AgentStack
SKILL verified MIT Self-run

Jtbd Job Mapper

skill-lishix520-jtbd-skills-jtbd-job-mapper · by lishix520

Build or audit a solution-free Universal Job Map for a defined Core Functional Job. Use when asked to decompose a customer's functional job into Define, Locate, Prepare, Confirm, Execute, Monitor, Modify, and Conclude steps; identify missing, misordered, solution-specific, or vendor-centric job-map steps; or prepare a validated job map for ODI desired-outcome research.

No reviews yet
0 installs
1 views
0.0% view→install

Install

$ agentstack add skill-lishix520-jtbd-skills-jtbd-job-mapper

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README — it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-lishix520-jtbd-skills-jtbd-job-mapper)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
yesterday

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Jtbd Job Mapper? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

JTBD Universal Job Mapper

Map how a job executor completes an already-defined Core Functional Job.

A job map describes the customer's functional process, not a product workflow, feature list, purchase journey, vendor process, or current solution.

Scope

Input must include:

  • A Core Functional Job statement
  • A job executor, confirmed or explicitly marked as a hypothesis
  • Evidence, a domain description, or an explicit request to produce a provisional map

Output:

  • Job-map stages and a functional dependency flow using Universal Job Map categories
  • Evidence and confidence for each step
  • Explicit gaps, alternative paths, and non-applicable stages
  • A map suitable as input to jtbd-outcome-engineer

Do not:

  • Redefine the Core Functional Job
  • Add desired outcomes, features, products, technologies, or performance claims
  • Treat the current workflow as the ideal job map
  • Force all eight stages to contain a step
  • Infer missing steps as facts without evidence
  • Calculate opportunities or recommend product strategy

Universal Job Map categories

Use these categories as an organizing framework:

  1. Define — determine objectives, constraints, criteria, or plan
  2. Locate — identify, gather, access, or obtain required inputs
  3. Prepare — arrange, configure, organize, or make inputs ready
  4. Confirm — verify readiness, validity, completeness, or appropriateness
  5. Execute — perform the central action that advances the job
  6. Monitor — observe progress, status, output, or changing conditions
  7. Modify — correct, adjust, adapt, or refine when required
  8. Conclude — finalize, preserve, communicate, hand off, or close the job

A category may be:

  • present: supported by direct evidence or an explicitly labeled domain rationale
  • conditional: occurs only in stated circumstances
  • not_applicable: genuinely irrelevant to this job
  • unknown: insufficient evidence; do not invent a step

Step rules

Every step must:

  1. Use the job executor's perspective.
  2. State a functional action, not a product feature, channel, technology, vendor activity, or internal company process.
  3. Be solution-free and outcome-free.
  4. Represent an observable part of completing the core job, not a separate independent job.
  5. Be mutually distinguishable from adjacent steps.
  6. Be ordered by functional dependency, not necessarily by current product workflow.
  7. Be concise: one primary action per step.
  8. Preserve loops and branches when evidence requires them; do not force a linear path.

Procedure

  1. Validate that the input Core Functional Job is present and solution-free.
  2. Confirm the job executor. If unknown, return insufficient_input.
  3. Extract direct evidence and label assumptions separately.
  4. For each Universal Job Map category, identify supported candidate actions.
  5. Mark unsupported categories as unknown or not_applicable; never fill them merely for completeness.
  6. Check that each step advances the specified Core Functional Job.
  7. Identify loops, branches, and conditional steps using flow.edges.
  8. Audit for solution, outcome, vendor, purchase, and lifecycle contamination.
  9. Return the map and the smallest next research question needed to resolve the highest-impact uncertainty.

Validation checklist

Reject, remove, or rewrite any step that:

  • Names a brand, product, feature, technology, interface, channel, or implementation
  • Includes performance criteria such as fast, accurate, safe, cheap, easy, reliable, or seamless
  • Describes the vendor's internal process
  • Describes buying, receiving, installing, learning, maintaining, repairing, or disposing of a solution
  • Is an emotional or social objective
  • Repeats another step without a distinct functional role
  • Is a different independent job
  • Exists only because the eight-step template demands it

Output format

job:
  core_functional_job: ""
  status: accepted | candidate | rejected
  job_executor:
    value: ""
    status: confirmed | inferred | unknown

map_status: provisional | evidence_supported | insufficient_input

stages:
  - category: define | locate | prepare | confirm | execute | monitor | modify | conclude
    applicability: present | conditional | not_applicable | unknown
    steps:
      - statement: ""
        status: evidence_supported | hypothesis
        basis: direct_evidence | domain_rationale | explicit_request
        evidence: []
        assumptions: []
    notes: ""

flow:
  edges:
    - from: define | locate | prepare | confirm | execute | monitor | modify | conclude
      to: define | locate | prepare | confirm | execute | monitor | modify | conclude
      when: "" # optional condition for loops or branches
  branches: []

excluded_items:
  - statement: ""
    classification: solution | desired_outcome | vendor_activity | lifecycle_activity | emotional_job | social_job | separate_job
    reason: ""

evidence_gaps: []
next_research_question: ""

Reference materials

Read references/universal-job-map-rules.md before:

  • Mapping a job with ambiguous stage boundaries
  • Auditing an existing job map
  • Deciding whether a category is conditional or not applicable
  • Handling loops, repeated execution, or non-linear workflows

Read examples/valid-job-maps.md for expected scope and granularity. Read examples/invalid-job-maps.md when correcting common errors.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.