kalyvask
UserAgentic writting toolkit built from Glenn Kramon's Winning Writing at Stanford GSB and Rachel Konrad's cold-outreach guest lectures. 31 Claude skills, a browser Coach with span-level inline critic and refinement chat, plus a Chrome MV3 extension that runs the same critic in the Gmail side panel.
Categories
Indexed Skills (77)
winning-writing
Mode-aware writing critic. Distilled from Rachel Konrad's Stanford GSB "Winning Writing" course (spring 2026), the 10 rules of cold outreach, Heidi Roizen's mailing rules, and live class critiques. Loads a rule catalog (rules/catalog.json) and a mode definition (rules/modes.json) at invocation. Use whenever drafting or critiquing a cold email, outreach message, LinkedIn intro, exec memo, personal essay, bio, README, or LinkedIn post. Pass a mode argument to filter which rules apply.
bluf-rewriter
Reorganizes a memo, email, status update, or report so the bottom line is up front. Implements Kramon's BLUF (Bottom Line Up Front) rule. Use when a draft buries the lede, opens with context instead of conclusion, or builds up to the point with "organ music." Triggers on "BLUF," "lede," "buried," "memo," "status update," "exec summary," "TL;DR."
compression
Cuts a draft to a target word count without losing substance. Two modes behind one skill. target-count hits a specific number (200 for a cold email, 500 for an op-ed, 6 for a product summary). redundancy catches the specific failure where a phrase says what the verb or context already implied — "going forward" after a future-tense verb, "as I mentioned earlier," "reduce so they are smaller." Implements Kramon's "rewrite this in less than 100 words" exercise, the six-word summary drill, and the in-class redundancy exercise. Use when the user says "shorten this," "cut this," "tighten," "make it concise," "too many words," "going forward," "say it twice," "redundant." Pass --mode target-count|redundancy|both (default both) and --target-words N for target-count.
feedback-rephraser
Rewrites blunt downward or peer feedback as "what I like plus what I would like," focused on the work rather than the person, ideally phrased as a question. Use whenever the user is drafting a performance review, a Slack message to a report, a 1:1 talking point, an HR conversation script, a peer-review comment, or any line where they're tempted to criticize a colleague directly. Triggers on "give feedback to," "tell my report," "perf review line," "stop doing X," "you don't / you're not / you should stop," "smile more," "speak up more," "interrupt less," "less blunt," "burning out," "running late."
fun-angle
Finds the unexpected, dry, or self-deprecating angle that makes an email memorable. Turns "professional and polite" into "this person sounds like a real human." Use when a draft is technically correct but forgettable, when the user wants humor without slapstick, or when they need a subject line or sign-off with personality. Triggers on "make it funny," "more personality," "less corporate," "humor," "memorable subject line," "sign-off ideas."
headline-as-claim
Rewrites section titles, slide titles, op-ed headlines, email subject lines, and chapter headings from category labels into bold arguable claims. Implements Constine's "punchy slide titles that tell the story" rule and Kingsbury's NYT Opinion guidance that headlines should make a bold claim, not a neutral description. Use when the user has titles like "Product," "Market," "Background," "Why this matters" — labels that waste the reader's eye. Triggers on "slide titles," "section headings," "op-ed headline," "subject line," "chapter title," "punchy title," "scannable."
irrelevant-detail-killer
Cuts cinematic details that don't serve the main point. The opposite move from vividness. Vividness adds sensory detail; this skill removes detail that's vivid but distracts from the argument. Use when a narrative paragraph has impressive sensory texture (sounds, colors, weather, mechanics of an unrelated scene) that the reader has to push past to get to the point. Triggers on "eliminate irrelevant detail," "tighten the narrative," "the details are great but distract," "this paragraph wanders," "too much texture."
pick-a-lane
Diagnoses drafts that tell three half-stories instead of one full story, and rewrites them around the single strongest narrative thread. Implements Konrad's rule 7 and Adam Bryant's "stay in your lane" advice — distinct from compression (which cuts words) because pick-a-lane cuts whole stories. Use when a bio, cold email, op-ed, or pitch reads as a resume regurgitation, when the writer is dumping multiple accomplishments instead of telling one fully, or when a paragraph keeps turning corners. Triggers on "pick a lane," "stay in your lane," "too many stories," "resume dump," "before/after rewrite," "compress the narrative," "feels like a CV."
