Skills Overview
Benchmarked against: Anthropic — Skills Overview Architecture: Progressive Disclosure Layer 3 Location:
.claude/skills/directory
Skills are on-demand Standard Operating Procedures (SOPs) that load into an agent's context only when invoked. They are Layer 3 of the Progressive Disclosure system — detailed procedures that would waste tokens if loaded at startup.
What is a skill?
A skill is a structured prompt file that gives an agent step-by-step instructions for a specific task. Unlike rules (always loaded), skills are loaded only when needed.
| Property | Rules (L2) | Skills (L3) |
|---|---|---|
| Loading | Always | On demand |
| Purpose | Shape all behavior | Guide specific tasks |
| Token cost | ~2,000 total | ~500-2,000 each |
| Invocation | Automatic | /skill-name command |
| Examples | Constitution, cost awareness | 66s review, project scaffold |
Available skills
| Skill | Command | Purpose | Token cost |
|---|---|---|---|
| 66s Review | /66s-review | Six Hats + Six Shoes systematic analysis | ~1,500 |
| Create | /create | Scaffold new project structure | ~800 |
| Orchestrator | /orchestrator | Multi-agent communication scripts | ~800 |
| Brain Lite | /brain_lite | Emergency quota downshift | ~500 |
| Brain Mid | /brain_mid | Standard model configuration | ~500 |
| Brain Pro | /brain_pro | Full pro capabilities | ~500 |
| UI | /ui | Frontend component generation | ~1,000 |
How skills work
- User invokes with
/skill-name(or system determines skill needed) - Skill prompt loaded from
.claude/skills/skill-name/ - Detailed SOP injected into current context
- Agent executes following the skill's step-by-step instructions
- Skill content persists in context until compaction
Skill directory structure
.claude/skills/
├── 66s-review/
│ └── prompt.md # The skill prompt
├── brain_lite/
│ └── prompt.md
├── brain_mid/
│ └── prompt.md
├── brain_pro/
│ └── prompt.md
├── create/
│ └── prompt.md
├── orchestrator/
│ └── prompt.md
└── ui/
└── prompt.md
Each skill is a directory containing at minimum a prompt.md file with the full SOP.
When to use skills vs. rules
| Question | Answer → Action |
|---|---|
| Does it affect every action? | Yes → Make it a rule |
| Is it a specific procedure? | Yes → Make it a skill |
| Should agents always know this? | Yes → Rule |
| Is it invoked by command? | Yes → Skill |
| Does it have step-by-step instructions? | Yes → Skill |
Token economy
Loading a skill costs 500-2,000 tokens. Over a session with multiple compaction cycles, unused skills waste significant context.
| Scenario | Skills loaded | Token cost |
|---|---|---|
| Lean session (no skills) | 0 | 0 |
| One review | 1 (66s) | ~1,500 |
| Complex session | 2-3 | ~2,500-4,000 |
| All skills loaded | 7 | ~5,600 (wasteful!) |
Principle: Only load what you need, when you need it.
Related pages
| Page | Relationship |
|---|---|
| Creating a Skill | How to build new skills |
| Design Patterns | Best practices |
| CLAUDE.md + PD | Progressive Disclosure system |
| Skills in CLAUDE.md | Integration points |