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
Turn any article into 7 platform-native posts (LinkedIn, X, Instagram, Threads) with different angles, tones, and formats — so multi-platform followers never see the same recycled lede twice.
Paste your resume and a job description, and get a tailored version that highlights genuinely relevant experience, mirrors the JD's keywords for ATS matching, and flags any gaps honestly instead of fabricating skills. No generic buzzword stuffing.
A phased mega-prompt that turns an AI into a disciplined infrastructure consultant — Built and battle-tested deploying a self-hosted Nextcloud stack on Proxmox, but generalized for any homelab/self-hosting build.
Paste an error stack trace plus the function it points at. Get a plain-English root cause, the smallest diff that fixes it, why that fix works, and the edge cases to watch — no over-engineering, no try/catch band-aids.
Describe what you need to know in plain English and paste your schema. Get a correct, readable SQL query with CTEs, aliases, a plain-English explanation, and an index note — no guessing at column names.
Describe your product, support scope, tone, and escalation rules. Get a production-ready system prompt for a support agent with persona, knowledge boundaries, escalation triggers, and a refusal policy baked in — pasteable straight into your agent config.
Give your destination, all-in budget, dates and travel style, and get an honest day-by-day plan with timings, costs, neighborhoods, what to skip, and a real daily budget that adds up. Built for travelers who hate over-research.
Turn a dry spec sheet into a benefit-led product description with a scene-setting hook, feature-to-benefit translation, and an outcome CTA. Flags any claim that needs verifying. For any product category.
Paste a prospect's website copy and get a sub-120-word cold email that opens with a real, specific observation about their business instead of a fake compliment. For SDRs and founders doing outbound who are tired of 1% reply rates.
Paste your staged git diff and get one properly-typed, properly-scoped Conventional Commit message — imperative summary, optional why-body, and a BREAKING CHANGE footer when needed. For devs who want a readable history without agonizing over wording.
Paste a messy Slack or Teams thread and get a clean table of action items, each with an owner pulled from the actual @mentions, a due date, and a priority. Built for ops leads, chiefs of staff, and PMs who live in chat.
Paste a full contract and get every clause sorted into High / Medium / Standard plus a Missing-Clauses list, so your lawyer reviews flagged sections instead of a blank page. A triage tool to make legal review cheaper — not legal advice.
Dump your messy to-do list (however chaotic) and get it sorted into a realistic daily plan — prioritized by urgency and impact, time-blocked to fit your day, with a clear "if you only do 3 things" shortlist for when the day goes sideways.
Give a science topic and your level. Get a hierarchical concept map showing how the ideas connect, plus a deck of spaced-repetition flashcards (atomic Q&A with cloze deletions and a misconception check) ready to paste into Anki. For students and self-learners.
Paste a raw CSV sample and get a data-quality report: column types, likely primary key, and issues split into "observed" vs "suspected" — mixed date formats, hidden summary rows, near-duplicates, and outliers. Never guesses a statistic it can't compute from what you gave it.
Describe a process in plain language and get a formatted standard operating procedure with numbered steps, roles, decision branches, quality checks, and a failure-modes section. Ideal for ops teams turning tribal knowledge into something a new hire can follow on day one.
Describe a user interaction you want to track. Get a complete, engineering-ready tracking plan: canonical event name, exact trigger, a property table, what NOT to track, and a QA checklist that includes the error case.
Enter the meeting details and your goal and get a one-page brief: talking points in priority order, the objections to expect with prepared responses, your single clearest ask, and an opening line. For chronic over-preparers and under-preparers alike.
Generate a complete 5-email cold outreach sequence — subject lines, preview text, send timing, and bodies — where each email has a distinct job and none of them feels like a CRM wrote it. For founders, SDRs, and freelancers selling B2B.
Drop in who you met and what they cared about, and get a personalized post-showing follow-up: a same-day text, a value-add message two days later, and a gentle nudge email — each referencing the real details from the visit. For agents drowning in 'just following up!' templates that everyone ignores.
Paste open-ended survey answers or interview transcripts and get a rigorous thematic analysis — named themes with verbatim quotes, honest frequency bands, a key-tensions section, and goal-tailored recommendations. Built for UX, research, and product teams who need rigor at speed.
Generate a full branching NPC conversation tree with a consistent voice, meaningful player choices, optional lore reveals behind the right branch, quest triggers, and at least one deliberate dead end. For RPG and adventure writers.
Turn one piece of content into multiple platform-ready posts, captions, and scripts while preserving the original message.
Paste a messy customer bug report and get a clean engineering ticket: steps to reproduce, expected vs actual, environment, a suggested severity, and the exact clarifying questions you still need — with every guess flagged. For support and QA.
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.