style-tells
Scrubs the three surface tells that make prose feel AI-generated, padded, or jargon-heavy. Three targets behind one skill, picked via the --target arg. em-dashes (default off in cold email / memo / Slack, max one per page in op-eds), adverbs (the -ly and intensifier pile), jargon (the Silicon Valley / consultant kill-list plus AI-tell phrases). Use when the user says "kill the AI tells," "scrub jargon," "remove em-dashes," "cut the adverbs," "make this sound human," "less corporate," "sounds like ChatGPT," "—," "very," "really," "leverage," "synergy," "delve," "tapestry." Pass --target em-dashes|adverbs|jargon|all (default all).
tell-them-something-new
Cuts opening sentences that recap what the recipient already knows about themselves, their company, or their own work. Implements Konrad's rule 2 ("begin with something they don't know — tell me a secret about the future") and Kramon's rule 4. Use when a draft opens with flattery, a summary of the reader's accomplishments, restating their stated thesis, or reciting biographical facts they already have. Triggers on "they already know," "rewrite the opener," "stop with the flattery," "first sentence is weak," "secret about the future," "tell them something new."
vividness
Pushes a draft from abstract toward concrete at two scales. Noun-level (replaces "dog" with "German shepherd," "customer" with "Sarah at JPMorgan's options-trading desk," "many" with "47 of 100") and scene-level (turns "I was angry" into the body signal, room, and dialogue). Implements Kramon's "specific over abstract" rule, Kristof's "real names, real numbers, real interviews," and Lauren Weinstein's "could a director recreate this scene?" test. Use when a draft is technically correct but flat, when category nouns leak through, when stories tell instead of show, or when the user says "be specific," "show don't tell," "more vivid," "less abstract," "make it concrete," "find the colors." Pass --mode noun-level|scene-level|both (default both).
cold-email-coach
Drafts and critiques cold emails using Rachel Konrad's 10 rules, Heidi Roizen's mailing rules, and Danny Hertzberg's six elements. Use whenever the user is writing a cold email, LinkedIn DM, intro request, hiring-manager outreach, VC pitch email, or any unsolicited message to someone with more power than them. Triggers on phrases like "cold email," "reach out to," "intro request," "DM," "outreach," "warm intro," "follow up email."
connection-finder
Finds specific, genuine "like you" hooks between the writer and a cold-outreach target — the bridges that turn a generic email into one that feels hand-written. Takes the recipient dossier and the writer's profile (about-me.md) and surfaces ranked angles. Use after recipient-research is done, before drafting. Triggers on "like you," "find a connection," "what do we have in common," "common ground."
cross-model-review
Independent second-model gate for cold emails before send. Must run on a DIFFERENT model than the one that drafted (e.g., draft on Opus, review on Sonnet — or vice versa). Acts as a binary pass/fail gate, not a regrade or rewrite. Names the specific failure mode from a 14-mode catalog (strategy / personalization / posture). Always surfaces the most likely counter-question the recipient will reply with. Triggers on "second pass," "cross-model review," "independent review," "review before send," or as the final step after `cold-email-coach` and `winning-writing-critic`.
dealing-with-reporters
Drafts and reviews answers to reporter questions, on-the-record statements, crisis-comms responses, and press-inquiry replies. Implements Andrew Ross Sorkin's 11 rules (taught with Kramon at Stanford GSB) plus AP attribution definitions for off-the-record / background / deep background conversations. Use when a journalist is calling, when a story is about to break, when a competitor has just been hacked and you want to get ahead of inquiry, or when a class assignment asks you to play CEO under fire. Triggers on "reporter," "journalist," "press inquiry," "PR statement," "no comment," "on background," "off the record," "crisis comms," "media interview," "quote me."
gratitude-note-coach
Helps draft cinematic, specific gratitude notes — Kramon's favorite assignment. Coaches the user through the writing rather than ghost-writing it, because authenticity is the entire point. Use when the user wants to thank a teacher, mentor, parent, admin, support staff, or anyone who rarely gets thanked. Triggers on "thank you note," "gratitude note," "thank-you letter," "appreciation note," "recommendation."
