The ones I actually reach for — title and use-case at a glance, full text on preview, copy in one click. Take what you need.
62 / 62 prompts
shelf
PRM-001prove
Prove it, don't describe it
Before accepting any agent claim that work is done — run the receipt loop first.
claudecursorverification
You are implementing a change. Do not tell me it works until you have shown receipts.
Before applying the fix:
preview →
PRM-002prove
Refute that this is merge-ready
Fresh-context reviewer — prompted to break the change, not approve it.
reviewagent-armoradversarial
You did not write this change. You have no stake in it being correct.
Your job is to refute that it is merge-ready — not to approve it, not to suggest polish, not to rewrite it.
preview →
PRM-003write
Clarify the question before drafting
When an essay or note keeps rewriting itself — the question is probably wrong.
writingessaysthinking
Before writing anything, answer these in plain language:
1. What question am I actually trying to answer? (One sentence.)
preview →
PRM-004plan
Structured literature pass
For papers and concepts — extract the claim, method, and what would falsify it.
researchreadingpapers
Read the source carefully. Output exactly these sections:
**Claim** — What are they actually asserting? (Not what the abstract wishes they asserted.)
preview →
PRM-005plan
Scope before implement
When a task is vague — force a minimal plan with explicit non-goals.
cursorplanningscope
Do not write code yet.
Given the task, produce:
preview →
PRM-006prove
Review until the round is empty
Meta-prompt for multi-round review loops — stop only when a pass finds nothing.
reviewiterationquality
Round {N} of adversarial review.
Review the current diff against the original intent. Find:
preview →
PRM-007ship
Rebuild the landing page from positioning
The landing page doesn't pass the 10-second test — who, problem, outcome, difference, first value moment.
productlandingcopyconversion
Act as a world-class UX strategist, conversion copywriter, and product designer.
Product: [product name + one-line description]
preview →
PRM-008build
Design a frictionless feature
Adding or reshaping a feature — it must feel obvious on first use and reduce cognitive load.
productuxfeatureimplementation
Design and implement [feature name] so it feels frictionless, intuitive, and low in cognitive load.
Context:
preview →
PRM-009audit
Maximize feature value
A feature works but doesn't feel indispensable — audit cognitive, emotional, and monetary value.
productstrategyvalueretention
Analyze [feature name] as a product strategist focused on maximizing user value.
Product: [product]
preview →
PRM-010build
Ship high-leverage improvements autonomously
You want the agent to pick and execute the highest-ROI product work without a task list.
productagentuxprioritization
Act as a top-tier product designer and engineer working on [product].
First, identify the 3 weakest points in the current product experience. Be specific — name screens, flows, or behaviors.
preview →
PRM-011plan
Research-backed product concept
Starting a new product — need honest concept doc grounded in real user pain, not category clichés.
productresearchmvpstrategy
I want to build [product idea] — not as a generic version of the category. It should be original, emotionally resonant, scientifically grounded where relevant, and product-grade.
Act as my technical co-builder, product strategist, and research partner.
preview →
PRM-012audit
Activation and time-to-value audit
Signups don't convert to meaningful value fast enough — find what's missing or fragile in the first journey.
productactivationonboardingaudit
Evaluate [product] like a product strategist focused on activation and robustness.
From the moment a user signs up, identify what prevents them from reaching meaningful value quickly and convincingly.
preview →
PRM-013audit
Elevate from vibe-coded to product-grade
The app feels assembled from startup tropes — diagnose why and prioritize standards upgrades.
productqualityuxpolish
The app [product] still feels vibe-coded rather than product-grade. Diagnose exactly why, then systematically elevate it toward category-defining standards.
Do not confuse polish with decoration. Product excellence means:
preview →
PRM-014ship
Premium UI and copy pass
The product needs quiet confidence — calm, precise, desirable without hype or noise.
productuicopypremium
Refine the UI and copy for [product / screen / flow] so it feels premium, calm, elegant, and quietly desirable.
Aim for confidence from taste, precision, and restraint — not noise.
preview →
PRM-015ship
Product-led viral loop
GTM needs organic distribution — design a share mechanism rooted in the product workflow, not referral spam.
productgtmviralgrowth
Design a product-led in-app viral mechanism for [product] that can materially support GTM by turning users into natural distributors.
