skills.rest
artgaurav16420-oss
artgaurav16420-ossCOMMUNITY
Explore all skills by this author →
GitHub

writing-skills

Document TDD-based skill authoring guidance with frontmatter and rationalization tracking.

Updated May 2, 2026
Search Tags:#tdd#documentation#subagents#rationalization#skill-writing#testing-skills
One-click install
npx skills add https://github.com/artgaurav16420-oss/Mega-Skills --skill writing-skills-artgaurav16420-oss
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/artgaurav16420-oss/Mega-Skills/tree/main/distribution/harnesses/tabnine/agent/skills/writing-skills
Command: npx skills add https://github.com/artgaurav16420-oss/Mega-Skills --skill writing-skills-artgaurav16420-oss

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Writing skills apply TDD principles to process documentation, ensuring that Skill guidance is testable, versionable, and resistant to rationalization by agents. The framework guides authors to structure SKILL.md with clear frontmatter, inline explanations, and explicit failure counters, enabling reliable discovery and enforcement of documented patterns.

Core Features & Use Cases

  • TDD-aligned skill authoring: RED-GREEN-REFACTOR workflow applied to documentation to prevent gaps and regressions.
  • Structured frontmatter and inline guidance: consistent name/description fields and navigable, compact content for quick loading.
  • Rationalization tracking: capture verbatim agent rationalizations and red flags to plug holes before deployment.
  • Heavy-reference vs inline content guidance: balance between inline patterns and external references for maintainability.

Quick Start

Draft a SKILL.md with frontmatter following the writing-skills guidance, and execute a RED-GREEN-REFACTOR cycle to validate the skill against simulated agent behavior.

Frequently Asked Questions about writing-skills

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

FAQPage Schema
How do I apply TDD principles to write agent skill documentation?▼

Apply TDD to skill documentation by using a RED-GREEN-REFACTOR workflow to structure SKILL.md files. This enforces test-first validation, preventing regressions and gaps in agent guidance before deployment.

What is rationalization tracking in skill authoring?▼

Rationalization tracking captures verbatim agent rationalizations and red flags during skill testing. It plugs enforcement holes by preventing agents from bypassing documented patterns before the skill is deployed.

How do I structure SKILL.md frontmatter for reliable agent discovery?▼

Structure SKILL.md frontmatter using consistent name and description fields alongside inline explanations. This compact, navigable content format supports quick loading and robust skill discovery across agents.

When should I use inline patterns versus heavy references in skill docs?▼

Balance inline patterns and heavy references based on maintainability needs. Inline guidance ensures immediate pattern enforcement, while external references reduce duplication for large, complex skill frameworks.

Can I use this framework to edit existing agent skills?▼

Yes, you can use this framework to edit existing skills across agents. It applies TDD-based authoring guidance to both creating new skills and updating existing ones, ensuring test-first validation and anti-rationalization.

Related Skills

Explore More Content & Communication Skills→
AgentTeam-TaichuAIAgentTeam-TaichuAI
630

skill-creator

Draft, test, and refine reusable agent skills within the ScienceClaw framework.

Community
Advanced
dgrochdgroch

self-model

Maintain a live inventory of agent capabilities with incremental updates.

Community
Intermediate
benmaierbenmaier

Create data science agents

Design and validate data-science agent prompts and parallel-agent configurations.

Community
Advanced
tuantiensiutuantiensiu
1

testing-skills-with-subagents

Run baseline scenarios without a skill to document failures and apply RED-GREEN-REFACTOR cycles.

Community
Advanced