graveyard-historian
When pitching an idea, researches the graveyard — companies that tried something similar in the past 5–25 years and failed, what specifically killed them, and which operators or investors lived through those failures and would be valuable to talk to. Use before pitching to a VC, a customer, or a hiring manager — the graveyard reframes the pitch from "this is a great idea" to "this is a great idea AND I know why every previous attempt died." Triggers on "research the graveyard," "who tried this before," "previous attempts," "failed companies in this space," "post-mortem," "why did X fail."
humanize
Makes a draft read like a real human typed it — adds asymmetry, light contractions, and (rarely) one safe typo. Use only when a draft is technically correct but reads polished beyond plausibility, when the user wants to "rough it up," "make it more human," or "less AI-clean." Does NOT run on high-stakes writing (see "When NOT to humanize"). Triggers on "humanize," "rough it up," "less polished," "more casual," "sounds too clean."
op-ed-coach
Drafts and critiques op-eds, opinion pieces, and LinkedIn long-form posts using Glenn Kramon's framework, Katie Kingsbury's NYT Opinion guidance, and Nicholas Kristof's storytelling rules. Use when the user is writing an op-ed, an opinion piece, a Substack essay, a LinkedIn long-form post, or pitching one to a publication. Triggers on "op-ed," "opinion piece," "essay," "column," "pitch to NYT," "Substack post," "LinkedIn article."
performance-review-coach
Drafts and critiques performance reviews using Glenn Kramon's seven rules from Stanford GSB's Winning Writing course. Use when the user is writing an annual review, mid-year check-in, self-review, 360 feedback, peer review, or any written feedback for an employee, boss, partner, or themselves. Triggers on phrases like "performance review," "annual review," "self-review," "write up my feedback for," "review my report's performance," "evaluate my employee," "write feedback for [name]," "promotion packet," "calibration writeup."
pitch-coach
Drafts and critiques business pitches, investor decks, mission statements, and personal pitches using the 7-part pitch framework, S.H.I.T., and the six-word test. Use when the user is writing a VC pitch, a deck narrative, a "tell me about yourself," a LinkedIn bio, a one-pager, a founding story, or any pitch about themselves or their company. Triggers on "pitch," "deck," "investor," "mission statement," "tell me about yourself," "founding story," "LinkedIn bio," "elevator pitch."
pitch-memo
Drafts and critiques a text-first investor pitch memo for pre-seed and seed founders, structured around the 15 questions every investor asks. Use as an alternative or complement to a pitch deck — memos are faster to iterate, harder to hide weak thinking inside, and serve as the script for walking through a deck in a meeting. Triggers on "pitch memo," "investment memo," "fundraise memo," "memo for investors," "pitch document," "alternative to deck," "memo not deck."
recipient-research
Builds a research dossier on a cold-outreach target before drafting. Pulls LinkedIn, podcasts, blog posts, news, portfolio (if VC), and any specific personal details that would let an email feel hand-written rather than templated. Use when the user says "I want to email X" or "research Y before I write to them" or "build a dossier on Z." Triggers on "research," "dossier," "before I email," "background on," "find out about."
rhythm-killer
Fixes two sentence-rhythm tells that mark prose as AI-generated. Two targets behind one skill, picked via the --target arg. fragment-chain (three or more short sentences back-to-back) and uniform-length (two or more consecutive sentences within ~2 words of each other, especially with parallel structure). Use when the user says "reads like AI," "too choppy," "same length sentences back to back," "staccato," "fragments piled up," "rhythm is off," "uniform pacing." Pass --target fragment-chain|uniform-length|all (default all).
sent-mail-outcome-tracker
Read the user's recent cold-outreach sent mail, look up which messages got replies, classify reply sentiment, and produce an outcome report that surfaces what the responders had in common. Use when the user says "did my cold emails get replies," "what's my reply rate," "sent-mail outcomes," "track outcomes," or "/sent-mail-outcome-tracker." Requires a connected Gmail MCP. Read-only. Never contacts recipients.
