CtrlK
BlogDocsLog inGet started
Tessl Logo

jtbd-generator

Generate JTBD (Jobs-to-be-Done) markdown files from step descriptions. Use when creating API workflows, building JTBD files, documenting multi-step processes, or when user says "create a JTBD", "generate workflow", "document these API steps", or "build a job with these operations".

80

3.17x
Quality

72%

Does it follow best practices?

Impact

92%

3.17x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/jtbd-generator/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

100%

Internal Artifact Catalog Onboarding Workflow

JTBD file structure and naming conventions

Criteria
Without context
With context

Correct save path

0%

100%

Kebab-case name

0%

100%

Name length

0%

100%

Description field present

0%

100%

Description length

0%

100%

Step headers exist

0%

100%

Sequential step numbering

0%

100%

URN format for api field

0%

100%

operationId field present

0%

100%

Inputs section present

0%

100%

Action-oriented overview

0%

100%

Folder name matches frontmatter name

0%

100%

Prerequisites section

0%

100%

Completion or summary section

0%

100%

82%

29%

Automated Project Onboarding and Team Notification

Multi-step data flow between JTBD steps

Criteria
Without context
With context

Two step headers

0%

100%

Step 1 outputs section

100%

100%

projectId captured in outputs

100%

100%

Step 2 links projectId to Step 1

75%

60%

organizationId reused from Step 1

0%

33%

URN format in both steps

0%

100%

Inputs in both steps

100%

100%

Correct save path

0%

100%

Kebab-case name

100%

100%

Sequential step numbering

0%

100%

What happens next in Step 1

30%

100%

95%

59%

Application Deployment Workflow Documentation

Conversational prose and action-oriented documentation

Criteria
Without context
With context

Overview section present

0%

100%

Overview starts with action verb

0%

100%

Conversational step language

53%

100%

Purpose explanations

53%

66%

What happens next sections

0%

100%

Prerequisites section

0%

100%

No placeholder text

100%

100%

Correct save path

0%

100%

URN format in YAML blocks

0%

100%

Specific terminology in descriptions

100%

100%

Repository
mulesoft/mulesoft-dx
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.