skills.rest
Viranya2006
Viranya2006COMMUNITY
Explore all skills by this author →
WebsiteGitHub

writing-skills

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

Updated Aug 13, 2026
Search Tags:#prompt engineering#test-driven development#skill authoring#rationalization#skill discovery#agent documentation#subagent testing
One-click install
npx skills add https://github.com/Viranya2006/Lumen --skill writing-skills-viranya2006
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/Viranya2006/Lumen/tree/main/SKILLS/writing-skills
Command: npx skills add https://github.com/Viranya2006/Lumen --skill writing-skills-viranya2006

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Writing effective agent skills is hard because untested documentation often fails under real-world pressure, and authors cannot know if a skill actually changes agent behavior without observing baseline failures first. ## Core Features & Use Cases - TDD-Based Skill Authoring: Applies the RED-GREEN-REFACTOR cycle to documentation by running baseline pressure scenarios with subagents before writing any skill content. - Skill Discovery Optimization: Provides rules for writing descriptions, names, and keywords so future agents can find and correctly trigger the skill. - Rationalization Bulletproofing: Supplies techniques like rationalization tables, red flags lists, and persuasion principles to close loopholes agents exploit under pressure. - Use Case: When creating a new discipline-enforcing skill like a testing requirement, run pressure scenarios without the skill, document the agent's excuses verbatim, then write minimal guidance that counters those exact rationalizations. ## Quick Start Use the writing-skills skill to create a new skill for my agent following the test-driven development process.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I write a SKILL.md file for an AI agent?▼

Start with YAML frontmatter containing a name and a description that begins with "Use when" followed by triggering conditions. Then structure the body with an overview, when-to-use section, core patterns, quick reference, and common mistakes, keeping the total under 500 words where possible.

How to 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 specific rationalizations, and re-test with the skill present. Combine three or more pressures like time constraints, sunk cost, and authority for realistic testing.

What should go in a skill description field?▼

The description should only describe triggering conditions and symptoms, starting with "Use when", written in third person. Never summarize the skill's workflow in the description, because agents may follow the description shortcut instead of reading the full skill body.

Why do agents ignore or bypass skill instructions?▼

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

When should I not create a new skill?▼

Skip skill creation for one-off solutions, project-specific conventions, standard practices already well documented, and mechanical constraints that can be enforced with validation or regex. Skills are for reusable techniques, patterns, and references that apply broadly.

Related Skills

Explore More Software Engineering Skills→
rpamisrpamis
2.9k

writing-skills

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

Official
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