speech-coach
Drafts and critiques speeches, talks, keynotes, lightning talks, demo-day pitches, all-hands updates, conference presentations, wedding toasts, and any spoken-delivery piece using Glenn Kramon's 12 wowing-the-crowd rules from Stanford GSB's Winning Writing. Use when the user is preparing a talk, presentation, keynote, panel opener, board presentation, all-hands, town hall, demo-day pitch, toast, eulogy, commencement address, or any piece that will be delivered aloud. Triggers on phrases like "I'm giving a talk," "preparing a speech," "keynote," "all-hands," "demo day pitch," "wedding toast," "panel opener," "TED-style," "deliver this aloud," "speaking at," "presentation script."
voice-update
Update `context/voice-and-style.md` or `context/about-me.md` from one of three sources. Manual (user dictates a single new rule, sample, or career fact). Memory (batch pull from Claude Code's auto-memory in `~/.claude/projects/<slug>/memory/`). Sent-mail (analyze the last 20-50 sent Gmail messages and propose updates from observed patterns). Always proposes diffs and requires per-file approval; never auto-writes. Use when the user says "save this to my voice file," "remember this style," "consolidate my voice," "update from memory," "read my sent mail," "voice from sent mail," "what does my voice actually look like," "voice-update," or "/voice-update." Pass --source manual|memory|sent-mail.
warm-intro-finder
Finds the human bridges between the writer and a target — mutual contacts, alumni networks, ex-colleagues, podcast connections, board overlaps — and ranks them by how likely they are to make a useful introduction. Different from connection-finder (which finds "like you" content hooks). This one finds *people* who can vouch. Use whenever the user is about to send a cold email and hasn't checked who they know in common with the target. Triggers on "warm intro," "find a connection," "who do I know," "mutual contact," "do I have anyone," "who can introduce me."
winning-writing-critic
Grades any draft against the full Winning Writing rubric (Kramon + Konrad + Kingsbury) and rewrites it. The orchestrator skill — invoke when you don't know which specialized skill applies, when the user just says "review this" or "make this better," or when the draft spans multiple forms (e.g., a pitch email that's also kind of an op-ed). Triggers on "review," "critique," "feedback," "make this better," "is this good," "grade this."
yourself-story
Drafts and critiques bios, LinkedIn About sections, intro slides, "tell me about yourself" interview answers, and personal-essay openers using Adam Bryant's 500-CEO research and Lauren Weinstein's warmth+competence frame. Different from pitch-coach (which is product-shaped) and cold-email-coach (which is recipient-shaped). This skill is for the format where you ARE the subject. Use when writing a bio for a website, a LinkedIn About paragraph, the first slide of a deck about yourself, the opening of an application essay, or rehearsing the "tell me about yourself" interview answer. Triggers on "tell me about yourself," "write my bio," "LinkedIn About," "about me page," "intro slide," "personal essay," "self-introduction."
ent-career-coach
Coach a career decision for someone who wants to end up building or joining startups — which job to take, how to evaluate offers, whether to take a chief-of-staff role, when to leave. This is the OFF-SPINE career layer, separate from the 00→07 venture journey. Use when the question is "where should I work / which offer / should I take this role," NOT "how do I build my company." Full reference in career/career_strategy.md.
ent-cold-email
Write a winning cold email or outreach message — for RDI research, customer discovery, fundraising, hiring, or any cold outreach. Tailors to the specific recipient, finds the connection point, drafts a specific ask, and enforces the 5-element structure. Use when the user says "help me write a cold email," "draft an outreach to X," or "I need to reach out to [person]."
ent-concept-test
Design a cheap, fast concept test that proves whether a desperate customer would WANT a candidate solution — before building it. Picks the right format (landing page, video, concierge, follow-me-home, wizard-of-oz), defines the behavioral pass threshold, and keeps the user from drifting into an expensive build. Use when the user has a solution shape and needs to validate demand (Stage 03 / pre-Stage 05).
ent-customer-discovery
Track and steer a customer-discovery sprint across many interviews — surface recurring patterns, score desperation across the batch, and flag when the user is talking to needy vs. desperate customers or has stopped too early. Use when the user is in the middle of customer discovery (Stage 02), running multiple interviews, and wants to know what the data is telling them so far.
