skills/working-with-pm/SKILL.md
Helps engineering managers build a functional PM–EM partnership and become more product-oriented — produces a 3-pattern PM–EM dynamic model (PM-Led / Engineering-Led / Fake Balanced), a true partnership definition, the "It's Important to Me" card for navigating disagreements, tips for getting engineers closer to customers and usage data (launch vs. landing, session recordings, customer conversations), and an explicit responsibilities exercise. Use when the user says "PM relationship," "PM drives me crazy," "product manager," "roadmap disagreement," "PM overrides me," "PM–EM partnership," "I want to be more product-oriented," or "how do I get engineers closer to customers." Do NOT use for general roadmap prioritization (use `roadmap-planning`) or when urgency is being manufactured by a PM (use `managing-urgency`).
npx skillsauth add manager-dot-dev/manager-skills working-with-pmInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Check for EM context first. If .agents/em-context.md exists, read it.
If .agents/em-context.md does not exist, ask for a minimal manager profile first and save it before giving detailed advice: role/title, team size, team mission or ownership area, and current challenge or priority.
If a specific person is central to the conversation and .agents/reports/[name].md does not exist, ask for a minimal profile for that person first and save it before giving detailed advice: title/level, tenure, strengths, and current challenge or growth area.
.agents/em-context.md or .agents/reports/[name].md automatically. Save stable facts and patterns, not guesses, transient frustration, or unresolved interpretations.Keep the first answer concise and useful. Do not dump the whole framework unless the user asks for depth.
Default to:
When helping with a PM-EM relationship, identify the operating pattern first:
If the PM is creating urgency, connect to managing-urgency; if the issue is roadmap tradeoff, connect to roadmap-planning.
The PM talks to customers alone, sets the roadmap alone, and tells you how long things should take. You're executing orders.
The real problems surface after a while:
You might think you can just insist on more time and higher standards. People who've been in this situation know the reality: when the PM is the final decision maker, it's very hard to resist.
You set the priorities, scope, and estimates. You make unilateral calls on refactoring. High-level designs and estimates are never challenged.
This results in disappointed stakeholders and customers — which misses the entire point of engineering. If your PM is not up to the task, sometimes you have to take a deep breath and do the PM work yourself.
Each side has its own territory — tech debt time is untouched, product roadmap is untouched. On the surface this looks fine.
In the long run, it fails. A much better model: a single roadmap that both of you agree on, where every technical initiative has a product-related justification.
A true partnership is reached when both sides want to make the right decision for the long-term success of the company — not just their team, not just customers, not just other stakeholders.
The best restaurant in the world was run by both the chef and the restaurateur together, making decisions for the good of the whole. An engineering team works the same way.
If your PM doesn't have a technical background, it's on you to bring them up to speed. Explain the benefits of technical work using real examples, not technical jargon.
Instead of: "We need to create the backend in a new service instead of our Java monolith, there was a decision to start breaking it down to microservices."
Go for: "We prefer to create the logic in a new service our team will own, instead of the shared code. This will allow us to move much faster on future requirements, without being bogged down by other teams."
You don't have the privilege to not care about the business.
When you understand the business and feel close to customers and other departments, it becomes much harder to bury your head in technical excellence alone. It also lets you sympathize with your PM, understand the reasons behind their decisions, and challenge them more credibly.
You'll never agree on everything. Neither of you can abuse the card by pulling it too many times. But it means: whoever genuinely cares more about an issue can have their way.
The willingness of one person to relinquish their own position helps build trust between you. Over time, it creates a relationship where both sides know they can fight hard for the things that truly matter.
One of the most effective ways to become a true PM–EM partner: get your engineers closer to customers and usage data before and after they build.
Before building — ask simple questions every time:
These aren't PM questions. These are questions every engineer should be able to answer about what they're building. If they can't, the spec isn't done yet.
Launch vs. Landing. A feature is not finished when code is in production — it's finished when users actually use it. Launching (writing the code, deploying, announcing) is the fun part. Landing (adoption, actual impact) is boring and non-technical, but it's the part that matters. When you release, schedule a check-in with the engineer who built it 1–2 weeks out to look at the data. This one habit changes how engineers think about their work.
Understand how users actually behave. Most PMs have access to session recording tools (FullStory, Hotjar, Posthog). Nothing stops engineers from watching them too. Start with a 30-minute "movie time" monthly — watch recordings related to features your team owns. The gap between what you think users do and what they actually do is always surprising.
Get engineers into customer conversations. Three practical ways that don't require reorganizing anything:
Three questions that work in any customer conversation:
After shipping — engage with usage data. What got used? What didn't? Share this in retrospectives, not just bugs and velocity.
Articulate tech debt in business terms. When engineers can say "this API costs us $40k/year and causes our top 3 customer complaints" rather than "this code is messy," they become credible voices in roadmap conversations — not just implementers pushing back on scope.
If the user asks where a framework came from or wants more context on any topic in this skill — read references/sources.md.
roadmap-planning — A true partnership produces a single shared roadmapmanaging-urgency — Most manufactured urgency originates from PM–EM misalignmentwritten-communication — How to frame technical work in terms a PM and stakeholders understandinfluence — Making the case for engineering priorities in cross-functional settingstesting
Score an Engineering Manager's coverage across all 12 cells of the EM Grid based on their calendar and Slack. Use this skill whenever someone wants to understand where they're spending their management energy, find blind spots, get a monthly self-reflection on their EM focus, or hear phrases like "score my EM grid", "where am I spending time as a manager", "what are my blind spots", "analyze my calendar as EM", "which EM areas am I neglecting", "how balanced is my management focus", or "check my EM grid coverage". Always pull live calendar data — never ask the user to describe their week manually.
development
Helps engineering managers write messages, announcements, and stakeholder updates that land well — produces a 3-Step Writing Framework (Prepare / Write Simply / Run a Garbage Collector), the Async Re-Explanation Trap (calling out missed messages), and the Compression/Decompression model for diagnosing why messages are misunderstood. Use when the user says "draft a message," "write an announcement," "communicate this change," "how do I word this," "message for my team," "write an update," or "how do I communicate X." Do NOT use for verbal feedback or difficult conversations (use `feedback` or `difficult-situations`).
testing
Helps engineering managers work effectively with Software Architects, Staff Engineers, and Principal Engineers — covers the EM's side of the relationship (responsiveness, proactive consultation, giving credit), how to advocate for architect time, pre-consultation preparation, and the two architecture team models (Centralized vs. Decentralized). Use when the user says "architect," "staff engineer," "principal engineer," "technical design review," "working with senior technical people," "getting architecture help," or "how do I get more architect time." Do NOT use for managing staff/principal engineers who report directly to you (use `managing-high-performers` or `delegation`).
development
Helps engineering managers assess and improve team health across morale, cohesion, delivery culture, and engagement — produces Google's 5 Factors (Project Aristotle), a 4-state team health diagnosis (Falling Behind / Treading Water / Repaying Debt / Innovating), a 5-zone intensity model, the Engagement Stack, the Trust Battery, Teamicide patterns (Peopleware), a blameless postmortem format, and a library of team activities organized by driver. Use when the user says "team morale," "team is struggling," "burnout," "engagement," "attrition risk," "psychological safety," "team dynamics," "something feels off," "team culture," "team is unhappy," "retros aren't working," "team isn't working hard enough," "ideas for team activities," or "how do I run a team offsite." Do NOT use for individual performance concerns (use `managing-high-performers`), team staffing or hiring (use `team-composition`), or individual motivation interventions (use `engineer-motivation`).