Claude Skills by Sidsaladi9

Writes a product vision — the 3-5 year picture of the world your product is trying to create, and what has to become true along the way. Use when a PM or founder says "write the product vision", "what's our vision", "where is this going in three years", "the team can't see the bigger picture", or when every roadmap conversation collapses into next quarter because nothing above it exists.

Adversarially attacks a PRD, strategy, or plan to find its holes before reality does — naming load-bearing assumptions, weakest links, and what a skeptical exec or competitor would exploit. Steelmans the plan first, then attacks it hard. Use when you're about to ship a doc to leadership, "this feels too clean," "what am I missing," "poke holes in this," "what would kill this," or prepping for a tough review.

Turns a list of shipped changes into audience-tiered release notes — a benefit-led user-facing changelog, a what/why/impact internal log, and a short social announcement cut. Use when you say "write release notes," "draft the changelog," "we just shipped X, announce it," "turn these tickets into release notes," or "summarize this release for customers and the team."

Facilitates a structured team retrospective using the well/wrong/confusing framework — gathering observations, tracing them to root causes instead of symptoms, and committing to 2-3 specific improvements with named owners and due dates. Use when you say "let's run a retro," "what went well and what didn't," "sprint retrospective," "post-mortem the launch," or "we keep making the same mistakes."

Use when the user wants to update the roadmap, build a Now/Next/Later view, reprioritize after new information, decide what moves to make room for a new initiative, shift timelines after a dependency slip, or figure out where a new initiative fits. Forces explicit trade-offs and keeps the roadmap anchored to outcomes, not a feature wishlist.

Segment a market or user base by needs and behavior — not just demographics — then size, score, and pick a beachhead segment with a defensible rationale. Use when someone says "segment this market", "who should we target first", "find our beachhead", "break our users into segments", "which customers do we prioritize", or "TAM/SAM by segment".

Create a new skill for this Product Manager OS — in the same format and quality bar as the built-in skills. Use when the user says "make a skill for X", "add a skill", "I keep doing X manually, turn it into a skill", or wants to extend the OS with their own framework or workflow.

Audits what actually shipped against what the spec promised, and turns the gap into a decision list. Use when a PM says "did we build what we specced", "what's actually in this release", "the spec says X but the product does Y", "check this against the PRD", "what got dropped", or before writing release notes, a launch announcement, or a retro on a delivery that drifted.

Plan a sprint — scope work, estimate realistic capacity, set a goal, and draft a copy-pasteable plan. Use when you say "plan our sprint", "size the backlog", "what fits in this sprint", need a "sprint goal", are deciding "P0 vs stretch", or need to "handle carryover" from last sprint. Works from a pasted backlog or pulls from Linear/Jira if connected.

Translates a product question into clean, correct SQL against a described schema and explains it line by line. Covers the core product-analytics patterns — funnels, retention and cohorts, DAU/MAU stickiness, and event counts — plus how to sanity-check the output. Use when you say "write me a query for", "how many users did X then Y", "what's our 7-day retention", "DAU/MAU by week", "build a funnel from signup to activation", or "is this number right?"

Maps stakeholders onto an influence/interest grid, captures each one's stance, motivations, and decision power, and derives a per-person engagement plan with a RACI overlay. Use when you say "who do I need to get on board," "map my stakeholders," "build a power/interest grid," "figure out who's blocking this," "who decides vs. who's just informed," or "I keep getting surprised by the same exec."

Generate a stakeholder update tailored to audience and cadence. Use when the user wants to "write a stakeholder update", "exec update", "weekly status", "monthly status", "announce the launch", "escalate this blocker", or "make a leadership-friendly version" — and when the same progress needs to be re-cut for execs, engineers, or customers.

Synthesize user research from interviews, surveys, and feedback into structured, evidence-backed insights. Use when you have a pile of notes to make sense of and say things like "synthesize these interviews", "find themes in this feedback", "what are users telling us", "turn this research into insights", or "analyze these support tickets". Extracts themes ranked by frequency and impact, then translates them into roadmap recommendations.

Derives QA test scenarios and acceptance test cases from a spec or user story, covering happy paths, edge cases, error states, data variations, and ML quality-bar/eval cases. Use when you need to "write test cases for this story," "figure out what QA should check," "turn this spec into acceptance criteria," "find the edge cases we're missing," or "design eval cases for this AI feature."

Designs the event tracking plan for a feature or product area — the event taxonomy, naming convention, properties, and QA checklist that make a metric answerable later. Use when a PM says "what should we instrument", "write a tracking plan", "what events do we need", "we can't answer that from the data", "define the analytics for this feature", or is about to ship something with no way to tell whether it worked.

Sorts a pile of inbound feature requests from sales, support, and users into themes, quantifies demand behind each, and recommends build / watch / decline with a templated reply for every requester. Use when you say "I have 40 requests to go through," "what are people actually asking for," "triage this feedback dump," "theme these tickets," or "should we build this or say no?"

Breaks an epic, spec, or feature into well-formed user stories with Given/When/Then acceptance criteria, applies INVEST, and splits stories that are too big. Use when a PM says "break this epic into stories", "write user stories", needs "acceptance criteria for X", wants to "split this story", or asks to "turn this PRD into a backlog".

Maps what customers actually want against what your product relieves and creates, using the Value Proposition Canvas, and produces the fit assessment plus the statements that come out of it. Use when a PM says "what's our value prop", "map the value proposition", "why do customers care", "our messaging isn't landing", or when the product does many things and nobody can say which one is the reason people buy.

Turns a PM artifact into a clean, self-contained HTML visual you can open and screenshot — a RICE/Kano prioritization matrix, a Now/Next/Later roadmap board, an OKR tree, a metrics scorecard, or a journey-map swimlane. Use when you say "make this visual", "turn this into a board / matrix / chart", "render the roadmap", "show me a scorecard", "visualize this", "I want to screenshot this", or after any skill produces a structured artifact and a picture would land harder than text.

Runs a win/loss analysis across decided deals to find why you actually win and lose, separating stated reasons from real causes. Use when a PM or PMM says "why are we losing deals", "run a win-loss", "analyze these lost deals", "what's killing our close rate", "sales says it's price", or when the same objection keeps surfacing and nobody has checked it against the data.

Turns a vague feature idea or problem statement into a structured, review-ready feature spec or PRD with goals, non-goals, success metrics, and testable acceptance criteria. Use when a PM says "write a PRD", "spec this feature", "turn this idea into a spec", "scope this", "define success metrics", "write acceptance criteria", or needs to break a big ask into a phased spec.