19 free prompts · all verified
Claude prompts
Claude responds measurably better to explicit structure — XML-style tags, imperative instructions, stated output formats. These prompts are written for that, not generic copy pasted from a ChatGPT list.
Every prompt lists the exact tool and version it was tested against.
Set up a Claude Project that stays accurate for months, not just this chatA structured Claude Projects setup that splits durable knowledge from custom instructions and adds an explicit staleness-check protocol, so every new chat in the Project inherits accurate context automatically instead of the knowledge base quietly rotting into confidently wrong answers.Claude (Projects)Claude Enterprise2026-07-20Build a multi-view dashboard as one self-contained Claude ArtifactA prompt for building a single-file interactive dashboard Artifact with multiple tabs sharing one dataset and one state model, so filters and selections stay consistent across views instead of several disconnected mini-tools bolted together.Claude (Artifacts)Claude.ai2026-07-21Audit a full contract for risk using Claude's whole context window, not a skimA long-context prompt that forces a clause-by-clause, quote-grounded risk audit of an entire pasted contract or policy document, ranked by severity and tied to one party's actual position, instead of a general summary of what the document is about.Claude (Opus 4.6, 1M context)Claude (Sonnet 4.6, 200K context)2026-07-22Feed Claude untrusted or user-submitted text without letting it hijack your instructionsAn XML-tagged prompt structure for any task where Claude must process content you did not write yourself — customer submissions, scraped pages, forum posts — that keeps instructions and untrusted data in separate labeled blocks and requires flagging any embedded instruction-injection attempt.Claude (Sonnet 4.6)Claude (Opus 4.6)2026-07-23Get Claude's extended thinking to actually spend its budget on your hardest stepA prompt for a genuinely hard multi-step problem that names an explicit reasoning effort level and gives the thinking process concrete verification work — checking the answer against every stated constraint and weighing a real alternative — instead of leaving a reasoning budget to wander.Claude (Opus 4.6, extended thinking)Claude (Sonnet 4.6, extended thinking)2026-07-24Get Claude to write in your actual voice, not the generic AI defaultA style-matching prompt that extracts a checkable checklist of concrete voice markers from several real writing samples before writing anything new, with a forced self-check pass to catch any drift back toward a more generic, more polished register.Claude (Sonnet 4.6)Claude (Opus 4.6)2026-07-25Compare several proposals or contracts side by side, not one summary at a timeA structured comparison prompt for several long documents at once that forces a criteria-by-criteria table with weighted and unweighted recommendations, so genuine cross-document differences surface instead of three separate summaries you have to compare yourself.Claude (Sonnet 4.6, long context)Claude (Opus 4.6)2026-07-27Get a web-search research brief where every claim traces to a real, checkable sourceA prompt for Claude's web search feature that requires an inline citation on every substantive claim, a source-quality breakdown of primary versus secondary sources, and an explicit list of what search could not actually verify, instead of a fluent answer that blends real results with plausible filler.Claude (with web search)Claude.ai2026-07-28Force Claude to critique and score its own draft before you ever see itA four-pass drafting prompt — draft, numerically scored critique, a dedicated blind-spot check, and a re-scored revision — so an improved draft has to earn its improvement against a rubric, not just read like a nicer version of the same thing.Claude (Sonnet 4.6)Claude (Opus 4.6)2026-07-29Get Claude for Excel to show its formulas, not just narrate a numberA spreadsheet-analysis prompt for Claude for Excel and Sheets that requires real live formulas written into named cells, a chat-side manifest of what went where, and explicit data-quality flags, so the analysis can be re-run and audited instead of trusted on faith.Claude for ExcelClaude for Sheets2026-07-30Force a brainstorm into real, differentiated options instead of one idea repeated five waysA constrained brainstorming prompt with hard kill criteria, mandatory diversity axes, and a required, sized tradeoff per idea, so options that violate a real constraint get cut outright and the ones that remain are genuinely comparable instead of cosmetic variations on the same idea.Claude (Sonnet 4.6)Claude (Opus 4.6)2026-07-31Brief Claude for Chrome for a browsing task without letting it wander or click something irreversibleA scoped task brief for Claude's browser extension with an explicit site allowlist, a reversibility-based rule for what needs your confirmation before it happens, and a structured after-action report — so an agentic browsing session stays auditable instead of an opaque "it did something" result.Claude for ChromeClaude (Computer Use)2026-08-01Turn a raw CSV into a statistics report with charts, code includedA prompt for Claude's built-in analysis tool that requires every number in the report to come from actual executed code shown alongside it, plus explicit data-quality and statistical-caveat sections, instead of a narrated conclusion nobody can verify against the underlying data.Claude (Analysis Tool)Claude.ai2026-08-02Brief Claude's voice mode to run a real rehearsal, not a scripted Q&AA setup prompt for the start of a Claude voice-mode session that fixes turn length, feedback timing, and in-character behavior up front, so a spoken rehearsal for an interview or hard conversation stays usable in a format with no bullet points or headers to lean on.Claude (Voice Mode)Claude Mobile App2026-08-03Get grounded answers across your connected Google Workspace, with a real source for every claimA prompt for Claude with Google Workspace connectors that requires every fact to trace to a specific document, email, or event, surfaces conflicting sources by name, and forces an honest 'not found' outcome instead of a plausible-sounding guess when the connected sources don't actually say it.Claude (Google Workspace connectors)Claude Enterprise2026-08-04Tell Claude exactly what to remember across chats, and what to never rememberA one-time configuration prompt for Claude's persistent memory feature that draws an explicit line between facts worth carrying forward and facts that should never persist, plus a correction protocol so a stale or wrong memory gets fully updated instead of half-fixed.Claude (Memory)Claude.ai2026-08-05Define a Custom Style once so every future chat gets the same tone by defaultA prompt for authoring a reusable Claude Custom Style — concrete, directly actionable patterns instead of vague adjectives, explicit anti-patterns, and a before/after demonstration — so a saved formatting and tone preference actually holds up across chats instead of drifting back to Claude's own default.Claude (Custom Styles)Claude.ai2026-08-06Generate a role-specific onboarding doc from company knowledge without leaking what that role shouldn't seeA prompt for Claude Enterprise or Team that turns shared company knowledge into a new-hire onboarding document scoped to one role, with an access boundary enforced by omission rather than by mention, so restricted content never even gets hinted at.Claude EnterpriseClaude Team2026-08-07Get a structured diagnostic review from a screenshot, not just a description of itA vision prompt for reviewing a UI screenshot, error screen, or mockup that forces a severity-ranked list of specific, locatable issues instead of a general paragraph, with an explicit ban on fabricated precise measurements and a closing call on the best fix for the effort.Claude (Vision)Claude.ai2026-08-08
