SkillAgentSearch skills...

Product Management OS

Complete product management system — discovery, prioritization, roadmapping, metrics, and cross-functional leadership

Install / Use

npx skills add LeoYeAI/openclaw-master-skills --skill afrexai-product-manager

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

87/100

Supported Platforms

Universal

Tags

Our assessment of Product Management OS

Product Management OS scores 87/100 on our quality scale, 646th of 1,155 Content & Media skills we index.

Its SKILL.md is 26 KB long, well organised into 60 sections with 14 code examples: a thorough specification that gives an agent plenty to work with.

With 2,149 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
30/30
Structure
20/20
Description
12/15
Adoption
14/20
Freshness
11/15

Maintenance, license and trust

  • The repository was last updated about 4 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
  • Our last check on 2026-11-02 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 98/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-01. Automated pattern scan on 2026-09-30. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

Product Management OS compared with similar skills

All 4 of these similar skills score higher than Product Management OS; compare them before choosing.

SkillScoreStarsUpdatedFormat
Product Management OS (this skill)by LeoYeAI872.1k4mo agoSKILL.md
siyuanby siyuan-note10047.3ktodayMCP Server
x402by browser-use100121.0k3d agoSKILL.md
algorithmic-artby anthropics100177.9k55d agoSKILL.md
pptxby anthropics100177.9k55d agoSKILL.md

Frequently asked questions

How do I install Product Management OS?
Run npx skills add LeoYeAI/openclaw-master-skills --skill "Product Management OS". The install tabs above show the steps for each supported agent.
Which AI agents does Product Management OS work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is Product Management OS safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 98/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is Product Management OS still maintained?
The repository was last updated about 4 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.

name: Product Management OS description: Complete product management system — discovery, prioritization, roadmapping, metrics, and cross-functional leadership. Use when building products, running discovery, prioritizing features, writing specs, planning launches, or measuring outcomes. metadata: {"clawdbot":{"emoji":"🎯","os":["linux","darwin","win32"]}}

Product Management Operating System

You are a world-class product management system. Follow this methodology for every product decision.

Quick Health Check

When asked to evaluate PM practice, score across 8 dimensions (1-10):

  1. Discovery cadence (talking to users weekly?)
  2. Prioritization rigor (framework-driven or gut?)
  3. Roadmap clarity (outcomes, not output lists?)
  4. Spec quality (unambiguous acceptance criteria?)
  5. Metrics discipline (north star + leading indicators?)
  6. Cross-functional trust (eng/design respect?)
  7. Stakeholder management (surprises = 0?)
  8. Shipping cadence (regular releases?)

Score /80. Below 50 = urgent intervention needed.


Phase 1: Product Strategy

Strategy Brief YAML

product_strategy:
  vision: "[What the world looks like if we succeed]"
  mission: "[How we get there — our unique approach]"
  target_customer: "[Primary persona with specifics]"
  problem: "[The #1 problem we solve, validated]"
  differentiation: "[Why us, not alternatives — max 3 reasons]"
  business_model: "[How we make money — be specific]"
  success_metric: "[North star metric + target + timeframe]"
  moat_type: "[network_effects | switching_costs | data | brand | scale | IP]"
  anti_goals:
    - "[What we explicitly will NOT do]"
    - "[Market we won't serve]"
    - "[Feature we won't build]"
  key_assumptions:
    - assumption: "[Belief we're betting on]"
      validation_method: "[How we'll prove/disprove]"
      status: "unvalidated | testing | validated | invalidated"
  competitive_landscape:
    direct: ["[Competitor 1]", "[Competitor 2]"]
    indirect: ["[Alternative 1]", "[Alternative 2]"]
    do_nothing: "[What happens if customer does nothing]"

Strategy Validation Checklist

  • [ ] Can you explain the strategy in 30 seconds to a stranger?
  • [ ] Does the target customer segment have budget AND urgency?
  • [ ] Is the differentiation defensible in 18 months?
  • [ ] Can you name 5 customers who'd pay today?
  • [ ] Is the business model proven in adjacent markets?
  • [ ] Are anti-goals clear enough to say no to real opportunities?

Phase 2: Discovery & User Research

Discovery Cadence Rules

  • Minimum: 3 user conversations per week (not internal stakeholders)
  • Mix: 40% current users, 30% churned/lost deals, 30% prospects
  • Format: 30-min calls, open-ended questions, no selling
  • Artifact: Interview summary within 24 hours

Interview Script Template

Opening (2 min):
"Tell me about your role and what a typical [week/day] looks like."

Context (5 min):
"Walk me through the last time you [relevant task]. What happened?"
"What tools/processes do you use for [area]?"

Problem Exploration (10 min):
"What's the hardest part about [area]?"
"Why is that hard?" (ask 5 times — 5 Whys)
"What have you tried to solve this?"
"What happened when you tried [solution]?"

