agentsclimarketplace
Sign in

Aipom workflow opportunity advisor

Skill deanpeters/ai-product-operating-model-skills/skills/aipom-workflow-opportunity-advisor

Identify which product-team decision or productive workflow should be redesigned with AI first, based on outcome value, friction, evidence, consequence, and readiness.From its SKILL.md

Install
npx -y skills add deanpeters/ai-product-operating-model-skills --skill aipom-workflow-opportunity-advisor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • 26 days oldThe repository was created 26 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

4.5 KB, 694 tokens by cl100k_base, as published. Nobody here has run it

AIPOM Workflow Opportunity Advisor

What Is It

Choose the product-team decision or productive motion where redesign with AI could create meaningful value and responsible learning. Start with work and outcomes, not a tool looking for a task.

Why Use It

Automating low-value artifact production can increase volume while leaving slow decisions, weak evidence, and rework untouched. This advisor directs redesign toward consequential friction.

When to Use It

Use when teams have many AI workflow ideas, adoption is tool-led, or the organization needs one bounded redesign target.

What It Produces

  • Candidate workflow comparison
  • Recommended first redesign and rationale
  • Readiness, consequence, and evidence gaps
  • Baseline and next mapping or pilot action

Who Should Participate

Include people who perform and receive the work, Product Operations, a Product Manager, and design, research, engineering, or governance partners as needed.

Evidence to Bring

Bring actual workflows, decisions, cycle time, wait time, rework, quality failures, user impact, context inputs, exceptions, and current measures.

How to Do It

  1. Recognize supplied workflows and desired outcomes.
  2. Identify the decision each workflow enables—not merely its artifacts.
  3. Compare outcome importance, frequency, friction, evidence loss, rework, consequence, and context readiness.
  4. Exclude work where the problem is unclear, authority is unsafe, or a simpler non-AI fix dominates.
  5. Present the strongest options and recommend one bounded starting point.
  6. Define baseline, owner, first mapping action, and success evidence.

Facilitation Protocol

Use guided, context-dump, or best-guess mode. Ask only questions that change selection. Present numbered candidates with fit, risk, and learning value; accept combined or custom choices.

Decision Logic

Prefer workflows with an important repeated decision, observable friction, accessible evidence, manageable consequence, and a bounded path to learning. Defer workflows with unclear purpose, missing authority, unavailable context, or irreversible consequences. Recommend process simplification when AI adds no material advantage.

Completion Criteria

Finish with one priority motion, alternatives considered, evidence and assumptions, baseline, human owner, next mapping or pilot step, and unresolved readiness gaps.

Key Concepts

  • Productive motion means a repeatable pattern that improves a decision or outcome.
  • Artifact speed is not decision quality.
  • AI fit depends on context and consequence, not task popularity.
  • Redesign before automation.

Organizational Applications

Use for discovery synthesis, evidence review, prioritization, roadmap learning, customer-feedback routing, and decision preparation.

Common Pitfalls

  • Selecting the easiest document to generate
  • Automating an unclear or broken process
  • Ignoring review burden and affected users
  • Measuring usage rather than the decision or outcome
  • Attempting an end-to-end transformation as the first test

Combine With

Use aipom-productive-motion-map to understand current work, human-aipom-work-contract to assign responsibilities, and aipom-workflow-playbook-builder after the redesigned motion works.

Assets and Templates

Sources

This advisor is an original AIPOM synthesis of workflow redesign and evidence-based product practice.

What ships with it: 3 files

1.2 KB alongside SKILL.md

examples/

Gives 0 of the 12 instructions most automation workflows skills give in 694 tokens

Counted across 745 of the 1,008 authors here whose files we hold, read 2026-08-07

  • Write conventional commit messagesin 36 of 745, across 35 files
  • Delete branches after mergein 30 of 745, across 21 files
  • Make atomic commitsin 25 of 745, across 15 files
  • Write minimal code to pass testsin 22 of 745, across 10 files
  • Re-snapshot after navigation or DOM changesin 21 of 745, across 13 files
  • Use try-catch for error handlingin 20 of 745, across 8 files
  • Run tests before committingin 20 of 745, across 12 files
  • Write tests before implementationin 20 of 745, across 8 files
  • Configure branch protection rulesin 19 of 745, across 5 files
  • Explain the why in commit messagesin 19 of 745, across 9 files
  • Refactor code while tests remain greenin 19 of 745, across 6 files
  • Interact with elements using refsin 19 of 745, across 11 files

Said here and by no other author read

  • start with work and outcomes
  • identify the decision each workflow enables
  • compare workflows by outcome friction and consequence
  • exclude work with unclear problems or unsafe authority
  • present strongest options and recommend one bounded start
  • define baseline owner and success evidence

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,645. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.