skills.rest
chhpt
chhptCOMMUNITY
Explore all skills by this author →
GitHub

writing-skills

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

Updated Aug 23, 2026
Search Tags:#documentation#prompt engineering#test-driven development#skill authoring#skill.md#agent testing#subagent testing
One-click install
npx skills add https://github.com/chhpt/skills --skill writing-skills-chhpt
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/chhpt/skills/tree/main/skills/writing-skills
Command: npx skills add https://github.com/chhpt/skills --skill writing-skills-chhpt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Untested skill documentation often fails in practice because authors never observe how agents actually behave without it, leading to instructions that agents ignore, misinterpret, or rationalize away under pressure. ## 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. - Rationalization Bulletproofing: Provides techniques for closing loopholes, building rationalization tables, and creating red flag lists so discipline-enforcing skills resist agent workarounds. - Discovery Optimization: Guides writing effective YAML frontmatter descriptions, keyword coverage, and naming conventions so skills are found when needed. - Use Case: When creating a new skill that enforces a workflow rule, run pressure scenarios with subagents first, document their verbatim excuses, then write the minimal skill that counters those specific failures. ## Quick Start Ask the agent to help you create a new skill by first running baseline test scenarios without the skill, then writing the SKILL.md to address the observed failures.

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, then structure the body with an overview, when-to-use triggers, core patterns, and common mistakes. Test the skill with subagent pressure scenarios before deploying to verify agents actually comply.

How to test agent skills before deployment?▼

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 until agents comply under combined pressures like time, sunk cost, and exhaustion.

What should go in a skill description field?▼

The description should only state triggering conditions starting with "Use when...", written in third person with specific symptoms and situations. Never summarize the skill's workflow, 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 sunk cost, pragmatism, or spirit-versus-letter arguments. Counter this with explicit negations of each loophole, rationalization tables, red flag lists, and foundational principles stated early.

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 automation instead of documentation.

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
NeuralChainXNeuralChainX

writing-skills

Author agent skills using a RED-GREEN-REFACTOR cycle with pressure-based test scenarios.

Official
Advanced
Intense-VisionsIntense-Visions
18

check-mechanical-constraints

Validate linter rules, boundary schemas, and forbidden imports in code projects.

Official
Advanced