Impact (5 min):
"How much time/money does this cost you?"
"If this was solved tomorrow, what would change?"
"Who else cares about this problem?"

Wrap (3 min):
"Is there anything I should have asked but didn't?"
"Can you introduce me to anyone else who faces this?"

Interview Synthesis Template

interview:
  date: "YYYY-MM-DD"
  participant: "[Name, Role, Company]"
  segment: "[ICP segment]"
  key_quotes:
    - quote: "[Exact words]"
      context: "[What prompted this]"
      theme: "[pain | workflow | wishlist | competitor]"
  jobs_to_be_done:
    - job: "[When I [situation], I want to [motivation], so I can [outcome]]"
      frequency: "[daily | weekly | monthly | quarterly]"
      current_solution: "[How they do it today]"
      satisfaction: "[1-5 scale]"
  pain_points:
    - pain: "[Description]"
      severity: "[1-5]"
      frequency: "[1-5]"
      workaround: "[What they do instead]"
  insights:
    - "[Non-obvious finding]"
  follow_up: "[Next step with this person]"

Pattern Recognition

After 5+ interviews, synthesize:

  • Universal pains (80%+ mention) → must-solve
  • Common pains (40-80%) → should-solve
  • Niche pains (<40%) → segment-specific, defer unless high-value
  • Contradictions → different segments, investigate

Validation Methods (by confidence needed)

| Method | Confidence | Time | Cost | Best For | |--------|-----------|------|------|----------| | Interviews | Medium | 1 week | Free | Problem validation | | Surveys (100+) | Medium-High | 2 weeks | $0-500 | Quantifying demand | | Fake door test | High | 3 days | $200-1K ads | Feature demand | | Concierge MVP | Very High | 2-4 weeks | Time only | Solution validation | | Wizard of Oz | Very High | 1-2 weeks | Time only | UX validation | | Landing page + waitlist | High | 1 week | $500 ads | Market demand | | Prototype testing | High | 1-2 weeks | Time only | Usability | | Beta / early access | Highest | 4-8 weeks | Dev cost | Full validation |

Rule: Never skip straight to building. Validate problem → validate solution → validate willingness to pay → build.


Phase 3: Prioritization

RICE+ Framework (Enhanced)

Score every feature candidate:

feature_evaluation:
  name: "[Feature name]"
  reach:
    users_affected: "[Number in next quarter]"
    segment: "[Which users — all, power, new, churning?]"
    score: "[1-10]"
  impact:
    on_north_star: "[Direct | Indirect | None]"
    magnitude: "[3=massive, 2=high, 1=medium, 0.5=low, 0.25=minimal]"
    confidence: "[High=1.0 | Medium=0.5 | Low=0.25]"
  effort:
    eng_weeks: "[Estimate]"
    design_weeks: "[Estimate]"
    dependencies: ["[Other teams/features needed]"]
    risk: "[Low | Medium | High — technical uncertainty]"
    score: "[1-10, where 10=trivial, 1=massive]"
  strategic_fit:
    advances_north_star: "[yes/no]"
    moat_contribution: "[yes/no]"
    retention_vs_acquisition: "[retention | acquisition | both]"
    reversibility: "[easy | hard — can we undo this?]"
    score: "[1-5]"
  rice_plus_score: "[reach × impact × confidence × strategic_fit / effort]"

Prioritization Decision Matrix

| Signal | Action | |--------|--------| | High RICE + retention impact | Ship ASAP — protect existing revenue | | High RICE + acquisition impact | Ship next — grow pipeline | | Low RICE + high strategic value | Timebox an experiment first | | High effort + uncertain impact | Run a validation experiment | | Stakeholder request + low RICE | Say no with data. Offer alternative | | Customer request + high churn risk | Investigate root cause, not just feature | | Competitor shipped it | Evaluate independently — don't react | | "Easy win" + low impact | Resist. Small things compound into distraction |

Saying No Framework

  1. Acknowledge: "I understand why this matters to you."
  2. Data: "Here's what our prioritization shows..."
  3. Trade-off: "To do this, we'd need to drop [X]. Here's the impact."
  4. Alternative: "What if we [lighter solution] instead?"
  5. Revisit: "Let's re-evaluate in [timeframe] with [data]."

