Writing skills skill for AI agents

​

When your agent uses it

• Creating new skills, editing existing skills, or verifying skills work before deployment
• Reviewing a SKILL.md for format, structure, and trigger quality, or testing whether it fires with a subagent

​

Install

npx -y summer-engine@latest skills install writing-skills --agent claude-code

​

The skill

​

Overview

​

What is a Skill?

​

TDD Mapping for Skills

​

When to Create a Skill

• Technique wasn’t intuitively obvious to you
• You’d reference this again across projects
• Pattern applies broadly (not project-specific)
• Others would benefit

• 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

​

Pattern

​

Reference

​

Directory Structure

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

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

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

​

SKILL.md Structure

• Two required fields: name and description (see agentskills.io/specification for all supported fields)
• 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

---
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)

​

1. Rich Description Field

# 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

• 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
• If skill is technology-specific, make that explicit in the trigger
• Write in third person (injected into system prompt)
• NEVER summarize the skill’s process or workflow

# BAD: Too abstract, vague, doesn't include when to use
description: For async testing

# BAD: First person
description: I can help you with async tests when they're flaky

# BAD: Mentions technology but skill isn't specific to it
description: Use when tests use setTimeout/sleep and are flaky

# GOOD: Starts with "Use when", describes problem, no workflow
description: Use when tests have race conditions, timing dependencies, or pass/fail inconsistently

# GOOD: Technology-specific skill with explicit trigger
description: Use when wiring a CharacterBody3D controller and handling slope or stair movement

​

2. Keyword Coverage

• 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

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

​

4. Token Efficiency (Critical)

• getting-started workflows: <150 words each
• Frequently-loaded skills: <200 words total
• Other skills: <500 words (still be concise)

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

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

# 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 [other-skill-name] for workflow.

# BAD: Verbose example (42 words)
the user: "How did we handle the camera clipping through walls in the last project?"
You: I'll search past conversations for camera collision patterns.
[Dispatch subagent with search query: "SpringArm3D camera collision clipping"]

# GOOD: Minimal example (20 words)
Partner: "How did we stop the camera clipping through walls?"
You: Searching...
[Dispatch subagent → synthesis]

• Don’t repeat what’s in cross-referenced skills
• Don’t explain what’s obvious from command
• Don’t include multiple examples of same pattern

wc -w library/skills/<slug>/SKILL.md
# getting-started workflows: aim for <150 each
# Other frequently-loaded: aim for <200 total

• Good: condition-based-waiting > async-test-helpers
• Good: using-skills not skill-usage
• Good: flatten-with-flags > data-structure-refactoring
• Good: root-cause-tracing > debugging-techniques

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

​

4. Cross-Referencing Other Skills

• Good: **REQUIRED SUB-SKILL:** Use verification-before-completion
• Good: **REQUIRED BACKGROUND:** You MUST understand investigating-bugs
• Bad: See library/skills/debug (unclear if required)
• Bad: @library/skills/debug/SKILL.md (force-loads, burns context)

​

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"];
}

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

• Reference material → Tables, lists
• Code examples → Markdown blocks
• Linear instructions → Numbered lists
• Labels without semantic meaning (step1, helper2)

​

Code Examples

• Testing techniques → TypeScript/JavaScript
• System debugging → Shell/Python
• Data processing → Python

• Complete and runnable
• Well-commented explaining WHY
• From real scenario
• Shows pattern clearly
• Ready to adapt (not generic template)

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

​

File Organization

​

Self-Contained Skill

defense-in-depth/
  SKILL.md    # Everything inline

​

Skill with Reusable Tool

condition-based-waiting/
  SKILL.md    # Overview + patterns
  example.ts  # Working helpers to adapt

​

Skill with Heavy Reference

pptx/
  SKILL.md       # Overview + workflows
  pptxgenjs.md   # 600 lines API reference
  ooxml.md       # 500 lines XML structure
  scripts/       # Executable tools

​

The Iron Law (Same as TDD)

NO SKILL WITHOUT A FAILING TEST FIRST

• 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

​

Testing All Skill Types

​

Discipline-Enforcing Skills (rules/requirements)

• Academic questions: Do they understand the rules?
• Pressure scenarios: Do they comply under stress?
• Multiple pressures combined: time + sunk cost + exhaustion
• Identify rationalizations and add explicit counters

​

Technique Skills (how-to guides)

• Application scenarios: Can they apply the technique correctly?
• Variation scenarios: Do they handle edge cases?
• Missing information tests: Do instructions have gaps?

​

Pattern Skills (mental models)

• Recognition scenarios: Do they recognize when pattern applies?
• Application scenarios: Can they use the mental model?
• Counter-examples: Do they know when NOT to apply?

​

Reference Skills (documentation/APIs)

• Retrieval scenarios: Can they find the right information?
• Application scenarios: Can they use what they found correctly?
• Gap testing: Are common use cases covered?

​

Common Rationalizations for Skipping Testing

​

Bulletproofing Skills Against Rationalization

​

Close Every Loophole Explicitly

Write code before test? Delete it.

Write code before test? Delete it. Start over.

**No exceptions:**
- Don't keep it as "reference"
- Don't "adapt" it while writing tests
- Don't look at it
- Delete means delete

​

Address “Spirit vs Letter” Arguments

**Violating the letter of the rules is violating the spirit of the rules.**

​

Build Rationalization Table

| Excuse | Reality |
|--------|---------|
| "Too simple to test" | Simple code breaks. Test takes 30 seconds. |
| "I'll test after" | Tests passing immediately prove nothing. |
| "Tests after achieve same goals" | Tests-after = "what does this do?" Tests-first = "what should this do?" |

​

Create Red Flags List

## Red Flags - STOP and Start Over

- Code before test
- "I already manually tested it"
- "Tests after achieve the same purpose"
- "It's about spirit not ritual"
- "This is different because..."

**All of these mean: Delete code. Start over with TDD.**

​

Update CSO for Violation Symptoms

description: use when implementing any feature or bugfix, before writing implementation code

​

RED-GREEN-REFACTOR for Skills

​

RED: Write Failing Test (Baseline)

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

​

GREEN: Write Minimal Skill

​

REFACTOR: Close Loopholes

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

​

Anti-Patterns

​

Bad: Narrative Example

​

Bad: Multi-Language Dilution

​

Bad: Code in Flowcharts

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

​

Bad: Generic Labels

​

STOP: Before Moving to Next Skill

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

​

Skill Creation Checklist (TDD Adapted)

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

• Name uses only letters, numbers, hyphens (no parentheses/special chars)
• YAML frontmatter with required name and description fields (max 1024 chars; see spec)
• Description starts with “Use when…” and includes specific triggers/symptoms
• Description written in third person
• Keywords throughout for search (errors, symptoms, tools)
• Clear overview with core principle
• Address specific baseline failures identified in RED
• Code inline OR link to separate file
• One excellent example (not multi-language)
• Run scenarios WITH skill - verify agents now comply

• 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

• Small flowchart only if decision non-obvious
• Quick reference table
• Common mistakes section
• No narrative storytelling
• Supporting files only for tools or heavy reference

• Commit skill to git and push to your fork (if configured)
• Consider contributing back via PR (if broadly useful)

​

Discovery Workflow

1. Encounters problem (“tests are flaky”)
2. Finds SKILL (description matches)
3. Scans overview (is this relevant?)
4. Reads patterns (quick reference table)
5. Loads example (only when implementing)

​

The Bottom Line

​

Files in this skill

• testing-skills-with-subagents.md

​

Related skills

• debug: Disciplined bug, crash and error loop: script errors, console, debugger, hypothesis, fix, verify.