Skill Authoring Standard

Skill Authoring Standard

The DNA of every skill in this repository. Follow this standard when creating new skills or upgrading existing ones.

---

SKILL.md Template

---
name: skill-name
description: "When to use this skill. Include trigger keywords and phrases users might say. Mention related skills for disambiguation."
license: MIT
metadata:
  version: 1.0.0
  author: Alireza Rezvani
  category: domain-name
  updated: YYYY-MM-DD
---

# Skill Name

You are an expert in [domain]. Your goal is [specific outcome for the user].

## Before Starting

**Check for context first:**
If `[domain]-context.md` exists, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

Gather this context (ask if not provided):

### 1. Current State
- What exists today?
- What's working / not working?

### 2. Goals
- What outcome do they want?
- What constraints exist?

### 3. [Domain-Specific Context]
- [Questions specific to this skill]

## How This Skill Works

This skill supports [N] modes:

### Mode 1: Build from Scratch
When starting fresh — no existing [artifact] to work with.

### Mode 2: Optimize Existing
When improving something that already exists. Analyze what's working, identify gaps, recommend changes.

### Mode 3: [Situation-Specific]
When [specific scenario that needs a different approach].

## [Core Content Sections]

[Action-oriented workflow. Not a textbook — a practitioner guiding you through it.]

[Tables for structured information. Checklists for processes. Examples for clarity.]

## Proactive Triggers

Surface these issues WITHOUT being asked when you notice them in context:

- [Trigger 1: specific condition → what to flag]
- [Trigger 2: specific condition → what to flag]
- [Trigger 3: specific condition → what to flag]

## Output Artifacts

| When you ask for... | You get... |
|---------------------|------------|
| [Common request 1] | [Specific deliverable with format] |
| [Common request 2] | [Specific deliverable with format] |
| [Common request 3] | [Specific deliverable with format] |

## Communication

All output follows the structured communication standard:
- **Bottom line first** — answer before explanation
- **What + Why + How** — every finding has all three
- **Actions have owners and deadlines** — no "we should consider"
- **Confidence tagging** — 🟢 verified / 🟡 medium / 🔴 assumed

## Related Skills

- **skill-name**: Use when [specific scenario]. NOT for [disambiguation].
- **skill-name**: Use when [specific scenario]. NOT for [disambiguation].
- **skill-name**: Use when [specific scenario]. NOT for [disambiguation].

---

The 10 Patterns

Pattern 1: Context-First

Every skill checks for domain context before asking questions. Only ask for what's missing.

**Implementation:**

## Before Starting

**Check for context first:**
If `marketing-context.md` exists, read it before asking questions.
Use that context and only ask fo