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 rockclaver/systemcraft
code-graph
Builds and maintains a `.claude/codegraph.md` index of a codebase — a structured map of every module with purpose, key exports, and dependencies — so the agent can navigate any repo by reading one file instead of scanning dozens. Use when starting work on an unfamiliar codebase, when asked to index a repo, when context costs are high from repeated scans, or at the start of any task that will touch multiple files.
14find-code
Locate files and code using grep and shell scripts — never by AI scanning. Returns exact file paths and line numbers so the agent can jump directly to the location. Use whenever the agent needs to find a function, class, variable, import, file, or any pattern in the codebase. Code and file discovery must always be a tool call, never an AI guess.
14grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
13prd-to-plan
Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/. Use when user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions "tracer bullets".
13write-a-prd
Create a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.
13design-api
Design and implement consistent, DRY REST API endpoints for database models — handlers, routing, validation, error responses, and shared utilities — then generate test coverage for every endpoint. Use when the user asks to write an API, add endpoints for a model, build a REST layer, or create CRUD routes.
13