claude

opus-for-product-managers-pack

39 skills for running the whole product cycle with Claude, in seven phases that each hand a named artifact to the next: set Claude up and connect it, frame the question, discover the evidence, decide, build and ship, communicate the call and run the week. Each skill teaches one named, checkable method, with the inputs it needs, where it breaks, a fixed output template and the next skill to run.

54 on GitHubby 90nv1.0.0LicenseRef-PolarBear-Internal-Useupdated 17 days agoproductivity
/

Plugin opus-for-product-managers-pack from marketplace 90n-skills in polar-bear-org/claude-skills. Commands read from the repo's manifest — 17 days ago.

What it installs

Skills (39)

  • pmc-analyse-usage-data

    Answers one metric question through a read-only analytics connector or a CSV export as a Usage Data Answer with the query, event definitions, date range, a cleaning log with row counts, charts saved as files and caveats, plus a SQL draft for the data team when the connector cannot answer. Use for "r

  • pmc-build-business-case

    Builds a One-Page Business Case on why change, the best-value option against business as usual, how it is delivered and what it costs and returns, with confirmed figures kept apart from assumptions and a range for every return, as a Claude Doc with a backing spreadsheet. Use for "run pmc-build-busin

  • pmc-build-deck-in-claude-slides

    Builds a deck in Claude Slides from a finished doc, starting with a deck storyline of action titles you approve, then one claim per slide, numbers checked against the doc, speaker notes, and export to PowerPoint or PDF. Use for "run pmc-build-deck-in-claude-slides", "write the action titles first, t

  • pmc-build-issue-tree

    Breaks the framed question into an Issue Tree of sub-questions that do not overlap and together cover it, each leaf with the data that would answer it and where that data lives. Use for "run pmc-build-issue-tree", "build an issue tree", "break down why activation is flat", "check this tree for overl

  • pmc-define-the-kpis

    Defines the KPIs for a release with one outcome metric, leading and lagging indicators with definitions and owning teams, a baseline, a target, a guardrail per metric and a review date, in a KPI Definition Sheet. Use for "run pmc-define-the-kpis", "define the KPIs for the new onboarding", "which are

  • pmc-draft-hypotheses

    Turns the issue tree into a Hypothesis Board with an answer-first guess per branch, what would prove it wrong, the evidence needed and the cheapest test, ranked by importance and evidence. Use for "run pmc-draft-hypotheses", "draft the hypotheses", "first-guess answer for each branch", "what evidenc

  • pmc-frame-the-problem

    Turns a vague ask into a Problem Frame with one testable question, the decision it feeds and its owner, scope in and out, success criteria, constraints and a deadline. Use for "run pmc-frame-the-problem", "frame the problem", "turn fix onboarding into one question", "what decision is this for", "who

  • pmc-generate-options

    Generates an Option Set of three to five options that differ in kind, with do nothing as option zero, the bet each one makes and what each gives up. Use for "run pmc-generate-options", "give me four genuinely different ways to fix churn in month two", "add the do-nothing option and what it costs", "

  • pmc-map-the-competitors

    Builds a Competitor Landscape with a sourced, dated table of each named alternative's offer, target segment, published pricing and recent moves, plus where you differ, what not to copy and an optional weekly watch as a draft-only scheduled task. Use for "run pmc-map-the-competitors", "map the compet

  • pmc-map-the-stakeholders

    Builds a Stakeholder Map by role, showing who decides, who influences and who can block, with each role's interest, constraint, formal decision right and how to involve it before the decision date. Use for "run pmc-map-the-stakeholders", "map the stakeholders", "who decides on the pricing change", "

  • pmc-model-scenarios

    Builds a Scenario Model with base, upside and downside for each option, the two or three drivers that separate them, every assumption marked, a sensitivity check and the early signals that tell you which scenario you are in, as an editable spreadsheet. Use for "run pmc-model-scenarios", "model base,

  • pmc-morning-brief

    Builds a daily Morning Brief as a scheduled task that reads your connectors and lists what needs you, what is blocked, metric moves past your threshold and today's meetings, with a since-date catch-up mode after time off. Use for "run pmc-morning-brief", "brief me every weekday at 8", "what needs me

  • pmc-plan-connectors

    Plans which Claude connectors to turn on for your product stack, producing a stack map checked against each tool's official directory page, the read and write actions with writes kept off, who enables each one, a setup order and a first-run test per connector. Use for "run pmc-plan-connectors", "wha

  • pmc-plan-the-discovery

    Writes a time-boxed Discovery Workplan where each hypothesis gets a method (data, desk research or calls), an owner role, sources, a due date and a decision checkpoint set before work starts. Use for "run pmc-plan-the-discovery", "plan the discovery", "plan two weeks of discovery", "what can we answ

  • pmc-prep-for-meeting

    Prepares a one-page Meeting Brief for one meeting from your calendar, docs, tickets and last meeting notes, with the purpose, the decision wanted, what each attending role cares about, open actions and three questions to ask. Use for "run pmc-prep-for-meeting", "prep me for my 2pm with sales leaders