ent-design-partners
Help the user identify, qualify, sign, and manage design partners — 2–5 early B2B customers who co-create the MVP. Pushes back on tire-kickers, big-logo traps, and free-pilot programs. Use when the user is preparing to sign design partners, qualifying a candidate, structuring the partnership terms, or troubleshooting an existing design-partner relationship.
ent-idea-coach
Help the user harvest insights from research and convert them into a falsifiable bet (Stage 01). Pushes back on wishes, ideas masquerading as insights, and consensus thinking. Use when the user has finished discovery / RDI and is trying to commit to a specific opportunity, or when they say "I have an idea" and need to test whether it's actually an insight.
ent-intake
Conversational placement and state capture. Interviews the founder to work out where they are on the 00→07 journey and writes the venture workspace for them, instead of asking them to hand-fill files. Use at cold start (no founder-state.yaml yet), when someone says "set me up", "where do I start", "onboard me", or to refresh state after time away.
ent-interview-debrief
Capture, structure, and score a customer interview immediately after it happens — score desperation markers, distinguish facts from interpretation, surface surprises, and update the hypothesis tracker. Use within 30 minutes of completing a customer interview. Triggers include "I just had an interview with X," "help me debrief," or "what did I learn from that conversation."
ent-interview-prep
Prepare the user for a specific customer interview — building a focused script, surfacing the right questions for their current hypothesis, and enforcing Mom Test discipline. Use before any customer discovery / RDI conversation. Triggers include "I have a customer interview with X tomorrow," "help me prep for an interview," or specific mentions of an upcoming conversation.
ent-mvp-review
Run a two-week MVP product review during the build phase — what was built, what was learned from customers, what's next, and whether there's enough evidence to pivot/persevere/keep building. Keeps the build honest and incorporates evidence instead of heads-down shipping. Use at the end of each two-week sprint during MVP build (Stage 05).
ent-mvp-scoper
Help the user decide what's in v1 of their MVP — given the value hypothesis and leap of faith, work out the smallest possible build that tests the leap of faith. Aggressively pushes back on overbuilding. Use when the user has a value hypothesis (Stage 04) and is about to build, when they ask "what should I build first," or when their MVP scope is exceeding 3 months.
ent-office-hours
The front door. Take a half-formed product idea and interrogate it YC-office-hours style — listen to the pain not the feature request, reframe what the user is actually building, challenge premises, generate 2-3 implementation approaches with effort estimates, and recommend the narrowest wedge to test first. Use when someone shows up with "I want to build X" and needs it pressure-tested and reframed before committing.
ent-pivot-coach
Run a structured pivot-or-persevere decision. Diagnoses the failure mode in the user's data, identifies the over-performing slice if any, drafts the new value hypothesis if pivoting, and forces a written commitment with thresholds. Use when the user's PMF self-check is failing, when they say "should we pivot?", or when the data is telling them something isn't working.
ent-pmf-evaluator
Run an honest, structured PMF self-check on the user's current data — Sean Ellis test, retention curves, organic acquisition %, the "tell" tests. Pushes back on wishful interpretation. Use when the user asks "do we have PMF?" or "how do we know if we're at PMF?" or when they're claiming PMF without strong evidence.
ent-pmf-memo
Synthesize the founder's whole journey into a 1-2 page PMF memo — insight, value hypothesis, desperation evidence, validation, metrics, the surprise, and an honest verdict. The capstone artifact you hand an investor, co-founder, or early hire. Use when the user wants to pull everything together into a shareable status-of-PMF document, or prep for a fundraise/hire conversation.
ent-problem-statement
Turn customer-discovery notes into a defensible, falsifiable problem statement (Stage 03). Forces specificity on the desperate customer, the single pain, the trigger, frequency, magnitude, alternatives, and behavioral evidence of desperation. Use when the user has finished a batch of discovery and needs to crystallize what they found before designing a solution.
ent-prompt-troubleshoot
Help the user fix AI prompts that aren't working — generic output, hallucinated facts, instruction-ignoring, output that's too long/short, no actionable conclusions. Use when the user complains about AI giving "slop," when they say "this prompt isn't working," or when they're frustrated with generic AI output.
