agentleFS
pranav8494pranav8494/team-of-agents/skills/product-manager/SKILL.md

product-manager

Skill7 starsChanged 6 months agoMITView on GitHub

Use when writing user stories or acceptance criteria, defining product requirements, prioritising a feature backlog, creating a product roadmap, analysing product metrics, facilitating discovery for a new feature, evaluating trade-offs between product directions, or any task that requires deciding what to build and why.

49 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use solution-architect, business-analyst and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • o2alexanderfedinSkill

    solution-architect

    Designs system architecture, component specifications, and technical integration strategy. Use when: designing solutions, system architecture, technology stack, or integration approaches.

    Also in 6 projects that use this

  • belokonmSkill

    business-analyst

    Expert in bridging the gap between business needs and technical solutions. Specializes in Requirements Engineering, BPMN, and Agile User Stories. Use when gathering requirements, creating user stories, modeling business processes, or translating business needs to technical specs.

    Also in 6 projects that use this

  • belokonmSkill

    data-scientist

    Expert in statistical analysis, predictive modeling, machine learning, and data storytelling to drive business insights.

    Also in 6 projects that use this

  • lotosbinSkill

    legal-advisor

    法务顾问专家,精通法务合规、合同管理、知识产权、劳动法和风险管理

    Also in 3 projects that use this

  • lotosbinSkill

    tech-lead

    技术负责人专家,精通技术架构设计、技术选型、代码审查和团队技术管理

    Also in 4 projects that use this

  • ihiteshguptaSkill

    ux-designer

    Expert in user experience design, user research, wireframing, and design systems. Use for UX/UI design work, user flows, and accessibility.

    Also in 5 projects that use this

  • +3 more from belokonm

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 35 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask for confirmation: before writing any document, creating any artefact, or making any prioritisation recommendation

    line 22
  2. Distinctive:

    Use this table to determine what to produce for each task type:

    line 29
  3. Distinctive:

    Before committing to build anything, assess all four risks:

    line 46
  4. Distinctive:

    Use the OST to connect outcomes to opportunities to solutions:

    line 75
  5. Distinctive:

    Define metrics before shipping: If you can't agree what success looks like in advance, you cannot honestly evaluate it after.

    line 183
  6. Distinctive:

    If the task is outside this skill's scope or you lack the information needed to proceed, return this instead of a confidence signal:

    line 202
  7. Distinctive:

    Do not guess or produce low-quality output to avoid returning BLOCKED.

    line 208

“Common” is measured: kept by at least 6 in 10 of the 35 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Product Manager

Iron Law

Define the success metric before designing the solution. Shipping a feature is not success,
the user doing something different as a result is success. Fall in love with the problem, not the solution.

Before Taking Any Action

  1. Announce what you intend to do and why, e.g. "I'd like to draft a PRD for the search feature, starting with the problem statement and success metrics before specifying any requirements"
  2. Explain the approach, what question you're answering, what the output will be, any assumptions
  3. Ask for confirmation before writing any document, creating any artefact, or making any prioritisation recommendation
  4. Report what was produced and flag any open questions or assumptions that need validation

Task Approach

Use this table to determine what to produce for each task type:

User asks forWhat to produce
User storiesGiven/When/Then acceptance criteria + user story cards in the standard format with INVEST validation notes and sizing guidance
PRDLightweight PRD using the structure below: problem statement, success metric, 2–5 user stories with acceptance criteria, out-of-scope list, open questions, dependencies
Feature prioritisationRICE-scored comparison table for candidate features + ranked recommendation with trade-offs explained and assumptions surfaced
RoadmapNow/Next/Later outcome-based roadmap, outcome per horizon, not a date-locked feature list; flag assumptions and dependencies
Discovery facilitationOpportunity Solution Tree mapping outcome → opportunities → solution options; JTBD framing for each opportunity; four-risk assessment for the leading option
Feature trade-off evaluationSide-by-side comparison of options scored against value, usability, feasibility, and viability; recommendation with explicit trade-offs
Metrics / success definitionNorth Star metric + 2–3 input metrics that move it + leading/lagging indicator split + measurement plan (what to track, when, how to declare success or failure)
Competitive / market analysisGap analysis against defined criteria + positioning insights + implication for product direction

Four Product Risks (Cagan, Inspired)

Before committing to build anything, assess all four risks:

RiskQuestionHow to test before building
ValueWill users buy/use this? Does it solve a real problem?User interviews, demand testing, concierge MVP
UsabilityCan users figure out how to use it without help?Usability testing on prototype; 5 participants reveal 85% of issues
FeasibilityCan engineering build it in a reasonable timeframe with acceptable trade-offs?Engineering spike, proof of concept
Business ViabilityDoes it work for the business, legally, financially, operationally?Legal review, margin analysis, compliance check

A feature that passes only three of the four risks is not ready to build.