  • pmc-prepare-hard-questions

    Prepares a hard questions sheet for a review, with likely questions grouped by role (finance, engineering, sales, the sponsor), short answers with evidence, the numbers to have ready, and what to say when you do not know. Use for "run pmc-prepare-hard-questions", "what will finance ask about this pl

  • pmc-prepare-weekly-update

    Drafts the Friday Weekly Product Update from tickets moved, things shipped, metric changes and decisions made in chat, with a headline, what changed, at risk, what I need from you, links, and one cut per audience, never sent by Claude. Use for "run pmc-prepare-weekly-update", "draft my weekly update

  • pmc-prototype-in-claude-design

    Builds a clickable prototype from the spec in Claude Design, with two or three layout options and empty, error and loading states, plus a Prototype Test Brief (what it tests, pass line, what it does not prove, gap to production). Use for "run pmc-prototype-in-claude-design", "prototype the flow from

  • pmc-read-product-health

    Builds a Product Health Read across usage, quality, revenue signals and feedback, each line with its source and date, plus what changed since last quarter and what is still unknown. Use for "run pmc-read-product-health", "health read of the product", "what state is the product in", "what changed sin

  • pmc-read-the-experiment

    Reads a finished A/B test into an Experiment Readout with the hypothesis, a sample ratio check, the primary metric with its interval, guardrails, exploratory segments and a ship, iterate or stop call against the rule set before launch. Use for "run pmc-read-the-experiment", "read the results of the

  • pmc-red-team-the-plan

    Red-teams a plan into a Red Team Review with the strongest case against it, a pre-mortem failure story, the counter-evidence already on file, three questions a sceptical exec will ask and a list of what to change now. Use for "run pmc-red-team-the-plan", "argue against this plan as hard as you can",

  • pmc-run-decision-meeting

    Plans and records a meeting built around one decision, producing the agenda with DACI roles and the pre-read, the way disagreement is recorded, and a decision record drafted in Claude Docs for you to send after. Use for "run pmc-run-decision-meeting", "plan a 45-minute meeting to decide on the prici

  • pmc-run-deep-research

    Writes a research brief (question, the decision it feeds, sources allowed and banned, date window) for Claude Research, then turns the cited report into a Deep Research Report with a confidence note per finding, single-source and vendor claims flagged and a still-unknown list. Use for "run pmc-run-d

  • pmc-schedule-a-routine

    Specifies a Claude scheduled task that only drafts, producing a routine spec (self-contained prompt, cadence, connectors kept and removed, draft-only rule, where output lands, stop rule) and a first-run review list. Use for "run pmc-schedule-a-routine", "schedule my weekly update draft", "which conn

  • pmc-score-the-options

    Scores the options in an Option Scorecard with weighted criteria agreed before any scoring, every option scored on the same scale with evidence per score, and a sensitivity check on the weights. Use for "run pmc-score-the-options", "score these four options on impact, cost, risk and strategic fit",

  • pmc-segment-by-needs

    Builds Needs-Based Segments that group customers by the job they hire the product for and the circumstance they are in, each with a size signal from aggregate data, the current alternative, an underserved check and what it needs from the product, never profiles of individuals. Use for "run pmc-segme

  • pmc-sequence-the-roadmap

    Sequences approved work into a now, next, later board with a confidence note per item, an order set by cost of delay divided by duration, a "not on the roadmap" list with reasons and a one-screen exec cut. Use for "run pmc-sequence-the-roadmap", "sequence these initiatives into now, next, later", "o

  • pmc-set-up-claude-code

    Sets up Claude Code for a product manager with a product folder, a short CLAUDE.md from the context file, read-only settings agreed with an engineer, and a Feature Behaviour Explainer with file references. Use for "run pmc-set-up-claude-code", "set me up in Claude Code with read-only access", "how d

  • pmc-set-up-product-project

    Sets up a Claude project for one product area, producing the project instructions, a knowledge list sorted into load, link and keep out, and five first-week test prompts with what a good answer must contain. Use for "run pmc-set-up-product-project", "set up a Claude project for our product", "which

  • pmc-size-the-market

    Builds a Market Sizing Model with a top-down and a bottom-up estimate side by side, every input sourced or labelled as an assumption, a low, base and high range instead of a point, the gap between the methods explained and an editable spreadsheet. Use for "run pmc-size-the-market", "size the market"

  • pmc-synthesise-customer-calls

    Synthesises recorded customer calls, pulled through a read-only meeting-notes or research connector, into a Call Synthesis with themes stated as claims, exact quotes linked to each call, contradictions, counts by segment and questions for the next calls. Use for "run pmc-synthesise-customer-calls",

  • pmc-triage-feedback

    Triages a week of customer feedback from support, chat and research connectors into a Feedback Triage Log with fixed tags, the job behind each request, new against known themes, and reply drafts for a person to send. Use for "run pmc-triage-feedback", "triage this week's feedback", "triage feedback

