claudeskills.page

13 skills · category

Product Management skills for Claude Code

Skills for the product side of building software: user stories with real acceptance criteria, discovery interviews and jobs-to-be-done, outcome roadmaps, OKRs, honest prioritization, product metrics, sprint planning, research synthesis, launch readiness, feedback analysis, retrospectives and meetings that end with decisions.

Download all 13 (.zip) Browse the list
~/.claude/skills

curl -fsSL claudeskills.page/install.sh \
| sh -s -- --category product

Done. 13 skills ready · run /skills to confirm

All 13 Product Management skills

Each card opens the full playbook, example prompts and install commands.

Customer Feedback Analysis

From ticket noise to ranked, revenue-aware problems

Claude reads a sample first, drafts a codebook of problems rather than requested solutions, and tags every row with a bundled script that reports distinct accounts, segment share, revenue and monthly trend per theme. Keyword tags are validated against a hand-coded random sample before any number is reported, and top themes become problem statements cross-checked against usage data.

customer-feedback-analysis 181 lines · 2 files
★ Editor's pick

Feature Prioritization

Rankings anyone can challenge, cut lines that hold

Claude scores the backlog against a single stated objective, attaches a source to every reach, impact and effort number, and calibrates against a reference feature. A bundled script jitters the inputs to show which items near the cut line could flip, deadlines are handled with cost of delay instead of inflated impact, and every item below the line gets a reason and a revisit trigger.

feature-prioritization 186 lines · 2 files

Jobs to Be Done

Find the progress customers hire you for

Claude writes job statements with no product in them, plans switch interviews that rebuild real purchase timelines from first thought to decision, and codes the forces that drive and block switching. For feature prioritisation it builds a job map with measurable outcome statements and opportunity scores, then turns every finding into a specific roadmap, positioning or messaging decision.

jobs-to-be-done 215 lines · 2 files

Launch Readiness

Go/no-go calls backed by evidence, not vibes

Claude tiers the launch, then builds a cross-functional checklist where every item has one owner, an objective criterion and an evidence link, from load tests and rollback rehearsals to support macros and sales enablement. Rollout stages carry numeric promote and kill thresholds, the go/no-go meeting reviews only exceptions, and the decision, conditions and accepted risks are written down.

launch-readiness 153 lines · 2 files

Meeting Facilitation

Meetings that end in decisions and named owners

Claude first checks whether a meeting is needed at all, then writes an agenda of timeboxed questions with an outcome sentence, a named decider and a decision method. During the meeting it applies concrete moves for quiet voices, tangents and circular debate, and afterwards it sends a record that leads with decisions, trade-offs, dissent and actions owned by one person each.

meeting-facilitation 180 lines

OKR Planning

Key results that measure change, not activity

Claude turns launch-and-build task lists into outcome key results written as baseline to target with a named data source, adds guardrails so a number cannot be gamed, and labels each objective committed or aspirational. A bundled script flags activity phrasing and missing baselines, then scores KRs linearly for check-ins and the end-of-quarter review.

okr-planning 185 lines · 2 files

Product Discovery

Test the risky assumption before writing code

Claude starts from a measurable outcome, maps customer needs into an opportunity solution tree, and compares at least three solutions for the target opportunity. Interview guides ask about real past behavior instead of hypotheticals, assumptions are ranked by importance and evidence, and each test card carries a pass and fail threshold written before any data comes in.

product-discovery 191 lines
★ Editor's pick

Product Metrics

A north star and a metric tree teams can move

Claude picks a north star that measures delivered value, decomposes it into a metric tree whose children reconcile to the parent, and assigns each leaf to a team. Activation is chosen by comparing retention gaps across candidate behaviors, active means a value-carrying action rather than a login, and a bundled script builds N-period cohort retention tables from raw events.

product-metrics 196 lines · 2 files

Retrospectives

Three owned actions, checked at the next retro

Claude plans retros that open by reviewing the last retro's actions, show sprint data before anyone shares opinions, and use silent writing and dot voting so the loudest voice does not set the agenda. Discussion digs to causes the team controls, and the meeting ends with no more than three actions, each with an owner, a date and a measurable signal of success.

retrospectives 166 lines

Roadmap Planning

Now, Next, Later roadmaps built on outcomes

Claude rewrites a feature list into outcomes with target metrics, groups them under three to five strategy themes with a capacity split, and places them in Now, Next and Later with evidence labels. Now is checked against real capacity with a reserve for surprises, dates appear only on committed work, and leadership, sales and engineering get filtered views of one source plan.

roadmap-planning 157 lines

Sprint Planning

Commit to what the data says, not what feels good

Claude sets a sprint goal written as an outcome, collects availability and runs a bundled script that scales the 20th-percentile and median velocity by this sprint's capacity, then subtracts re-estimated carry-over. Stories are pulled in goal and dependency order up to the commit number, stretch work is labeled apart, and a written drop order decides what goes first when the sprint gets hit.

sprint-planning 169 lines · 2 files

User Research Synthesis

Findings you can trace back to the quote

Claude breaks transcripts and notes into atomic observations tagged by participant, clusters them bottom-up into themes named as findings, and builds a participant-by-theme matrix that shows breadth, segment skew and counter-evidence. Each insight cites participant counts and quotes with a confidence level, small samples are never turned into percentages, and recommendations trace back to evidence.

user-research-synthesis 157 lines

User Stories

Thin vertical slices a tester can verify alone

Claude writes stories around a named persona and a real outcome, then adds three to eight Given/When/Then criteria that cover rules, errors, permissions and empty states. Oversized stories get split by workflow step, business rule, data variation or deferred performance, never by frontend and backend, and the first slice is always a thin end-to-end walking skeleton.

user-stories 190 lines

Choosing Product Management skills

Install the skills that match requests you make every week. Each costs about 100 tokens of standing context until Claude loads it.

Start with

Background reading

Install

Every Product Management skill in one command

Installs all 13 into ~/.claude/skills/. Add --project after -- to install into the current repository instead.

The installer is a 101-line POSIX shell script. It downloads each skill you name from claudeskills.page and unpacks it into your skills folder, nothing else: no sudo, no telemetry. Every skill page shows the full SKILL.md, so you can read what you install first. Read install.sh

All 13 Product Management skills

curl -fsSL https://claudeskills.page/install.sh \ | sh -s -- --category product

Only the ones you want: list their names

curl -fsSL https://claudeskills.page/install.sh \ | sh -s -- customer-feedback-analysis feature-prioritization

Product Management skills FAQ

Short answers about installing and using these skills. For the details, read the install guide.

How do I install every Product Management skill at once?

Run curl -fsSL https://claudeskills.page/install.sh | sh -s -- --category product to install all 13 into ~/.claude/skills/, adding --project to install into the current repository. Or download the bundle at https://claudeskills.page/downloads/category/product.zip and unzip it yourself. To pick a few, pass their names instead: curl -fsSL https://claudeskills.page/install.sh | sh -s -- customer-feedback-analysis feature-prioritization jobs-to-be-done.

Will installing 13 skills slow Claude Code down?

No. Claude Code keeps only each skill's short description in context — roughly 100 tokens per skill — and loads the full instructions only when a request matches. Install the whole category if it fits your work; unused skills cost almost nothing.

Which Product Management skill should I start with?

Start with Feature Prioritization, Product Metrics, Customer Feedback Analysis. They cover the most common requests in this category; add the rest as your work calls for them.

Collections with Product Management skills

Explore other categories

esc