Writing Skills

Overview

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

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 requirements-framework: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 references/skill-authoring-best-practices.md. That 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

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

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)
Mechanical constraints (if it's enforceable with regex/validation, automate it — save documentation for judgment calls)

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

Directory Structure (Requirements Framework Convention)

plugins/requirements-framework/skills/
  skill-name/
    SKILL.md              # Main reference (required)
    references/           # Supporting files subdirectory
      supporting-file.md  # Only if needed

Key conventions for this framework:

Supporting files go in a references/ subdirectory (not flat alongside SKILL.md)
YAML frontmatter includes git_hash field for version tracking
Skills that satisfy requirements include a "Requirements Integration" section

Separate files for:

Heavy reference (100+ lines) — API docs, comprehensive syntax
Reusable tools — Scripts, utilities, templates

Keep inline:

Principles and concepts
Code patterns (< 50 lines)
Everything else

SKILL.md Structure

Frontmatter (YAML):

Required fields: name, description, git_hash
Max 1024 characters for name + description combined
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
git_hash: Set to uncommitted for new files; updated by ./update-plugin-versions.sh

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

# 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

## Requirements Integration (if applicable)
How this skill interacts with the requirements system:
- Which requirement it satisfies (satisfied_by_skill mapping)
- Auto-satisfy behavior
- Chaining to next skill

## Common Mistakes
What goes wrong + fixes

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.

# BAD: Summarizes workflow - Claude may follow this instead of reading skill
description: Use when executing plans - dispatches subagent per task with code review between tasks

# BAD: Too much process detail
description: Use for TDD - write test first, watch it fail, write minimal code, refactor

# GOOD: Just triggering conditions, no workflow summary
description: Use when executing implementation plans with independent tasks in the current session

# GOOD: Triggering conditions only
description: Use when implementing any feature or bugfix, before writing implementation code

Content:

Use concrete triggers, symptoms, and situations that signal this skill applies
Describe the problem (race conditions, inconsistent behavior) not language-specific symptoms (setTimeout, sleep)
Keep triggers technology-agnostic unless the skill itself is technology-specific
Write in third person (injected into system prompt)
NEVER summarize the skill's process or workflow

2. Keyword Coverage

Use words Claude would search for:

Error messages: "Hook timed out", "ENOTEMPTY", "race condition"
Symptoms: "flaky", "hanging", "zombie", "pollution"
Synonyms: "timeout/hang/freeze", "cleanup/teardown/afterEach"
Tools: Actual commands, library names, file types

3. Descriptive Naming

Use active voice, verb-first:

creating-skills not skill-creation
condition-based-waiting not async-test-helpers

Gerunds (-ing) work well for processes:

creating-skills, testing-skills, debugging-with-logs
Active, describes the action you're taking

4. Token Efficiency (Critical)

Problem: Bootstrap and frequently-referenced skills load into EVERY conversation. Every token counts.

Target word counts:

Bootstrap/frequently-loaded skills: < 200 words total
Other skills: < 500 words (still be concise)

Techniques:

Move details to supporting files:

# BAD: Document all flags in SKILL.md
search-conversations supports --text, --both, --after DATE, --before DATE, --limit N

# GOOD: Reference help or separate file
search-conversations supports multiple modes and filters. Run --help for details.

Use cross-references:

# BAD: Repeat workflow details
When searching, dispatch subagent with template...
[20 lines of repeated instructions]

# GOOD: Reference other skill
Always use subagents (50-100x context savings). REQUIRED: Use requirements-framework:dispatching-parallel-agents for workflow.

Compress examples:

# BAD: Verbose example (42 words)
your human partner: "How did we handle authentication errors in React Router before?"
You: I'll search past conversations for React Router authentication patterns.
[Dispatch subagent with search query: "React Router authentication error handling 401"]

# GOOD: Minimal example (20 words)
Partner: "How did we handle auth errors in React Router?"
You: Searching...
[Dispatch subagent -> synthesis]

5. Cross-Referencing Other Skills

When writing documentation that references other skills:

Use skill name only, with explicit requirement markers:

GOOD: **REQUIRED SUB-SKILL:** Use requirements-framework:test-driven-development
GOOD: **REQUIRED BACKGROUND:** You MUST understand requirements-framework:systematic-debugging
BAD: See skills/testing/test-driven-development (unclear if required)
BAD: @skills/testing/test-driven-development/SKILL.md (force-loads, burns context)

Why no @ links: @ syntax force-loads files immediately, consuming 200k+ context before you need them.

Flowchart Usage

digraph when_flowchart {
    "Need to show information?" [shape=diamond];
    "Decision where I might go wrong?" [shape=diamond];
    "Use markdown" [shape=box];
    "Small inline flowchart" [shape=box];

    "Need to show information?" -> "Decision where I might go wrong?" [label="yes"];
    "Decision where I might go wrong?" -> "Small inline flowchart" [label="yes"];
    "Decision where I might go wrong?" -> "Use markdown" [label="no"];
}

Use flowcharts ONLY for:

Non-obvious decision points
Process loops where you might stop too early
"When to use A vs B" decisions

Never use flowcharts for:

Reference material (use tables, lists)
Code examples (use markdown blocks)
Linear instructions (use numbered lists)

Code Examples

One excellent example beats many mediocre ones.