ent-rdi-coach
Coach the user through the Research Driven Inspiration (RDI) methodology — building a "prepared mind" in a new industry or space through team alignment, secondary research (industry primer), and 100+ stakeholder conversations. Use when the user is exploring a space and doesn't yet have a specific problem to solve, when they're considering a pivot to a new market, or when they explicitly mention RDI or "prepared mind."
ent-red-team
Pressure-test a hypothesis, value proposition, pitch, strategy, or pivot decision by arguing the strongest case against it. Surfaces blind spots and consensus-thinking the user can't see. Use when the user is about to commit to a major decision, has fallen in love with a hypothesis, or asks for "honest feedback" or "tell me where I'm wrong."
ent-stage-router
Diagnose which entrepreneurship stage the user is in (from prepared mind / RDI through PMF measurement) and route them to the right framework, playbook, template, and skill for that stage. Use when the user asks for general help with their venture, says "where should I focus next," or describes their current situation without specifying what they need.
ent-synthesis-coach
Help the user synthesize a batch of interviews or research into clusters, patterns, and insights. Uses Pile Building, Cluster Analysis with active insight labels, stakeholder comparison, 2x2s, and hypothesis tracking. Use after every 5–10 interviews, when the user feels overwhelmed by their research, or when they say "help me synthesize" or "what patterns am I seeing?"
ent-thesis
Maintain the founder's cross-venture learnings ledger and synthesize it into a PMF-insights view, an investment/founder-style memo, or a sharpened value-hypothesis stance. Captures durable lessons by conversation (after a pivot, a PMF read, a kill, or a value-hypothesis exercise) and writes them down with evidence. Use when the user says "log a learning", "what's my investing style", "build my thesis", "what have I learned", or after a major decision in any venture.
ent-unit-econ-check
Run a back-of-envelope unit-economics sanity check — LTV, CAC, LTV/CAC ratio, payback period — to catch a structurally broken business model before building. Not financial modeling; a directional check. Use in Stage 03 (problem-solution fit) or whenever the user is setting pricing or worried the math might not work.
ent-value-hypothesis-builder
Help the user write a PMF-grade value hypothesis — three components (what / who / how) plus a separate leap-of-faith statement. Pushes back on vague *whos*, compound *whats*, and confusing the value hypothesis with the leap of faith. Use when the user is in Stage 04, when they say "help me write my value prop / hypothesis," or when they've finished customer discovery and need to commit to a specific bet.
ent-diligence
Run verification-first diligence on a set of factual claims — verify / flag / discard with sources, a what-must-be-true frame, and a gap list. Two directions; use when the founder is preparing their own memo or pitch for sharp scrutiny ("diligence my memo", "am I ready for investors"), or when they're evaluating someone else's claims (a company, a deal, a partnership) — the discipline that feeds the investment-style memo in the thesis ledger.
pm-context-loader
Load the PM agent's persistent context — personal style and preferences from `you.md`, the active project list, cross-project stakeholders, and the relevant project's state. Use as the first step in any PM workflow when you need the agent to understand the user's current work before doing anything else. The other operate-stage skills (pm-morning-brief, pm-meeting-prep, pm-meeting-debrief, pm-weekly-review, pm-stakeholder-tracker) chain to this skill first.
pm-customer-interview-coach
Plan, critique, or stress-test a customer-discovery interview against the Mom Test rules. Use when the user is preparing an interview script, reviewing a transcript, debriefing what they "learned," or deciding what to do with a batch of customer conversations. Catches leading questions, fluff-inducing phrasing, compliments mistaken for data, premature zoom into a hypothesized problem, and missed commitment asks. Returns a question-by-question rewrite, a list of what was actually learned vs. imagined, and the next conversation to run.
pm-decision-coach
Walk a PM through a real product decision step by step — diagnosis, framing, framework application, validation plan, kill criteria. Use when the user is actively wrestling with a specific product decision (kill / continue / pivot, build vs. buy, scope a launch, prioritize a backlog, respond to flat metrics) and wants help thinking it through end-to-end. Different from pm-framework-selector — this skill *runs* the decision; the selector just points at the right framework.
pm-design-critic
Critically review the user-facing surface of a PRD, design spec, or feature proposal against behavioral and UX principles. Use when a PM has a solution in hand and wants the design layer pressure-tested — defaults, friction placement, choice architecture, information density, AI surface decisions, peak-and-end moments. Distinct from pm-red-team (strategy adversary) and pm-evaluator (rubric scoring); this skill stays at the design layer and asks whether the design works with human cognition or against it. Returns the three load-bearing design holes with specific re-writes.
