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".

3.17x

Quality

72%

Does it follow best practices?

Impact

92%

3.17x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

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

Quality

Content

55%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with executable code and a well-structured workflow with proper validation checkpoints and error recovery. However, it is severely bloated—easily 3-4x longer than necessary—with redundant sections (tips, example interactions, full utility listings) that waste context window tokens. The monolithic structure with no progressive disclosure compounds the verbosity problem.

Suggestions

Cut the content by at least 50%: remove the 'Tips for Quality Output' section (Claude knows how to write well), trim the 'Example Interaction' to just the data flow example, and remove obvious guidance like 'Be conversational and helpful'.

Move the 'Available Python Utilities' reference to a separate REFERENCE.md and link to it, as this is pure API documentation that doesn't need to be in the main skill.

Move 'Data Flow Intelligence' rules and 'Error Handling' patterns to separate files (e.g., DATA_FLOW.md, ERROR_HANDLING.md) and reference them from the main workflow steps where they're relevant.

Remove the 'Success Criteria' and 'Notes' sections—the success criteria largely restate the workflow steps, and the notes repeat instructions already given in the workflow.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~350+ lines. It over-explains concepts Claude already knows (how to write conversational prose, what kebab-case is, how to save files), includes lengthy example interactions, and repeats information across sections. The full API utility listing at the end duplicates what could be discovered from the code. Tips like 'Be conversational and helpful' and 'Explain the why' are unnecessary coaching for Claude.	1 / 3
Actionability	The skill provides fully executable Python code snippets with real imports, function calls, and concrete examples throughout. Each workflow step has copy-paste ready code with specific function signatures, parameters, and expected outputs. The validation command is a concrete bash command.	3 / 3
Workflow Clarity	The 6-step workflow is clearly sequenced (Parse → Discover → Analyze → Generate → Validate → Save) with explicit validation in Step 5 including error recovery (explain error, auto-fix, regenerate, re-validate). The data flow rules are well-defined with confidence levels, and error handling covers multiple failure scenarios with recovery paths.	3 / 3
Progressive Disclosure	Everything is crammed into a single monolithic file with no references to external documentation. The Available Python Utilities section alone is ~40 lines that could be in a separate REFERENCE.md. The Data Flow Intelligence rules, Error Handling patterns, and Tips sections could all be split out. No bundle files are provided to support the referenced library paths, making it impossible to verify the structure.	1 / 3
	Total	8 / 12 Passed

Description

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a solid skill description that clearly communicates its purpose and provides explicit trigger guidance. The 'Use when' clause with quoted user phrases is well done. The main weakness is that the specificity of capabilities could be improved by listing more concrete actions beyond just 'generate' (e.g., validate, update, parse steps).

Suggestions

Add more specific concrete actions beyond generation, such as 'validate step definitions', 'update existing JTBD files', or 'parse API operation sequences' to improve specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain (JTBD markdown files) and the primary action (generate from step descriptions), but doesn't list multiple concrete actions beyond generation. It mentions 'API workflows' and 'documenting multi-step processes' but these are more context than distinct capabilities.	2 / 3
Completeness	Clearly answers both 'what' (generate JTBD markdown files from step descriptions) and 'when' (explicit 'Use when' clause with multiple trigger scenarios and quoted user phrases).	3 / 3
Trigger Term Quality	Includes strong natural trigger terms: 'create a JTBD', 'generate workflow', 'document these API steps', 'build a job with these operations', 'API workflows', 'JTBD files', 'multi-step processes'. These cover multiple natural phrasings a user might employ.	3 / 3
Distinctiveness Conflict Risk	JTBD (Jobs-to-be-Done) markdown files is a very specific niche. The combination of 'JTBD', 'API workflows', and 'step descriptions' creates a distinct trigger profile unlikely to conflict with general documentation or code generation skills.	3 / 3
	Total	11 / 12 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (510 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: mulesoft/mulesoft-dx
Commit: 32e2b58

Reviewed: 24 days ago

Table of Contents

Discovery Implementation Validation

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.