write-a-skill
Writing Skills
Process
-
Gather requirements - ask user about:
- What task/domain does the skill cover?
- What specific use cases should it handle?
- Does it need executable scripts or just instructions?
- Any reference materials to include?
-
Draft the skill - create:
- SKILL.md with concise instructions
- Additional reference files if content exceeds 500 lines
- Utility scripts if deterministic operations needed
-
Review with user - present draft and ask:
- Does this cover your use cases?
- Anything missing or unclear?
- Should any section be more/less detailed?
Skill Structure
skill-name/
├── SKILL.md # Main instructions (required)
├── REFERENCE.md # Detailed docs (if needed)
├── EXAMPLES.md # Usage examples (if needed)
└── scripts/ # Utility scripts (if needed)
└── helper.js
SKILL.md Template
---
name: skill-name
description: Brief description of capability. Use when [specific triggers].
---
# Skill Name
## Quick start
[Minimal working example]
## Workflows
[Step-by-step processes with checklists for complex tasks]
## Advanced features
[Link to separate files: See [REFERENCE.md](REFERENCE.md)]
Description Requirements
The description is the only thing your agent sees when deciding which skill to load. It's surfaced in the system prompt alongside all other installed skills. Your agent reads these descriptions and picks the relevant skill based on the user's request.
Goal: Give your agent just enough info to know:
- What capability this skill provides
- When/why to trigger it (specific keywords, contexts, file types)
Format:
- Max 1024 chars
- Write in third person
- First sentence: what it does
- Second sentence: "Use when [specific triggers]"
Good example:
Extract text and tables from PDF files, fill forms, merge documents. Use when working with PDF files or when user mentions PDFs, forms, or document extraction.
Bad example:
Helps with documents.
The bad example gives your agent no way to distinguish this from other document skills.
When to Add Scripts
Add utility scripts when:
- Operation is deterministic (validation, formatting)
- Same code would be generated repeatedly
- Errors need explicit handling
Scripts save tokens and improve reliability vs generated code.
When to Split Files
Split into separate files when:
- SKILL.md exceeds 100 lines
- Content has distinct domains (finance vs sales schemas)
- Advanced features are rarely needed
Review Checklist
After drafting, verify:
- Description includes triggers ("Use when...")
- SKILL.md under 100 lines
- No time-sensitive info
- Consistent terminology
- Concrete examples included
- References one level deep
More from ishakantony/skills
discuss
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. DO NOT EVER USE THIS SKILL UNLESS THE USER EXPLICITLY ASKS YOU TO.
18tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
14prd-to-issues
Break a PRD into independently-workable issues and write each as a local markdown file in issues/. Use when the user wants to turn a PRD into a list of concrete tasks.
14write-a-prd
Generate a PRD from the client brief and write it as a local markdown file in issues/. Use when the user wants to turn a client request into a structured PRD.
14tackle-issues
Autonomously work through AFK issues from the local issues/ directory in a loop, spawning a subagent per task. Use when user types /tackle-issues or asks to "work the backlog", "burn down issues", "tackle AFK tasks", or run an AFK issue queue. Skips HITL issues. Each task is implemented via TDD in a subagent so the main context stays clean.
13commit
Stage changes, draft conventional commit messages, and commit with user confirmation. Use when user types /commit, asks to commit changes, or mentions creating a git commit.
10