Verified:GitHub

write-a-skill

Convert user intent and evaluation criteria into a future-agent prompt.

Updated Mar 12, 2026

Search Tags:#agent skills #yaml frontmatter #intent capture #prompt writing #quality bar #trigger design #agent briefing

Ready to run

npx skills add https://github.com/mpsuesser/workspace --skill write-a-skill-mpsuesser

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: write-a-skill
Source: https://github.com/mpsuesser/workspace/tree/main/dotconfig/pi/agent/skills/write-a-skill
Command: npx skills add https://github.com/mpsuesser/workspace --skill write-a-skill-mpsuesser

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of writing a new agent skill by translating a user’s intent and quality bar into clear, future-agent instructions.

Core Features & Use Cases

User interview to capture intent: Extracts how the skill should be triggered and what outcomes the agent should produce (and avoid) based on the user’s real use case.
Quality bar definition: Captures what “done well” means, including failure modes to avoid and any taste-level preferences.
Readable skill instructions: Produces a skill that reads like a senior colleague briefing the future agent, with concise, non-over-prescriptive guidance.
Good description for discovery: Ensures the YAML description is tight, includes concrete “Use when…” triggers, and is suitable for deciding when to load the skill.

Quick Start

Tell the AI what kind of tasks should trigger the new skill and describe what a great result looks like for your scenario.

Frequently Asked Questions about write-a-skill

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

FAQPage Schema

How do I write an agent skill prompt from a user intent?▼

To write an agent skill prompt, convert user intent and quality criteria into clear instructions formatted as a SKILL.md file with YAML frontmatter. The output provides concise guidance that avoids over-prescription while capturing constraints and trigger conditions.

What is the best way to design triggers for agent skills?▼

Designing triggers for agent skills involves writing a tight YAML description with concrete 'Use when...' scenarios. This ensures the agent correctly identifies when to load the skill based on specific task activation conditions.

How do I define the quality bar when creating a new agent skill?▼

Defining the quality bar for an agent skill requires capturing what 'done well' means, including failure modes to avoid and taste-level preferences. This translates user expectations into explicit, non-over-prescriptive instructions for the future agent.

What should be included in the YAML frontmatter for a skill file?▼

YAML frontmatter for a skill file must include the name and description fields. The description should be tight and contain concrete trigger scenarios to ensure proper discovery and loading by the agent.

Can I use this approach to refine an existing agent briefing?▼

Yes, you can refine an existing agent briefing by applying intent capture and trigger design principles. It restructures the prompt to read like a senior colleague briefing, removing unnecessary filler while clarifying constraints.

Why does my agent skill not trigger correctly during task activation?▼

Agent skills fail to trigger correctly when the YAML description lacks specific 'Use when...' triggers or over-prescribes behavior. Fixing trigger design requires tightening the description to match real use cases without unnecessary filler.