Product context:
preview →
PRM-016prove
Pre-mortem before you ship
Before a release, launch, or merge you can't easily undo.
pre-mortemkleinlaunchrisk
Run a pre-mortem (Gary Klein) before [release / launch / merge].
Context:
preview →
PRM-017prove
Falsify the assumption ledger
When the plan rests on beliefs nobody has tested yet.
leanassumptionsratstrategyzer
Build and stress-test an assumption ledger for [product / feature / bet].
List assumptions across: user, problem, solution, channel, pricing, technology, timing.
preview →
PRM-018prove
Audit every user-facing claim
Before shipping copy, UI labels, or marketing that states outcomes.
claimsevidencetrustcopy
Audit every user-facing claim in [landing page / UI / email / release notes / ad].
Inventory each claim verbatim. For each:
preview →
PRM-041prove
Blameless post-mortem
After an incident, failed launch, or outage — learn without scapegoating.
post-mortemsreetsyincident
Facilitate a blameless post-mortem for [incident / failed launch / outage].
What happened: [timeline, impact, duration]
preview →
PRM-042prove
Hypothesis-driven debug
When a bug is elusive — stop guessing and run a scientific isolation loop.
debuggingscientific-methodroot-cause
Debug [bug / failing test / unexpected behavior] using hypothesis-driven isolation.
Symptoms: [what fails, where, when]
preview →
PRM-060prove
SBAR agent session handoff
When resuming a long task, switching agents, or handing off to a fresh context window.
sbarhandoffagentcursor
Produce a structured handoff using SBAR (Situation–Background–Assessment–Recommendation) — adapted from clinical and SRE handoff practice for agent session transfer.
Task: [what we're trying to accomplish]
preview →
PRM-061prove
ReAct debug loop
When an agent is guessing at fixes — force thought, action, and observation each step.
reactyaodebuggingagentcursor
Debug [bug / failing test / broken behavior] using the ReAct loop (Yao et al. — Reason + Act + Observe).
Symptoms: [what fails]
preview →
PRM-062prove
Reflexion after failure
When an approach failed — critique what went wrong before retrying, not immediately rerolling.
reflexionshinnagentlearning
A prior attempt to solve [task / bug / implementation] failed. Run Reflexion (Shinn et al.) before trying again.
Failed attempt summary: [what was tried]
preview →
PRM-019plan
Jobs-to-be-done interview synthesis
Before building — when you need the real job, not stated preferences.
jtbdchristensenresearchinterviews
Synthesize Jobs-to-be-Done insights from interview notes or transcript.
Input: [paste interview notes, transcript, or bullet summary]
preview →
PRM-020plan
Riskiest-assumption sprint plan
When you have many unknowns and need to pick what to learn first.
ratleanexperimentsprint
Design a riskiest-assumption test (RAT) sprint for [product / feature bet].
Time box: [1–2 weeks]
preview →
PRM-021plan
Competitive teardown
Before positioning or building — map what alternatives actually deliver.
competitivestrategypositioningresearch
Run a competitive teardown for [product / category].
Our angle: [one sentence on what we're exploring]
preview →
PRM-043plan
Opportunity Solution Tree
When roadmap items aren't tied to outcomes — map bets to measurable results.
osttorresdiscoveryoutcomes
Build an Opportunity Solution Tree for [product / team / quarter] (Teresa Torres).
Desired outcome: [measurable business or product result — e.g. "increase week-2 retention to 40%"]
preview →
PRM-044plan
User story map
When the backlog is a flat list — visualize the journey and slice releases.
story-mappattonbackbonereleases
Create a user story map for [product / feature area] (Jeff Patton).
Actor: [primary user persona]
preview →
PRM-053plan
Mom Test problem interview
Before building — run interviews that surface past behavior, not compliments.
mom-testfitzpatrickinterviewsdiscovery
Design and conduct a Mom Test problem interview for [product hypothesis] (Rob Fitzpatrick).
Hypothesis: [what you think the problem is — hold loosely]
preview →
PRM-054plan
Working Backwards PR-FAQ
Before a big build — force customer-visible narrative before specs or wireframes.
amazonpr-faqworking-backwardsnarrative
Write a Working Backwards PR-FAQ for [product / feature] (Amazon process).