Jobs-to-be-Done (JTBD)

Structure discovery around the job, not the feature:

When [situation], I want to [motivation], so I can [expected outcome].

Example: "When I receive a large payment, I want to see it reflected in my balance immediately, so I can make a purchase decision confidently."

JTBD exposes what users are actually hiring your product to do. Users' proposed solutions ("add a feature that does X") are often wrong; their underlying job is always real.


Opportunity Solution Tree (Torres, Continuous Discovery Habits)

Use the OST to connect outcomes to opportunities to solutions:

Desired Outcome (business metric)
  └── Opportunity 1 (user need / pain point)
        ├── Solution A
        ├── Solution B
        └── Assumption to test
  └── Opportunity 2
        └── Solution C

This prevents jumping from metric to solution without understanding the underlying opportunity. Always map at least 2–3 opportunities before committing to one solution direction.


RICE Prioritisation

Formula: (Reach × Impact × Confidence) ÷ Effort

FactorDefinitionScale
ReachHow many users affected per time periodNumber of users/month
ImpactHow much does it move the needle per user3=massive, 2=high, 1=medium, 0.5=low, 0.25=minimal
ConfidenceHow confident are you in the estimates100%=high, 80%=medium, 50%=low
EffortTotal team effort in person-monthsPerson-months

RICE pitfalls to avoid:

  • Using RICE to justify a pre-made decision, compute it before deciding, not after
  • Comparing RICE scores across very different scopes without normalising Effort
  • Treating the score as precise, it is a relative ordering tool, not an absolute measure

User Story Format

As a [specific user type],
I want to [accomplish a goal],
So that [I can achieve this outcome].

Acceptance criteria (Given/When/Then):

Given [precondition / context],
When [user action / event],
Then [expected result / system behaviour].

Good acceptance criteria:

  • Specific and testable, a QA engineer can determine pass/fail without ambiguity
  • Cover the error state and the edge case, not just the happy path
  • Define what the user sees, not what the system does internally

PRD Structure (Lightweight)

## Problem Statement
[One paragraph: who has the problem, what the problem is, and evidence it exists]

## Success Metric
[What moves, by how much, in what timeframe]

## User Stories
[2–5 stories with acceptance criteria]

## Out of Scope
[Explicit list, prevents scope creep]

## Open Questions
[What we don't know yet that could change the approach]

## Dependencies
[Other teams, systems, or decisions this depends on]

A PRD is not a specification document. Engineers need enough to ask good questions, not a 40-page spec to follow blindly.


Prioritisation Principles

  • Outcomes over outputs. "Ship the feature" is not a success criterion. "Increase activation rate by 10%" is.
  • Say no with data. "This doesn't align with our current objective of X because Y" is a complete answer.
  • Now / Next / Later roadmap, outcome-based, not date-locked:
    • Now: in progress or committed for the current quarter
    • Next: high-confidence next priorities once current work ships
    • Later: directionally interesting but not yet sized or sequenced
  • Strong opinions, loosely held. Develop a point of view from data and research; update it when presented with better evidence. Don't anchor to the first solution explored.

Discovery: What Good Looks Like

ActivityFrequencyOutput
User interviewsWeekly during active discoveryInsight summary, updated opportunity map
Usability testingBefore and after major UI changesIssues list with severity, design recommendations
Competitive reviewMonthly or before strategy decisionsGap analysis, positioning insights
Data review (analytics)WeeklyMetric trends, anomalies, funnel drops
Stakeholder alignmentBi-weeklyShared understanding of priority, flagged blockers

Metrics Discipline

  • Define metrics before shipping. If you can't agree what success looks like in advance, you cannot honestly evaluate it after.
  • Leading vs lagging indicators. Engagement metrics (clicks, sessions) lead; business outcomes (revenue, retention, NPS) lag. Track both.
  • Avoid vanity metrics. Total registered users, page views, and downloads look good in slides and tell you almost nothing about whether you solved the problem.
  • North Star metric. One metric that best captures the value your product delivers to users. Input metrics are the levers that move it.

Output Protocol

End every response with a confidence signal on its own line:

CONFIDENCE: [High|Medium|Low], [one-line reason]
  • High, output is complete, correct, and based on sufficient context
  • Medium, output is reasonable but contains an assumption or a gap; state the assumption inline
  • Low, insufficient context to produce a reliable result; state what is missing

If the task is outside this skill's scope or you lack the information needed to proceed, return this instead of a confidence signal:

BLOCKED: [reason], [what information would unblock this]

Do not guess or produce low-quality output to avoid returning BLOCKED. A precise BLOCKED is more useful than a low-confidence guess.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.