Overview
This guide walks you through adding agent skills to an existing use case. By the end, your HTTP endpoints and scheduled workflows will be discoverable and usable by any Claude-based agent.New use cases get skills automatically. When you run
codika init, the scaffolded use case includes example skills for both the HTTP workflow and the scheduled workflow. This guide is for adding skills to existing use cases or customizing the defaults.Step 1: Identify triggerable workflows
Open yourconfig.ts and list all workflows with http or schedule trigger types. Skip sub-workflows, data ingestion, and service event workflows.
workflowTemplateIdfrom config.ts- Trigger type (http or schedule)
- Input schema fields (for HTTP)
- Output schema fields
- Integration UIDs used
- Credit cost
Step 2: Create the skills directory
Step 3: Write SKILL.md files
For HTTP workflows
Createskills/{name}/SKILL.md:
For scheduled workflows
Step 4: Validate
SKILL-STRUCTURE— Missing SKILL.md in a skills subdirectorySKILL-NAME-FORMAT— Name too long, wrong characters, or reserved wordsSKILL-WORKFLOW-REF— workflowTemplateId doesn’t match any workflowSKILL-DUPLICATE— Duplicate names or workflowTemplateIds
Step 5: Deploy
Step 6: Verify agent access
Naming rules
Thename field must follow Claude’s naming constraints:
Convention: Prefix with your use case slug:
wat-, propale-, crm-.
Description rules
Progressive disclosure for complex skills
If a skill needs more than 500 lines, split into referenced files:Checklist
Before deploying:- One skill per triggerable workflow (HTTP + scheduled with manual trigger)
- No skills for sub-workflows or data ingestion
- Each skill is a
{name}/SKILL.mddirectory - Frontmatter has
name,description,workflowTemplateId -
nameis valid (lowercase, hyphens, max 64 chars, no reserved words) -
descriptionis third person and under 1024 chars -
workflowTemplateIdmatches a workflow in config.ts - Body includes
codika triggercommand with example payload - Body includes input/output schemas
-
codika verify use-case .passes