pm-design-process-router
Given a feature scope description, recommend the appropriate design-process intensity. Routes large features (M/L/XL) through the full Research → PRD → Design Concept → Detailed Design → Working Code pipeline; routes small features and bug fixes (XS/S) through an Express Lane (verbal sign-off, no Figma) that skips stages without value. Catches both over-processing of small work and under-processing of large work. Use at kickoff when scoping a new feature, or when triaging a backlog where the design team is over-loaded and you need to decide where to invest the process.
pm-evaluator
Grade a PM's written analysis, strategy memo, PRD, or proposal against the five-criterion PM evaluation rubric. Use when the user shares a PM artifact (a memo, a deck draft, a PRD, an analysis of a real product situation) and wants honest critique — or when reviewing your own draft before sending it up the chain. Returns a score, the strongest sections, the weakest sections, and specific re-work recommendations.
pm-framework-selector
Recommend which product-management framework(s) to apply to a specific decision. Use when the user describes a product decision and asks "what framework should I use?" / "how should I think about this?" / "which lens applies?" — or when you spot a PM decision in a conversation that would benefit from explicit framework grounding (prioritization, MVP scoping, validation, growth, risk, problem-framing). Anchored in the lifecycle-phase frameworks library in this repo.
pm-funnel-critic
Critique an activation funnel, conversion funnel, trial-to-paid mechanic, or growth dashboard against the repo's activation and conversion content. Use when a PM has funnel data, an onboarding flow, a paywall design, or a growth dashboard and wants the funnel layer pressure-tested — drop-off drivers, the binding stage, whether the right model (Enterprise vs PLG) is being applied, whether the activation event is real or vanity. Distinct from pm-metrics-critic (metric layer) and pm-design-critic (surface layer); this skill sits between them at the funnel layer. Returns the three load-bearing funnel holes with specific experiments and kill thresholds.
pm-inbox-triage
Pull recent Gmail threads, classify them into action categories (substantive response needed / quick reply / FYI / can ignore), and draft replies for the substantive ones. Surfaces stale threads where the user is awaiting a response and stale threads where someone is awaiting them. Used as part of pm-morning-brief or invoked directly when the inbox feels out of control. Drafts only — never auto-sends.
pm-launch-reviewer
Review a launch plan against the repo's launch-criteria template and failure-management playbook. Use when the user is preparing a launch (closed beta, limited GA, full GA) and wants a pre-flight review, or is staring at a checklist of "ready" gates that all happen to be owned by the same person. Surfaces missing gates, unowned criteria, vague readiness bars, and the one or two failure modes most likely to show up post-launch. Returns a gate-by-gate verdict and a launch-or-defer recommendation.
pm-meeting-debrief
Given a Granola meeting transcript, extract commitments (yours and theirs), identify decisions made, draft follow-up messages, and update the relevant project's `todos.md` and `stakeholders.md`. Use right after a meeting to close the loop before the context fades. Surfaces commitments that need to be captured into the project state, drafts the follow-ups, and asks the user to approve writes.
pm-meeting-prep
Given a calendar event (or upcoming meeting context), draft a one-page meeting brief. Identifies attendees, pulls relevant project state and stakeholder context, surfaces last interaction and open commitments, and drafts an opinionated prep doc. Use 15-30 minutes before any meeting that matters — exec review, stakeholder check-in, customer call, decision point.
pm-morning-brief
Run the morning PM briefing. Pulls today's calendar, identifies meetings needing prep, surfaces commitments due today across projects, surfaces inbox threads needing attention, and identifies anything that slipped from yesterday's commitments. Writes the brief to `pm-state/inbox/YYYY-MM-DD-morning-brief.md`. Use first thing in the morning, before opening email or calendar.
pm-north-star-selector
Pick a single North Star metric for a product. Weighs candidates across behavioral (MAU, sessions), value-delivered (messages sent, orders completed), and financial (ARR, revenue), forcing the comparison most teams skip — explainability, adoption + retention coverage, lead/lag, gameability. Use when a PM is defining a North Star, debating between MAU/DAU vs. value/revenue, or revisiting an existing one. Pushes back on jumping to a sophisticated composite or to revenue too early. Different from pm-metrics-critic, which reviews whole dashboards; this skill picks the one number.
