Marketing Tools / Ads Ops

Task Map Designer

Convert customer situations into testable task and context hypotheses for agent-mediated advertising and commerce.

DocumentationAgent instructionsRequirements & limits

Use when an advertising or commerce experiment should begin from a customer task rather than a keyword or placement list.

Inputs

The released example shows these fields. Check the guide for which are required.

  • brand
  • situation
  • constraints
  • evidence

Outputs

  • Task map
  • Testable hypotheses
  • Measurement plan

Before you begin

  • Reading and copying the procedure require no terminal setup. Check requirements for any packaged programs separately.

Try this first

Read the procedure and supply its documented inputs. Use the full text in an agent app or chat that supports pasted instructions, following that host's guidance.

Limits for this step
  • Instruction package only; it does not provide or authorize an executable runtime capability.
  • Advisory planning only; targeting, activation, and data collection require platform and privacy approval.
Read full instructionsHide full instructionsSKILL.md · v0.1.0

Task Map Designer

When to use

Use this skill for the situations described in its frontmatter routing description.

Workflow

  1. Define the customer task as an observable job with a completion condition.
  2. Separate known evidence from assumptions about context, constraints, and decision criteria.
  3. Break the task into discovery, comparison, decision, transaction, and post-purchase stages as applicable.
  4. Record which brand capabilities can help at each stage.
  5. Write one falsifiable hypothesis per task-context pair.
  6. Define exposure, selection, completion, and quality measures.
  7. Return a task map that conforms to shared/schemas/advertising/task-map.schema.json.

Output

  • task_id and task statement
  • audience situation and context signals
  • constraints and decision criteria
  • required brand capabilities
  • testable hypothesis
  • channel routes: paid placement, earned discovery, executable participation
  • measures and disconfirming evidence

Guardrails

  • Do not infer sensitive traits from conversational context.
  • Do not convert weak assumptions into targeting facts.
  • Keep task hypotheses channel-neutral until evidence supports a route.
  • Distinguish customer completion from an ad click or platform conversion.
View file metadata
---
name: task-map-designer
description: Convert customer situations into testable advertising task and context hypotheses. Use when planning conversational, agent-mediated, search, social, or commerce experiments around what a person is trying to complete rather than around keyword lists alone.
---

Summary sources · Catalogue metadata, skill.yaml, SKILL.md, examples/input.json, examples/output.json · v0.1.0 · Release package

Install instruction files

These commands copy guidance into the selected runtime directories. Confirm that your agent app discovers it. Any packaged programs need separate setup and verification.

Install (Codex)

./bin/skills-hub install marketing/[email protected] --runtime codex

Install (Claude)

./bin/skills-hub install marketing/[email protected] --runtime claude

Install (Generic)

./bin/skills-hub install marketing/[email protected] --runtime generic --target ./my-agent/skills

How You Can Use This

Documentation

Resource form: Agent instructions

Read or copy the guidance. Any packaged programs have separate execution requirements and evidence.

First run: Read SKILL.md and follow the documented workflow.

Current limits

  • Instruction package only; it does not provide or authorize an executable runtime capability.
What installation and verification mean
File installation
Places package files and generated configuration in the selected directories.
Native discovery
Your agent app finds and accepts the instructions, tools or plugin registrations.
Mock execution
Exercises sample fixtures. Connected data and provider effects need a separate check.
Connected operation
Requires current configuration, provider authentication, scoped permissions and a successful operation in your intended environment.

Declared compatibility

Compatibility unknown: versions and capabilities have not been declared.

Classification: declared

Technical details and release files

Operational Summary

Execution mode: analysis-only

Approval boundary: Advisory planning only; targeting, activation, and data collection require platform and privacy approval.

Review and lifecycle

Review maturity: Experimental

Security review declaration: Not declared

Lifecycle: Active

These release declarations are separate from evidence that a workflow operates in your environment.

Runtime & Dependencies

ID: marketing/task-map-designer

Tags: task-design, chatgpt-ads, experimentation, agentic-commerce, planning

Runtimes: codex, claude, generic

Tool dependencies: 1

API dependencies: 0

Dependencies

Tools: shared/schemas/advertising/task-map.schema.json

APIs: Not documented

Outputs

  • Task map
  • Testable hypotheses
  • Measurement plan