frequently-loaded skills under 200 words and other skills under 500 words. Move heavy reference material over 100 lines into separate files and use cross-references instead of repeating content.

Related Skills

Explore More Software Engineering Skills→
bostonaholicbostonaholic
20

test-driven-development

Enforce the RED-GREEN-REFACTOR cycle for test-driven development.

Community
Advanced
OmniNode-aiOmniNode-ai
3

sharing-skills

Guide users through contributing skills via GitHub CLI pull requests.

Official
Intermediate
robkiskrobkisk

writing-skills

Create and refine documentation skills using a test-driven RED-GREEN-REFACTOR cycle.

Community
Advanced
AnthonyPoschenAnthonyPoschen
2

encode-lessons

Convert recurring corrections and preventable mistakes into durable structural guards.

Community
Basic