Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.crewship.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Templates

Crewship provides two types of templates: crew templates (pre-configured teams with agents) and workflow templates (reusable mission execution patterns).

​
Crew Templates

Crew templates create a complete team in one step — a crew with pre-configured agents, roles, system prompts, and skill assignments. Deploy with crewship template deploy <slug> or the Settings UI.

​
Seed Data Crews

The built-in seed data (cmd/crewship/seeddata/) provides four crew templates:
Slug: engineering | Icon: terminal | Color: Blue
AgentRoleAgent RoleProfileAdapter
TomasTechnical ArchitectLEADFULLCLAUDE_CODE
ViktorBackend EngineerAGENTCODINGCLAUDE_CODE
NelaFrontend EngineerAGENTCODINGCLAUDE_CODE
MartinInfrastructure EngineerAGENTCODINGCLAUDE_CODE
Skills: network-probe, script-runner, file-crafter, web-scraper, system-inspector

​
Agent Configuration

Each seed agent has these settings:
SettingDefault Value
LLM ProviderANTHROPIC
LLM Modelclaude-haiku-4-5
Memory Enabledtrue
CLI AdapterCLAUDE_CODE
Timeout (LEAD)3600 seconds (1 hour)
Timeout (AGENT)1800-2400 seconds (30-40 min)

​
System Prompts

Each agent has a dedicated system prompt file in cmd/crewship/seeddata/prompts/{slug}.md. These prompts define the agent’s persona, expertise areas, communication style, and behavioral guidelines.

​
Workflow Templates

Workflow templates define reusable execution patterns for missions. They are defined in internal/orchestrator/workflow.go and available via the sidecar at GET /mission/templates.

​
Built-in Templates

Sequential

Tasks execute one after another in order. Each step depends on the previous one.
step-1 --> step-2 --> step-3

Parallel

All tasks run simultaneously, then results are aggregated by a lead agent.
task-a --|
task-b --|-> aggregate
task-c --|

Dev-Test Loop

Developer implements, tester reviews. On failure, loops back (max 3 iterations). This is the Ralph Loop pattern.
develop <--(fail)-- test
(max 3 iterations)

Pipeline

Sequential preparation, parallel work streams, final aggregation by lead.
prepare -> work-a --|
        -> work-b --|-> finalize

​
Template Step Structure

Each template step defines: 
type TemplateStep struct {
    ID            string   // Unique step identifier
    Title         string   // Human-readable step title
    AgentRole     string   // Role-based assignment ("developer", "tester", "lead")
    AgentSlug     string   // Or specific agent slug
    DependsOn     []string // Step IDs this depends on
    MaxIterations int      // Max retry attempts (0 = no retry)
    LoopBackTo    string   // On failure, restart from this step ID
}

​
Using Templates

Lead agents can reference templates when creating missions via the sidecar: 
# List available templates
curl -s http://localhost:9119/mission/templates

# Create a mission with the dev-test-loop template
curl -s -X POST http://localhost:9119/mission/create \
  -H "Content-Type: application/json" \
  -d '{
    "title": "Implement auth module",
    "template": "dev-test-loop",
    "tasks": [
      {"title": "Write auth handlers", "assigned_to": "viktor"},
      {"title": "Test auth flow", "assigned_to": "petra"}
    ]
  }'

​
Credential Templates

The seed data also includes credential templates in cmd/crewship/seeddata/credentials.go:

​
Anthropic Credential

The ResolveAnthropicCredential function auto-detects the credential type:
PrefixTypeEnv Var Name
sk-ant-oatAI_CLI_TOKENCLAUDE_CODE_OAUTH_TOKEN
OtherAPI_KEYANTHROPIC_API_KEY

​
Google Credential

Optional Google credentials from SEED_GOOGLE_EMAIL and SEED_GOOGLE_PASSWORD environment variables, stored as a JSON object under the SECRET type.