writing-skills

What this skill does

# Writing Skills

## Overview

**Writing skills IS Test-Driven Development applied to process documentation.**

**Personal skills live in agent-specific directories (`~/.claude/skills` for Claude Code, `~/.codex/skills` for Codex)** 

You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).

**Core principle:** If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.

**REQUIRED BACKGROUND:** You MUST understand superpowers:test-driven-development before using this skill. That skill defines the fundamental RED-GREEN-REFACTOR cycle. This skill adapts TDD to documentation.

**Official guidance:** For Anthropic's official skill authoring best practices, see anthropic-best-practices.md. This document provides additional patterns and guidelines that complement the TDD-focused approach in this skill.

## What is a Skill?

A **skill** is a reference guide for proven techniques, patterns, or tools. Skills help future Claude instances find and apply effective approaches.

**Skills are:** Reusable techniques, patterns, tools, reference guides

**Skills are NOT:** Narratives about how you solved a problem once

## Skills vs Other Claude Features

Understanding when to use each feature:

| Feature | Purpose | When to Use |
|---------|---------|-------------|
| **Custom Instructions** | Your personality | Global settings across all conversations: "Always use active voice", communication style, general preferences |
| **Projects** | Your reference library | Static context loaded at start of every chat in that Project. Always in context, never released. Background docs, company context, technical specs |
| **Skills** | Your specialist team | Load on-demand when needed, then release. Can include executable code. Task-specific workflows, specialized procedures |
| **MCP** | Your external connections | Standardized protocol to connect Claude to tools and data sources (database access, API connections, tool integrations) |

**How they work together:**

Example workflow:
1. **Custom Instructions** set your writing style
2. **Project** contains company background and brand guidelines
3. **MCP server** gives Claude access to your CRM data
4. **Skill** defines the workflow: "When generating quarterly reports, fetch CRM data via MCP, analyze trends, apply brand guidelines from Project, and format in my preferred style"

**The key distinction:** MCP handles connections, Skills handle workflows.

## The Three-Layer Architecture

Skills load information in stages. Understanding this changes how you structure them:

**Level 1: Metadata (always loaded)**
- Just the `name` and `description` from YAML frontmatter
- Costs ~100 tokens per skill
- This is why you can have hundreds of skills without performance issues
- **Put trigger logic here**

**Level 2: Instructions (loaded when triggered)**
- The full SKILL.md body with step-by-step guidance
- Under 5,000 tokens typically (keep under 500 lines)
- This is where Claude learns the workflow
- **Put reasoning and orchestration here**

**Level 3: Resources (loaded as needed)**
- Python scripts, templates, reference docs
- Effectively unlimited because scripts execute without loading into context
- Only the output comes back to Claude
- **Put deterministic operations and code here**

**Why this matters:** Don't write massive Level 2 instructions with code snippets. Write compact Level 2 instructions that say "run analyze.py" and put the actual code in Level 3. Claude executes the script and only sees the output. Way more efficient.

## TDD Mapping for Skills

| TDD Concept | Skill Creation |
|-------------|----------------|
| **Test case** | Pressure scenario with subagent |
| **Production code** | Skill document (SKILL.md) |
| **Test fails (RED)** | Agent violates rule without skill (baseline) |
| **Test passes (GREEN)** | Agent complies with skill present |
| **Refactor** | Close loopholes while maintaining compliance |
| **Write test first** | Run baseline scenario BEFORE writing skill |
| **Watch it fail** | Document exact rationalizations agent uses |
| **Minimal code** | Write skill addressing those specific violations |
| **Watch it pass** | Verify agent now complies |
| **Refactor cycle** | Find new rationalizations → plug → re-verify |

The entire skill creation process follows RED-GREEN-REFACTOR.

## When to Create a Skill

**Create when:**
- Technique wasn't intuitively obvious to you
- You'd reference this again across projects
- Pattern applies broadly (not project-specific)
- Others would benefit

**Don't create for:**
- One-off solutions
- Standard practices well-documented elsewhere
- Project-specific conventions (put in CLAUDE.md)

## Skill Types

### Technique
Concrete method with steps to follow (condition-based-waiting, root-cause-tracing)

### Pattern
Way of thinking about problems (flatten-with-flags, test-invariants)

### Reference
API docs, syntax guides, tool documentation (office docs)

## Directory Structure


```
skills/
  skill-name/
    SKILL.md              # Main reference (required)
    supporting-file.*     # Only if needed
```

**Flat namespace** - all skills in one searchable namespace

**Separate files for:**
1. **Heavy reference** (100+ lines) - API docs, comprehensive syntax
2. **Reusable tools** - Scripts, utilities, templates

**Keep inline:**
- Principles and concepts
- Code patterns (< 50 lines)
- Everything else

## SKILL.md Structure

**Frontmatter (YAML):**
- Only two fields supported: `name` and `description`
- Max 1024 characters total
- `name`: Use letters, numbers, and hyphens only (no parentheses, special chars)
- `description`: Third-person, describes ONLY when to use (NOT what it does)
  - Start with "Use when..." to focus on triggering conditions
  - Include specific symptoms, situations, and contexts
  - **NEVER summarize the skill's process or workflow** (see CSO section for why)
  - Keep under 500 characters if possible

```markdown
---
name: Skill-Name-With-Hyphens
description: Use when [specific triggering conditions and symptoms]
---

# Skill Name

## Overview
What is this? Core principle in 1-2 sentences.

## When to Use
[Small inline flowchart IF decision non-obvious]

Bullet list with SYMPTOMS and use cases
When NOT to use

## Core Pattern (for techniques/patterns)
Before/after code comparison

## Quick Reference
Table or bullets for scanning common operations

## Implementation
Inline code for simple patterns
Link to file for heavy reference or reusable tools

## Common Mistakes
What goes wrong + fixes

## Real-World Impact (optional)
Concrete results
```


## Claude Search Optimization (CSO)

**Critical for discovery:** Future Claude needs to FIND your skill

### 1. Rich Description Field

**Purpose:** Claude reads description to decide which skills to load for a given task. Make it answer: "Should I read this skill right now?"

**Format:** Start with "Use when..." to focus on triggering conditions

**CRITICAL: Description = When to Use, NOT What the Skill Does**

The description should ONLY describe triggering conditions. Do NOT summarize the skill's process or workflow in the description.

**Why this matters:** Testing revealed that when a description summarizes the skill's workflow, Claude may follow the description instead of reading the full skill content. A description saying "code review between tasks" caused Claude to do ONE review, even though the skill's flowchart clearly showed TWO reviews (spec compliance then code quality).

When the description was changed to just "Use when executing implementation plans with independent tasks" (no workflow summary), Claude correctly read the flowchart and followed the two-stage review process.

**The trap:** Descriptions that summarize workflow create a shortcut Claude will take. The skill body becomes documentation Claude skips.

```yaml