  • pmc-turn-task-into-skill

    Turns a prompt you paste every week into a Claude skill, producing a SKILL.md draft, three test inputs from past work and a before and after comparison against outputs you already approved. Use for "run pmc-turn-task-into-skill", "turn this prompt into a skill", "make a skill for release notes", "te

  • pmc-wrap-the-week

    Closes the week into a Weekly Wrap with done against planned, decision records for the log, open loops with owners, next week's top three, and proposed edits to the product context file and project memory for you to approve. Use for "run pmc-wrap-the-week", "wrap my week", "which decisions from this

  • pmc-write-executive-summary

    Condenses any finished piece of work into a one-page executive summary in Claude Docs, with the point in one line, three supporting points with numbers and sources, and the ask and the risk. Use for "run pmc-write-executive-summary", "turn this doc into a one-page exec summary", "say the point in on

  • pmc-write-leadership-memo

    Writes a narrative leadership decision memo in Claude Docs for one decision meeting, covering context, the problem, options considered, the recommendation, what it costs and the open questions, written to be read in silence before discussion. Use for "run pmc-write-leadership-memo", "write a six-pag

  • pmc-write-product-context

    Interviews you and writes a dated product context file with an owner per section, memory rules for what Claude remembers, and an audit of the memory Topics Claude already holds. Use for "run pmc-write-product-context", "build our product context file", "interview me about the product", "add our metr

  • pmc-write-spec-in-claude-docs

    Writes a product spec as a Claude Doc, answer first, with problem and evidence, non-goals, numbered testable requirements and open questions with owners, ready for comments and export. Use for "run pmc-write-spec-in-claude-docs", "write the spec as a Claude Doc", "write a PRD in Claude Docs", "list

  • pmc-write-the-recommendation

    Writes the Recommendation as a Claude Doc with the call and the ask on the first line, three reasons tied to evidence, the options rejected and why, risks with mitigations and owners, and what is needed from whom by when. Use for "run pmc-write-the-recommendation", "write the recommendation from thi

View source on GitHub 90n.ai

More from polar-bear-org/claude-skills

All 38 plugins →

42 skills for the whole product job, stage by stage, from the vision to the weekly update, in eight stages: set direction, discover, decide, define, deliver, launch, prove, and run the product. Each skill is named as an action and keeps one framework inside, with the inputs it needs, where it breaks, a fixed output template, a finish line and the next skill to run.

42 skills

54

41 skills for the documents product people write, from the first brief to the post-launch review: setting up your voice and templates, discovering, shaping the vision, defining the work, deciding, aligning, reporting up, shipping and learning, running the team, and reviewing and editing. Each skill produces one finished document with a named reader and a length budget.

41 skills

54

The Complete Claude Guide for L&D: 40 Claude skills for the whole L&D job, in eight stages: diagnose the need with the request triage, the performance gap and the action map; work with the experts through the interview, the task breakdown and the review plan; design the learning with objectives, an evaluation plan, a design document and a curriculum map; build and test scenarios, a storyboard, a knowledge check, the check of an AI draft and a learner walkthrough; run the room with a session plan, slides, a facilitator guide and a pilot; carry it into work with a job aid, spaced practice and a manager briefing; measure what changed with a feedback form, an ROI estimate and the one-page report; and lead L&D through the year plan and the business case. For L&D managers and specialists, instructional designers, trainers and facilitators, and L&D leaders. Claude drafts and checks, people decide: nothing a learner does in training is used to grade, rank or build a case against them.

40 skills

54

Claude for Consultants · Team in Claude: 39 Claude skills for winning and shaping client work when the client has AI too, from their brief to the signed scope, as eight desks in order: Intake reads the client's brief, qualifies the opportunity and records the bid or no-bid decision; Discovery prepares the call, keeps the notes and sends the recap email; Problem writes the problem statement, the issue tree and the hypothesis test plan; Strategy builds options and the recommendation memo; Pricing shapes good-better-best options, fees and a MoSCoW scope; Proposal writes the consulting proposal, the AI use statement and the statement of work; the Client room prepares the walk-through deck, the AI objection answer and the negotiation plan; Follow-through covers follow-up emails, the mutual action plan and the win/loss review. For independent consultants and partners in advisory practices. Claude structures, drafts and checks; it never invents a reference, a result, a number or a client quote, and you run the conversation, make the recommendation and send everything yourself.

39 skills

54

36 skills for deciding if AI fits, testing it before launch and keeping it honest after: deciding if AI fits, speccing it as tests, briefing the model and the agent, building the evals from real outputs, shipping it safely, running and improving it, and its cost, price and explanation to leaders. Each skill is one named method or one artifact, with the inputs it needs, where it breaks and a fixed output template.

36 skills

54

33 Claude Skills that carry a design project from a fuzzy challenge to a tested, decision-ready concept: challenge framing, interview guides and screeners, transcript synthesis, personas and journeys, HMWs and concept cards, prototype and test plans, and the stakeholder playback.

33 skills

54

Similar plugins

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

pake

claudecodex

Package any website or local web build into a lightweight desktop app with Pake CLI.

1 skill

tw93/Pake 63,463

Maintain opus-for-product-managers-pack?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins38 plugins