pm-persona-stress-tester
Stress-test a design, flow, or PRD section by simulating how a specific persona would walk through it step by step. Takes the design plus a target persona (defined inline or pulled from pm-state stakeholders) and outputs a walkthrough from the persona's point of view — what they see, what they think, where they get stuck, the first failure mode that would make them bounce. Designed to surface obvious failures in 10 minutes before committing engineering time or scheduling real user research. Distinct from pm-design-critic (which applies behavioral principles to the artifact) and pm-customer-interview-coach (which helps run interviews with real users); this skill simulates the user.
pm-prd-drafter
Draft or critique a PRD against the repo's PRD template and problem-framing rubric. Use when the user is starting a PRD, sharing a PRD draft for review, or stuck on a specific PRD section (problem statement, success metrics, scope, kill criteria). Pushes back on vague problem statements, generic success metrics, and feature-laundry-list scope. Returns either a structured PRD draft or a section-by-section critique with specific re-writes.
pm-progress-auditor
Audit a status update, exec review, board email, all-hands talking point, or dashboard callout for credibility leaks before sending. Flags claims that overstate ("shipped" when 5 users are in beta), cherry-picked windows ("+15% w/w" off a holiday), vanity metrics used as validation, attribution claims with obvious uncontrolled counterfactuals, and "on track" forecasts without a threshold. Use when a PM is about to communicate progress upward and wants every claim pressure-tested. Built on the principle that goodwill is a finite budget — every overclaim debits the account, and once drained the real wins stop being believed.
pm-red-team
Adversarially re-review a PM artifact, recommendation, or AI-generated critique that already exists. Use as a second pass after another skill (pm-evaluator, pm-prd-drafter, pm-decision-coach, pm-value-hypothesis-tester) has produced output, or on any external AI output the user wants pressure-tested before deferring to it. Plays the role of a hostile exec, skeptical board member, or competing PM — looking for what the first pass missed, what bias it brought, and what would not survive a real review. Returns the three load-bearing holes, what's already strong enough to keep, and the specific re-writes that would close the gaps.
pm-stakeholder-tracker
Cross-project stakeholder tracking — who you owe responses to, who owes you, last interaction date, open commitments per person. Reads cross-project and per-project stakeholder files plus recent Granola and Gmail signal. Surfaces relationships drifting toward neglect and commitments hanging in the gap between meetings. Use weekly or before any big stakeholder push (board prep, exec review, customer escalation cycle).
pm-value-hypothesis-tester
Pressure-test a value hypothesis (the what / who / how / why-now) before resources are committed, design the smallest experiment that would falsify it, and pre-commit kill criteria. Use when the user is about to launch, fundraise, or scale a product and wants the bet stress-tested — or when they're stuck on a fuzzy "we'll figure it out" hypothesis. Catches insight-free products, segments that are needy but not desperate, hedged "who" decisions, and skipped early-adopter beachheads. Returns a sharpened hypothesis, the falsifying experiment, and the kill threshold.
pm-weekly-review
Run the Friday PM weekly review — what got done, what slipped, what's worth renegotiating, what's on next week. Reads each active project's state, pulls the week's Granola transcripts and calendar, surfaces patterns across projects (stakeholders going cold, decisions deferred, todos rotting). Writes the review to `pm-state/inbox/YYYY-MM-DD-weekly-review.md`. Use late Friday afternoon before logging off.
pm-pmf-coach
Walk a founder or early-stage PM through finding product-market fit on a specific bet. Use when the user is pre-PMF (no validated value hypothesis), has a candidate insight + audience + business model, and needs help deciding what to test next, how to interpret a failed experiment, and whether to pivot (change who/how) or restart (change what). Different from pm-value-hypothesis-tester which pressure-tests a single hypothesis statement statically; this skill runs the multi-step PMF process iteratively. Built on the Lean Startup synthesis (Rachleff, Ries, Blank, Moore, Christensen, Marks, Fitzpatrick, Cook).
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.