**Press release** (write as if launching — future tense, customer-facing):
preview →
PRM-059plan
Plan-and-execute gate
Before an agent writes code — separate planning from execution with an explicit gate.
plan-and-solvereactcotagentcursor
Do not write or edit code yet. Run a plan-and-execute gate for [task] (Plan-and-Solve / ReAct lineage — planning before action improves LLM task success).
Task: [describe the change]
preview →
PRM-022build
Empty, loading, and error states
When a feature ships without designed non-happy paths.
uxstatesnn/gresilience
Design all non-happy paths for [feature / screen / flow].
Product: [product]
preview →
PRM-023build
First-session onboarding slice
When new users don't reach first value in one sitting.
onboardingactivationplgttv
Design the smallest first-session path to first value for [product].
First value moment: [what "aha" looks like — observable behavior]
preview →
PRM-024build
Accessibility implementation pass
Before calling a UI feature done — keyboard, focus, contrast, labels.
a11ywcagaccessibilityimplementation
Run a practical accessibility implementation pass on [screen / flow / component].
Audit against WCAG 2.2 AA (practical subset):
preview →
PRM-045build
Form and input design
When a flow is mostly fields and buttons — where most products lose users.
formswroblewskiinputsux
Design [form / checkout / signup / settings flow] using form UX best practices (Luke Wroblewski, NN/g).
User goal: [what they're trying to complete]
preview →
PRM-046build
Microcopy pass
When UI works but labels, buttons, and errors sound like placeholders.
microcopycontent-designux-writinglabels
Run a microcopy pass on [screen / flow / component] (content design / GOV.UK UX writing principles).
Inventory every user-facing string:
preview →
PRM-047build
Notification design
When the product pings users — email, push, in-app — without a clear policy.
notificationspushemailintercom
Design a notification strategy for [event / feature / product] (respectful notification UX).
Trigger: [what happened — e.g. comment, failure, milestone, reminder]
preview →
PRM-025audit
Nielsen heuristic evaluation
Quick structured UX audit without user tests.
heuristicsnielsenuxaudit
Evaluate [flow / product / screen] using Nielsen's 10 usability heuristics.
Walk the interface as a new user would. For each heuristic, note violations:
preview →
PRM-026audit
HEART metrics diagnosis
When you need to know which metric is broken and why.
heartmetricsgooglediagnosis
Diagnose product health using the HEART framework for [product / feature].
Pick the **one metric that matters most right now** from:
preview →
PRM-027audit
Kano feature classification
When prioritizing features — must-have vs performance vs delight.
kanoprioritizationroadmapaudit
Classify features in [backlog / roadmap / product] using the Kano model.
List features: [paste list or describe]
preview →
PRM-048audit
Product-market fit survey
When you need one honest signal — would users be disappointed if this disappeared?
pmfsean-ellissurveyretention
Design and interpret a product-market fit survey for [product] (Sean Ellis benchmark).
Audience: [who to survey — active users, not signups who never activated]
preview →
PRM-049audit
Cognitive walkthrough
When a specific task flow fails — step through what the user thinks at each action.
cognitive-walkthroughusabilitytask-flowaudit
Run a cognitive walkthrough on [task / flow] (Wharton / Polson et al.).
Task: [specific goal — e.g. "invite a teammate and set permissions"]
preview →
PRM-050audit
RICE prioritization
When the backlog is opinion wars — score impact, confidence, effort, and reach.
riceprioritizationintercomroadmap
Score and rank [backlog / feature list] using RICE (Intercom).
List items: [paste backlog or describe]
preview →
PRM-028write
Pyramid Principle outline
When a doc or essay feels scattered — lead with answer, then support.
pyramidmintooutlinestructure
Restructure [topic / draft / notes] using the Pyramid Principle (Barbara Minto).
Input: [paste draft, bullets, or messy notes]
preview →
PRM-029write
One-page decision memo
When a decision needs a shareable, async-readable brief.
memodecisionasyncwriting
Write a one-page decision memo for [decision].
Context: [background in 2–3 sentences]
preview →
PRM-030write
Explain to engineer and skeptic
When an idea is clear to you but lands poorly with technical or skeptical readers.
claritycommunicationfeynmandual-audience
Explain [idea / proposal / system] to two audiences who will read the same doc.
