Skills
A skill is a structured prompt file that encodes a workflow as a slash command. When you type /brainstorm or /work, you’re invoking a skill — a Markdown document with YAML frontmatter that gets loaded into the agent’s context.
How Skills Work
- You type
/brainstorm in Claude Code
- Claude Code finds
skills/brainstorm/SKILL.md
- The skill’s content is injected into the conversation
- The agent follows the skill’s instructions
Skills are not code — they’re prompt programs. They define phases, decision trees, output formats, and validation steps that the agent follows.
Skill Anatomy
Every skill lives in skills/<name>/SKILL.md with this structure:
---
name: brainstorm
description: Explore ambiguous or early-stage ideas interactively
---
# Brainstorm Skill
## Phase 1: Understand the Idea
...
## Phase 2: Explore Constraints
...
The frontmatter defines:
| Field | Purpose |
|---|
name | Skill identifier — matches the /command name |
description | One-line summary shown in skill listings |
Built-in Skills
Genie ships with 14 skills organized by function:
Core Pipeline
| Skill | Command | Purpose |
|---|
| Brainstorm | /brainstorm | Explore ideas interactively, track wish-readiness |
| Wish | /wish | Convert a design into a structured WISH.md |
| Work | /work | Execute a wish — dispatch agents per execution group |
| Review | /review | Validate work against criteria — SHIP or FIX-FIRST |
Debugging & Fixing
| Skill | Command | Purpose |
|---|
| Trace | /trace | Investigate unknown issues, isolate root cause |
| Fix | /fix | Apply minimal fix for FIX-FIRST gaps |
| Report | /report | Full bug investigation with GitHub issue creation |
Orchestration
| Skill | Command | Purpose |
|---|
| PM | /pm | Full PM playbook — triage, assign, track, report, escalate |
| Council | /council | 10-perspective architectural review |
| Dream | /dream | Batch-execute SHIP-ready wishes overnight |
| Genie | /genie | Transform any session into a Genie orchestrator |
Utilities
| Skill | Command | Purpose |
|---|
| Wizard | /wizard | Guided onboarding — scaffold to first wish |
| Refine | /refine | Optimize prompts via prompt-optimizer |
| Docs | /docs | Audit and generate documentation |
The /learn skill was removed as a standalone skill — behavioral corrections are now handled through Claude Code’s native memory system. The qa-runner agent has been merged into the /qa QA system accessible via genie qa.
Invoking Skills
Skills are invoked as slash commands:
/brainstorm Add a webhook system for real-time notifications
You can pass arguments — the text after the command becomes context for the skill.
Some skills are also triggered automatically:
/work is invoked by the team-lead when dispatching execution
/review is invoked after work completion
/fix is invoked when review returns FIX-FIRST
Skill Composition
Skills can delegate to other skills:
/wizard delegates to /brainstorm for identity shaping and /wish for plan creation
/work invokes /review after execution completes
/report cascades through /trace before filing an issue
/dream orchestrates /work → /review loops across multiple wishes
Creating Custom Skills
To add a custom skill:
- Create
skills/<name>/SKILL.md
- Add YAML frontmatter with
name and description
- Write the skill’s instructions in Markdown
- The skill becomes available as
/<name>
---
name: deploy
description: Guide deployment to staging and production environments
---
# Deploy Skill
## Phase 1: Pre-flight Checks
- Verify all tests pass
- Check CI status
- Confirm target environment
## Phase 2: Deploy
...
Skills installed via the plugin system (in ~/.claude/plugins/genie/skills/) are available globally across all projects.
Skill vs. Agent
| Skill | Agent |
|---|
| What | A prompt program | A running process |
| Lifetime | Single conversation turn | Persistent tmux session |
| State | Stateless (context is the conversation) | Stateful (worker registry, mailbox) |
| Invocation | /command | genie spawn <role> |
| Use case | Structured workflow | Long-running autonomous work |
Skills tell agents what to do. Agents are who does it.