writing-skills

Create and verify SKILL.md documentation using RED-GREEN-REFACTOR pressure scenarios.

Updated Feb 23, 2026
One-click install
npx skills add https://github.com/rishikanthc/ml-superpowers --skill writing-skills-rishikanthc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/rishikanthc/ml-superpowers/tree/main/skills/writing-skills
Command: npx skills add https://github.com/rishikanthc/ml-superpowers --skill writing-skills-rishikanthc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents untested, ambiguous, or easily-rationalized SKILL.md documentation by applying a test-driven development approach to skill authoring so that agents follow documented rules under pressure.

Core Features & Use Cases

  • RED-GREEN-REFACTOR for documentation: Run baseline pressure scenarios, write minimal SKILL.md to address observed failures, and iterate to close loopholes.
  • Testing methodology: Pressure-scenario templates, rationalization tables, red-flag lists, and verification checklists for discipline-enforcing skills.
  • Discovery & CSO guidance: Guidance on crafting discovery-optimized YAML frontmatter and token-efficient content so Claude finds and loads the right skill when needed.
  • Cross-references & progressive disclosure: Patterns for splitting heavy references, when to include scripts, and how to structure examples and flowcharts for efficient loading.

Quick Start

Run a realistic pressure scenario without this skill, document exact agent failures verbatim, add a minimal SKILL.md that addresses those failures, and re-run the scenario with the skill to verify 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 SKILL.md documentation to ensure AI agents follow rules under pressure?

Test-driven skill authoring verifies SKILL.md documentation by running baseline pressure scenarios, documenting agent failures, and iterating with minimal fixes to close rationalization loopholes.

What is RED-GREEN-REFACTOR for documentation and skill authoring?

RED-GREEN-REFACTOR for documentation applies test-driven development to skill authoring by running baseline pressure scenarios, writing minimal SKILL.md to address failures, and iterating to enforce agent compliance.

How do I write YAML frontmatter for skill discovery and token-efficient loading?

Skill discovery optimization requires crafting discovery-optimized YAML frontmatter and token-efficient content, using cross-references and progressive disclosure patterns so Claude finds and loads the right skill when needed.

Can I use test-driven development to prevent agents from rationalizing documented rules?

Yes, test-driven skill authoring prevents rationalized SKILL.md documentation by applying pressure-scenario templates, rationalization tables, red-flag lists, and explicit counters for discipline-enforcing skills.

How to structure SKILL.md examples and flowcharts for efficient agent loading?

Structure SKILL.md for efficient loading by using progressive disclosure patterns, splitting heavy references, and organizing examples and flowcharts to minimize token consumption during agent discovery and execution.

When should I not use test-driven development for skill documentation?

Test-driven skill authoring is unnecessary for simple reference skills without discipline-enforcing rules or pressure scenarios, where straightforward documentation without verification checklists suffices.