CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

jobs-to-be-done

Use when asked to "jobs to be done", "JTBD", "why customers churn", "prep for customer interviews", "hire and fire products", or "find real competitors". Helps discover unmet needs and the context behind purchasing decisions. The Jobs to be Done framework (created by Clayton Christensen and Bob Moesta) explains why customers hire and fire products.

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/jobs-to-be-done/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

26%Weight 40%Scale 1-5

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

The body is a conceptual overview of JTBD rather than a working skill: it explains what the framework is (which Claude already knows), lists when to use it, and cites books, but provides no executable method, templates, or sequenced process for actually doing JTBD work. Its strongest aspect is compact, headed structure with no bundle sprawl. The main fixes are to cut the primer/fluff and replace it with concrete JTBD working materials.

Suggestions

Replace the 'What It Is' primer with executable JTBD working materials: a job-story template ('When [situation], I want to [motivation], so I can [expected outcome]'), a starter interview question bank, and the four forces of progress (push, pull, anxiety, habit).

Add a sequenced workflow with checkpoints, e.g., 1. identify the struggling moment from the user's context, 2. map the four forces for the customer, 3. draft job stories, 4. validate them against churn or switching data if available.

Delete the 'Domain Context' and 'Input Requirements' sections and the JTBD-101 explanation — Claude already knows the framework, and the reclaimed tokens should fund the missing method; merge 'Resources' and 'Further Reading' into one section.

DimensionReasoningScore

Conciseness

Several sections are unnecessary: 'Domain Context' is padded fluff ('combines best practices from industry leaders', 'proven product management framework') and 'What It Is' re-explains JTBD basics Claude already knows ('people don't buy products, they hire them to make progress in their lives'), plus a largely filler 'Input Requirements' list. Scored 2 rather than 3 because roughly half the body could be deleted without losing actionable information.

2 / 5

Actionability

The only operational guidance is a single high-level reframe — 'Move from asking "What do customers want?" to asking "What progress are customers trying to make?"' — with no job-story template, interview questions, forces-of-progress mapping, or analysis steps. This matches 'minimal concrete guidance; high-level hints but missing the specific steps to execute' (2); not 1 because one actionable reframe and explicit applicability conditions ('When Not to Use It') are given.

2 / 5

Workflow Clarity

No sequence of steps exists anywhere in the body — it describes the framework and when/when-not to apply it but never instructs how to proceed (e.g., prepare an interview, map forces, draft job stories). This matches anchor 1 ('steps missing; no sequence'); the simple-skill exception doesn't apply because the intended action is not unambiguous, and anchor 2 requires at least a rough sequence, which is absent.

1 / 5

Progressive Disclosure

The body is ~50 lines with no bundle files and clearly headed sections ('What It Is', 'When to Use It', 'When Not to Use It', 'Further Reading' with a single one-level external link), satisfying the short-skill guideline. Minor organization gaps — duplicate heading hierarchies (H2 sections before a mid-document H1) and separate 'Resources' and 'Further Reading' sections that fragment the same content — keep it at 4 rather than 5.

4 / 5

Total

9

/

20

Passed

Description

70%Weight 40%Scale 1-5

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 is well-constructed: it leads with an explicit 'Use when' clause containing natural, varied trigger phrases including the framework acronym, and follows with a statement of what it does. Its main weakness is that the 'what' ('Helps discover unmet needs and the context behind purchasing decisions') and the framework attribution sentence stay at a generic level rather than naming concrete deliverables. Strong trigger coverage makes it clearly distinguishable in most cases, with modest overlap risk on the interview-prep and competitor triggers.

DimensionReasoningScore

Specificity

Names the domain ('The Jobs to be Done framework') and 1-2 actions — 'Helps discover unmet needs and the context behind purchasing decisions' — which parallels 'Processes PDF files and extracts content'. Not 2 because two concrete outcomes are explicitly stated; not 4 because the actions are generic PM language and no broader set of specific capabilities is given.

3 / 5

Completeness

The 'when' is explicit with concrete trigger phrases ('Use when asked to "jobs to be done", "JTBD", "why customers churn"...') and the 'what' is present ('Helps discover unmet needs and the context behind purchasing decisions'), but the what stays vague about what the skill actually does operationally. Both present with one side improvable matches 4; the when here is stronger than anchor 4's example, but the what is weaker than anchor 5's fully concrete action list.

4 / 5

Trigger Term Quality

Includes natural phrases users would actually say — 'jobs to be done', 'JTBD', 'why customers churn', 'prep for customer interviews', 'hire and fire products', 'find real competitors' — covering both the full term and its acronym. A few natural variants are missing (e.g., 'customer motivation', 'why customers buy', 'customer needs'), so 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

Triggers like 'JTBD' and 'hire and fire products' are distinctive to this framework, giving a clear niche. However 'prep for customer interviews' and 'find real competitors' overlap with generic user-research and competitive-analysis skills — minor overlap risk with closely related skills, matching anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

saski/arnesto

Path

.agents/skills/jobs-to-be-done/SKILL.md

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.