jobs-to-be-done
Uncover the functional, social, and emotional jobs driving customer behavior. Use when you need to understand why customers hire, switch, or abandon products — not just what they say they want.
66
58%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./product-skills/skills/jobs-to-be-done/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description effectively communicates both what the skill does and when to use it, with a clear 'Use when' clause that provides good trigger guidance. However, it lacks specific concrete actions beyond 'uncover jobs' and misses key trigger terms like 'JTBD' or 'jobs to be done' that users would naturally use. The description would benefit from more specific capabilities and stronger domain-specific keywords.
Suggestions
Add explicit trigger terms users would naturally say, such as 'jobs to be done,' 'JTBD,' 'customer interviews,' 'switching behavior,' or 'outcome-driven innovation.'
List more concrete actions the skill performs, e.g., 'Conducts JTBD interviews, maps job stories, identifies unmet needs, creates outcome statements, and analyzes hiring/firing criteria.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (jobs-to-be-done framework) and mentions some actions like 'uncover functional, social, and emotional jobs,' but doesn't list multiple concrete actions such as conducting interviews, analyzing transcripts, mapping job maps, or creating outcome statements. | 2 / 3 |
Completeness | Clearly answers both 'what' (uncover functional, social, and emotional jobs driving customer behavior) and 'when' (when you need to understand why customers hire, switch, or abandon products) with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'customer behavior,' 'hire,' 'switch,' 'abandon,' and 'jobs' but misses common trigger terms users would naturally say such as 'jobs to be done,' 'JTBD,' 'customer research,' 'user needs,' or 'value proposition.' | 2 / 3 |
Distinctiveness Conflict Risk | The JTBD framing provides some distinctiveness, but terms like 'customer behavior' and 'what they say they want' could overlap with general customer research, persona creation, or market analysis skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a moderately well-structured analytical prompt template for JTBD analysis. Its main strengths are the comprehensive categorization of job types and the prioritization framework. Its weaknesses are the lack of concrete input/output examples, some unnecessary explanatory text about JTBD concepts Claude already knows, and missing validation steps for distinguishing evidence-based findings from inferences.
Suggestions
Add a concrete example showing sample input (e.g., a few interview quotes or feature requests) and the expected structured output, so Claude knows exactly what good JTBD analysis looks like.
Remove the introductory explanation of JTBD philosophy ('Customers don't buy products — they hire them...') since Claude already knows this framework well.
Add an explicit validation step: after generating the analysis, verify each job is supported by evidence from the input, and clearly separate evidence-backed jobs from inferred ones with confidence levels.
Specify the expected output format more precisely (e.g., markdown table for prioritization, structured sections with quote attributions) rather than leaving it open-ended.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary framing ('Customers don't buy products — they hire them to make progress in their lives') and explanatory text that Claude already knows about JTBD. The prompt template itself has useful structure but the surrounding commentary and tips section add moderate bloat. | 2 / 3 |
Actionability | The prompt template provides a structured analytical framework with clear categories and sub-bullets, which is moderately actionable. However, it's a prompt template rather than executable code/commands — there are no concrete examples of input data and expected output format, making it harder to know exactly what good output looks like. | 2 / 3 |
Workflow Clarity | The 7-step numbered list within the prompt provides a clear sequence for analysis. However, there are no validation checkpoints, no feedback loops for verifying the quality of inferences vs. evidence, and no explicit guidance on what to do when input data is insufficient — the skill just says 'flag where more research is needed' without specifying how. | 2 / 3 |
Progressive Disclosure | The content is reasonably organized with sections (prompt template, tips) but everything is in a single file with no supporting references. The mention of 'craft-discovery-synthesis' as a companion skill is a nice cross-reference, but the prompt template itself is quite long and could benefit from separating the detailed sub-criteria into a reference file. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- amplitude/builder-skills
- Commit
221ffaa
- Reviewed
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.