Idea: [describe in your words]
preview →
PRM-034write
BLUF the async update
For email, Slack, or status posts where most readers stop after the first line.
blufasyncmilitaryemail
Rewrite [email / Slack update / status post] using BLUF — Bottom Line Up Front (U.S. military communication doctrine).
Input: [paste draft or bullet dump]
preview →
PRM-035write
Toulmin argument map
When a persuasive draft feels convincing but the logic chain is invisible.
toulminargumentlogicpersuasion
Map the argument in [essay / proposal / pitch draft] using the Toulmin model (Stephen Toulmin, *The Uses of Argument*).
Input: [paste draft or thesis + bullets]
preview →
PRM-036write
Orwell–Zinsser clarity edit
When a draft exists but reads bloated, abstract, or like it was written to impress.
orwellzinssereditingclarity
Edit [draft] for clarity using Orwell's rules (*Politics and the English Language*) and Zinsser's discipline (*On Writing Well*).
Input: [paste draft]
preview →
PRM-037write
Plain language rewrite
When a doc is legally correct or technically accurate but ordinary readers won't finish it.
When you've written a lot but can't tell if the structure actually works.
reverse-outlinestructureeditingpedagogy
Run a reverse outline on [draft] — standard revision technique (writing-center pedagogy).
Input: [paste full draft]
preview →
PRM-039write
Pinker curse-of-knowledge diagnostic
When experts wrote it and non-experts bounce — you know too much to notice.
pinkercurse-of-knowledgeclarityjargon
Diagnose [draft] for the curse of knowledge (Steven Pinker, *The Sense of Style*).
Writer's expertise: [what the author knows that the reader may not]
preview →
PRM-040write
Strip AI cadence, restore human voice
When the draft reads polished, generic, and interchangeable with every other AI-generated text.
ai-slopvoicehumanizingediting
Rewrite [draft] to remove AI rhetorical tics and restore a specific human voice.
Input: [paste draft]
preview →
PRM-055write
Nut graf and lede
When the opening doesn't earn the read — bury the lead or take too long to matter.
nut-grafledejournalismopening
Craft the opening for [essay / article / long post] using journalism structure (nut graf + lede).
Draft or topic: [paste draft or describe]
preview →
PRM-056write
Evergreen note
When an idea is worth keeping — atomic, linkable, understandable alone in five years.
evergreenmatuschakzettelkastennotes
Turn [idea / highlight / rough note] into an evergreen note (Andy Matuschak / Zettelkasten principles).
Source: [paste quote, thought, or messy bullet]
preview →
PRM-031ship
Obviously Awesome positioning
When the product category is crowded and differentiation is fuzzy.
positioningdunfordgtmcategory
Develop positioning using April Dunford's Obviously Awesome framework for [product].
Fill in:
preview →
PRM-032ship
PAS conversion section
For a key page section that must convert — hero, pricing block, email.
pascopyconversiondirect-response
Write a Problem–Agitation–Solution (PAS) section for [product / page section].
ICP: [specific audience]
preview →
PRM-033ship
Release notes that build trust
When shipping a release — changelog as credibility, not feature dump.
release-noteschangelogtrustproduct-marketing
Write release notes for [product] version [version / release name].
Changes: [paste PR list, commits summary, or bullet dump]
preview →
PRM-051ship
Pricing page audit
When pricing is live or planned but conversion or comprehension is weak.
pricingvan-westendorppackagingconversion
Audit the pricing page for [product] using pricing psychology and packaging best practices.
Current pricing: [tiers, prices, billing period — or "not built yet"]
preview →
PRM-052ship
StoryBrand brand script
When marketing talks about the product instead of the customer's story.
storybrandmillernarrativemessaging
Write a StoryBrand BrandScript for [product] (Donald Miller — customer is the hero).
Fill the seven elements:
preview →
PRM-057ship
Launch checklist
When a release is days away — sequence assets, channels, and rollback before you ship.
launchgtmchecklistrelease
Build a launch checklist for [product / feature / version].
Launch date: [target or window]
preview →
PRM-058ship
Case study structure
When you need proof that real customers got real results — not marketing fluff.
case-studysocial-proofb2bstorytelling
Write a case study for [customer / use case] using credible B2B product marketing structure.
Customer: [name or anonymized descriptor — industry, size]