Choose most relevant language:

Testing techniques: Python (pytest)
System debugging: Shell/Python
Data processing: Python
Web patterns: TypeScript/JavaScript

Good example:

Complete and runnable
Well-commented explaining WHY
From real scenario
Shows pattern clearly

Don't:

Implement in 5+ languages
Create fill-in-the-blank templates
Write contrived examples

You're good at porting — one great example is enough.

The Iron Law (Same as TDD)

NO SKILL WITHOUT A FAILING TEST FIRST

This applies to NEW skills AND EDITS to existing skills.

Write skill before testing? Delete it. Start over. Edit skill without testing? Same violation.

No exceptions:

Not for "simple additions"
Not for "just adding a section"
Not for "documentation updates"
Don't keep untested changes as "reference"
Don't "adapt" while running tests
Delete means delete

REQUIRED BACKGROUND: The requirements-framework:test-driven-development skill explains why this matters. Same principles apply to documentation.

Testing different skill types and bulletproofing against rationalization: See references/skill-testing-guide.md

RED-GREEN-REFACTOR for Skills

Follow the TDD cycle:

RED: Write Failing Test (Baseline)

Run pressure scenario with subagent WITHOUT the skill. Document exact behavior:

What choices did they make?
What rationalizations did they use (verbatim)?
Which pressures triggered violations?

This is "watch the test fail" — you must see what agents naturally do before writing the skill.

GREEN: Write Minimal Skill

Write skill that addresses those specific rationalizations. Don't add extra content for hypothetical cases.

Run same scenarios WITH skill. Agent should now comply.

REFACTOR: Close Loopholes

Agent found new rationalization? Add explicit counter. Re-test until bulletproof.

Testing methodology: See references/testing-skills-with-subagents.md for the complete testing methodology:

How to write pressure scenarios
Pressure types (time, sunk cost, authority, exhaustion)
Plugging holes systematically
Meta-testing techniques

Common Rationalizations for Skipping Testing

Excuse	Reality
"Skill is obviously clear"	Clear to you ≠ clear to other agents. Test it.
"It's just a reference"	References can have gaps, unclear sections. Test retrieval.
"Testing is overkill"	Untested skills have issues. Always. 15 min testing saves hours.
"I'll test if problems emerge"	Problems = agents can't use skill. Test BEFORE deploying.
"Too tedious to test"	Testing is less tedious than debugging bad skill in production.
"I'm confident it's good"	Overconfidence guarantees issues. Test anyway.
"Academic review is enough"	Reading ≠ using. Test application scenarios.
"No time to test"	Deploying untested skill wastes more time fixing it later.

All of these mean: Test before deploying. No exceptions.

Anti-Patterns

Narrative Example

"In session 2025-10-03, we found empty projectDir caused..." Why bad: Too specific, not reusable

Multi-Language Dilution

example-js.js, example-py.py, example-go.go Why bad: Mediocre quality, maintenance burden

Code in Flowcharts

step1 [label="import fs"];
step2 [label="read file"];

Why bad: Can't copy-paste, hard to read

Generic Labels

helper1, helper2, step3, pattern4 Why bad: Labels should have semantic meaning

STOP: Before Moving to Next Skill

After writing ANY skill, you MUST STOP and complete the deployment process.

Do NOT:

Create multiple skills in batch without testing each
Move to next skill before current one is verified
Skip testing because "batching is more efficient"

The deployment checklist below is MANDATORY for EACH skill.

Skill Creation Checklist (TDD Adapted)

RED Phase — Write Failing Test:

Create pressure scenarios (3+ combined pressures for discipline skills)
Run scenarios WITHOUT skill — document baseline behavior verbatim
Identify patterns in rationalizations/failures

GREEN Phase — Write Minimal Skill:

REFACTOR Phase — Close Loopholes:

Identify NEW rationalizations from testing
Add explicit counters (if discipline skill)
Build rationalization table from all test iterations
Create red flags list
Re-test until bulletproof

Quality Checks:

Small flowchart only if decision non-obvious
Quick reference table
Common mistakes section
No narrative storytelling
Supporting files only in references/ subdirectory

Requirements Integration (if applicable):

Add satisfied_by_skill mapping to auto-satisfy-skills.py
Create message YAML in ~/.claude/messages/ (if new requirement)
Add requirement definition to examples/global-requirements.yaml
Document auto-satisfy behavior in skill's "Requirements Integration" section

Deployment:

Commit skill to git
Run ./update-plugin-versions.sh to update git_hash
Run ./sync.sh deploy to deploy to runtime
Bump plugin version in plugin.json if needed

Requirements Integration

This skill has no direct requirement mapping — it's a meta-skill for creating other skills. However, skills you create using this methodology may need their own requirement integrations (see checklist above).

The Bottom Line

Creating skills IS TDD for process documentation.

Same Iron Law: No skill without failing test first. Same cycle: RED (baseline) → GREEN (write skill) → REFACTOR (close loopholes). Same benefits: Better quality, fewer surprises, bulletproof results.

If you follow TDD for code, follow it for skills. It's the same discipline applied to documentation.

writing-skills