Claude prompts are instructions tuned for Anthropic's Claude models, which excel at long-context reasoning, careful writing, and structured analysis. On Prompt Dock every Claude prompt is human-reviewed, and the in-app Playground runs against Claude directly — so you can reveal a prompt and immediately see how Claude responds. Whether you need a rigorous document summarizer, a coding assistant, or an agentic workflow, browse free and premium Claude prompts by category, each labelled with the model it was written for.
73 prompts
Get an idiomatic translation that keeps the original register and rhythm — formal, warm, urgent, dry — plus a translator's note explaining the choices that a word-for-word render would have botched. For anyone shipping copy into a language they don't speak.
Paste a student essay and the assignment brief and get structured feedback on thesis, evidence, structure, and sentence-level writing — every point anchored to a quoted line, with concrete revision suggestions and a 'fix these three first' list. The model coaches; it never rewrites the essay for the student.
Compare your published topics against a competitor's content and get a prioritized gap list: coverage map, the top eight missing topics with intent and difficulty, your counterintuitive advantages, and a 90-day article plan. Turns a month of competitive research into 20 minutes.
Paste any financial statement line or section and get a jargon-free explanation: what it is, what a change signals, how it connects to other statements, plus an everyday analogy and what to watch. Educational only, not financial advice. The 'never look clueless on an investor call again' prompt.
Describe the fields you need from messy text and get an extraction prompt that returns clean, valid JSON every time — explicit schema, null strategy for missing fields, array handling, a defined error object, and a per-item confidence score. Works without native JSON mode.
Paste a manager's rough, honest notes on someone and get a balanced, evidence-based review summary with accomplishments, growth areas, values alignment, and SMART goals. Strips bias and saves hours of drafting.
Give it a role, the competencies you care about, and the stage, and get STAR behavioral questions, follow-up probes, strong/weak answer signals, and a 4-level scoring rubric. Cuts hiring bias and makes panel debriefs short and decisive.
Paste your raw bullets or stream-of-consciousness brain-dump and get a crisp status update sized for Slack, email, or a standup doc. Built for PMs, engineers, and anyone who types faster than they think. Flags anything it can't confirm instead of inventing it.
Give one charged detail — an object, a color, a line, a place — and get exactly 200 words that drop you mid-action and end on an unfinished gesture, designed to pull you into writing the next thousand words yourself. A door, not a destination.
Turn a theme, a feeling, or a true story into a full lyric sheet — verse, pre-chorus, chorus, bridge — with locked syllable meter and concrete imagery, ready to track. For songwriters who stall after the first chorus.
Feed in your product, your buyer, and the objections that keep killing deals. Get a calm, non-defensive response framework for each: what it really means, an acknowledge-and-explore reply, an honest reframe, and what NOT to say. Build a team training doc in 10 minutes.
Paste your raw property facts, the buyer you're chasing, and the tone, and get a scroll-stopping MLS listing description with a headline, benefit-led bullets, and a neighborhood line. For agents and FSBO sellers who keep writing 'cozy, must-see, lots of potential.'
Paste any research paper or abstract and get a clear, jargon-free breakdown of the question, method, finding, and implication — plus a one-sentence takeaway and a caveats flag for sample size, funding, and replication. Built for non-specialists who need to use the evidence, not just admire it.
Hand it a keyword and get a full content brief: intent classification, recommended format, title tag, H1, an H2/H3 outline with snippet flags, an FAQ block, and internal-link placeholders. Built for content teams shipping articles weekly.
List your backlog items with short descriptions and get each scored on Reach, Impact, Confidence, and Effort, a clean RICE table, a ranked list with the key driver per item, and a flags section calling out low-confidence bets and likely-underestimated effort. The premium prioritization workhorse.
Writes cold emails that don't sound AI-generated, because it won't write until you give it something real. Validates your inputs, scores your prospect research, kills fabricated specifics, and returns three strategically different angles instead of three rewordings of the same email.
Paste two scenes featuring the same character and get a line-by-line drift report plus a reusable 150-word Voice Card. Catches the moment your guarded protagonist suddenly starts using words they'd never say. The one I'd pay for.
Paste a raw feature request, exec one-liner, or messy Slack thread and get a tight PRD: problem statement, goals, non-goals, user stories, a primary success metric with guardrails, and numbered open questions. Built for PMs who need alignment before scoping.
Paste any single contract clause and get a plain-English translation, exactly what you're agreeing to, what the other side gets, and a ranked list of red flags to raise with your lawyer. Educational triage, not legal advice.
Dump weeks of undated, chaotic symptom notes and get back a clean dated table, observed patterns, and the episodes most worth reporting — ready to share at your appointment. Readability aid, not medical advice.
Describe what you did, who you hurt, and how they're feeling, and get a genuine apology that takes responsibility, names the impact, and offers real repair — no 'sorry you feel that way,' no over-grovelling, no hidden excuses. For the conversations that actually matter, said the right way.
Get a full proofread plus a plain-English reason for every change — grammar, punctuation, articles, tense, word choice, style. Built for ESL writers, students, and anyone who wants to learn from edits instead of blindly accepting them. The premium one I run on everything that matters.
Dump a messy list of transactions or receipts and get them categorized into standard tax/accounting buckets, flagged for anything ambiguous or possibly non-deductible, and summarized by category — ready to hand to a bookkeeper or drop into a spreadsheet.
Analyze up to five competitors, find the crowded dimensions everyone fights over, and surface the white space your brand can own — plus a draft positioning statement. The premium strategy prompt I'd pay for.
Claude responds best to clearly structured instructions — explicit roles, XML-style sections, and long-context material. Claude prompts here are written and reviewed with those strengths in mind, and each names the Claude model it targets.
Yes — the in-app AI Playground executes prompts against Anthropic Claude models directly, so you see genuine Claude output before copying anything into your own tools. Every plan includes a daily token allowance.
Yes. Free Claude prompts can be revealed at no cost; premium ones unlock with an Explorer or Master subscription. All of them pass the same human review before publishing.