One-click install
npx skills add https://github.com/thedutchvisiongroup/agent-skills --skill writing-skills-thedutchvisiongroup
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-skills
Source: https://github.com/thedutchvisiongroup/agent-skills/tree/main/skills/writing-skills
Command: npx skills add https://github.com/thedutchvisiongroup/agent-skills --skill writing-skills-thedutchvisiongroup

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI agents tend to skip clarification and produce poorly structured skills with vague descriptions, bloated instructions, and missing edge-case handling. This Skill enforces a disciplined four-phase process for authoring skills that agents actually follow. ## Core Features & Use Cases - Mandatory Clarification Phase: Requires identifying assumptions and asking scope, constraint, and success-criteria questions before writing any skill content. - Structured Authoring Workflow: Covers structure design (progressive disclosure, degrees of freedom), persuasive writing techniques, and bias-resistant instruction patterns. - Validation Checklist: Provides a self-review checklist and red-flags table to test skills against real agent behavior before shipping. - Use Case: When asked to create a new skill for processing invoices, the agent first asks clarifying questions about scope and constraints, then drafts a SKILL.md under 500 lines with linked reference files, and finally validates it against the checklist. ## Quick Start Use the writing-skills skill to help me create a new agent skill for reviewing pull requests.

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 description, then write concise instructions under 500 lines. Move detailed material into reference files linked from SKILL.md, and include a clarification phase so the agent confirms scope before acting.

What makes a good skill description for agent discovery?

A good description states what the skill does and when to use it, written in third person with specific trigger terms. It is the only content loaded at startup, so vague descriptions like 'helps with documents' prevent the skill from being selected.

How long should a SKILL.md file be?

Keep the SKILL.md body under 500 lines. When content exceeds this limit, split detailed guides, examples, and API references into separate files in a references directory, linked directly from SKILL.md one level deep.

Why does my agent skip steps defined in a skill?

Agents skip steps when rules are weakly worded or verification is optional. Use commitment language like MUST and ALWAYS, add explicit checklists, and include STOP-and-verify gates to counter premature closure bias.

When should I not use progressive disclosure in a skill?

Avoid splitting content when the core workflow is short and always needed; inline it in SKILL.md instead. Progressive disclosure suits large references, domain-specific material, and rarely used advanced features, not essential instructions.