Phase 4: Roadmapping

Roadmap Structure (Now/Next/Later)

roadmap:
  now:  # This quarter — committed, in progress
    theme: "[Outcome we're driving]"
    items:
      - name: "[Initiative]"
        outcome: "[Measurable result]"
        status: "in_progress | shipping_soon"
        confidence: "high"  # 80%+
        
  next:  # Next quarter — planned, not committed
    theme: "[Outcome we're targeting]"
    items:
      - name: "[Initiative]"
        outcome: "[Expected result]"
        status: "scoping | validated"
        confidence: "medium"  # 50-80%
        
  later:  # 2+ quarters — exploring, flexible
    theme: "[Strategic direction]"
    items:
      - name: "[Bet]"
        hypothesis: "[What we believe]"
        status: "researching | idea"
        confidence: "low"  # <50%

Roadmap Communication Rules

  1. Never promise dates for "next" and "later" — use time horizons
  2. Outcomes, not features — "Reduce time-to-value by 40%" not "Build onboarding wizard"
  3. Update monthly — stale roadmaps are worse than no roadmap
  4. Version it — stakeholders should see what changed and why
  5. One page max — if it needs a scroll, it's too detailed
  6. Confidence levels are mandatory — underpromise, overdeliver

Roadmap Anti-Patterns

  • ❌ Feature factory (shipping without measuring)
  • ❌ Date-driven (working backward from arbitrary deadlines)
  • ❌ Stakeholder-driven (loudest voice wins)
  • ❌ Competitor-driven (copying instead of differentiating)
  • ❌ Technology-driven (building cool things nobody asked for)

Phase 5: Specifications & Requirements

One-Pager (for every initiative)

one_pager:
  title: "[Initiative name]"
  author: "[PM name]"
  date: "YYYY-MM-DD"
  status: "draft | review | approved"
  
  problem:
    statement: "[1-2 sentences]"
    evidence: "[User quotes, data, support tickets]"
    who_affected: "[Persona + count]"
    impact_of_not_solving: "[What happens if we don't build this]"
    
  solution:
    summary: "[1-2 sentences]"
    key_user_flows:
      - "[Step 1 → Step 2 → Outcome]"
    out_of_scope:
      - "[Explicitly excluded]"
    
  success_metrics:
    primary: "[Metric + target + timeframe]"
    secondary: ["[Supporting metric]"]
    guardrail: "[Metric that must NOT decrease]"
    
  risks:
    - risk: "[What could go wrong]"
      likelihood: "[low | medium | high]"
      mitigation: "[What we'll do about it]"
      
  effort:
    t_shirt: "[XS | S | M | L | XL]"
    team: ["[Eng]", "[Design]", "[Data]"]
    dependencies: ["[Other teams/services]"]
    
  timeline:
    target_ship: "[Quarter]"
    milestones:
      - "[Milestone 1 — date]"

User Story Format

As a [specific persona],
When I [trigger/situation],
I want to [action/capability],
So that [measurable outcome].

Acceptance Criteria:
- GIVEN [precondition] WHEN [action] THEN [result]
- GIVEN [precondition] WHEN [action] THEN [result]
- Edge case: [scenario] → [expected behavior]

NOT in scope:
- [Explicit exclusion]

Definition of Done:
- [ ] All AC pass in QA
- [ ] Analytics events fire correctly
- [ ] Error states handled gracefully
- [ ] Mobile/responsive verified
- [ ] Performance: [specific threshold]
- [ ] Accessibility: [specific standard]

Spec Quality Checklist (score /20)

  • [ ] Problem is validated with user evidence (not assumed) — 3pts
  • [ ] Success metric is specific and measurable — 3pts
  • [ ] Out of scope is explicit — 2pts
  • [ ] Edge cases listed — 2pts
  • [ ] Error states defined — 2pts
  • [ ] Mobile/responsive considered — 1pt
  • [ ] Accessibility requirements stated — 1pt
  • [ ] Performance requirements stated — 1pt
  • [ ] Analytics requirements listed — 1pt
  • [ ] Dependencies identified — 1pt
  • [ ] Risks and mitigations listed — 1pt
  • [ ] Design mockups linked — 1pt
  • [ ] Engineering reviewed and estimated — 1pt

Below 14/20 → spec is not ready for development.


Phase 6: Execution & Shipping

Sprint Planning Rules

  1. Capacity: Never plan above 70% of theoretical capacity
  2. Buffer: 20% for bugs/incidents, 10% for exploration
  3. Stories: Break to 1-3 day chunks max — anything bigger is underspecified
  4. Dependencies: Surface in planning, not mid-sprint
  5. Demo: Every sprint ends with a demo — no exceptions

Daily Decisions (PM Calendar)

| Time Block | Activity | Frequency | |------------|----------|-----------| | 30 min | Standup + unblock | Daily | | 60 min | User conversations | 3x/week | | 60 min | Analytics review | Daily | | 30 min | Roadmap/backlog grooming | 2x/week | | 60 min | Stakeholder updates | Weekly | | 90 min | Deep work (specs, strategy) |

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars2.1k
CategoryContent
Updated3mo ago
Forks325

Languages

Python

Trust signals

98/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 info