Instrument

Gemini prompts

Prompts written for Gemini by Google — badges mark the exact versions they were tested on.

31 prompts
Agents & Automation ⚙ AGENT

RAG Assistant System Prompt (Grounded, With Citations)

System prompt for retrieval-augmented assistants that actually stays grounded: strict source discipline, inline citations, and honest "not in the docs" answers.

✓ Claude Sonnet 4.5Gemini 2.5 Pro
★ 134⧉ 1105◌ 0LLM Atlas Team · 2mo ago
Career ¶ TEXT

ATS Keyword Gap Analyzer (Resume vs. Job Description)

Compares your resume against a job description the way screening software and recruiters do: matched terms, missing must-haves, and honest rewrites — no keyword stuffing.

GPT-5✓ Claude Sonnet 4.5Gemini 2.5 Pro
★ 66⧉ 520◌ 0LLM Atlas Team · 1mo ago
Education & Learning ¶ TEXT

Language Conversation Partner with Gentle Corrections

A patient conversation partner that keeps the dialogue flowing at your level, corrects only what matters, and recycles your mistakes into later practice.

✓ GPT-4oGemini 2.5 Flash
★ 93⧉ 705◌ 0LLM Atlas Team · 2mo ago
Education & Learning ¶ TEXT

Strict Socratic Tutor (Never Gives the Answer)

A tutor that refuses to hand over answers — it diagnoses what you already know, asks one question at a time, and resists every trick students use to extract the solution.

✓ Claude Sonnet 4.5Gemini 2.5 Pro
★ 63⧉ 490◌ 0LLM Atlas Team · 1mo ago
Business & Productivity ¶ TEXT

Meeting Minutes & Action Items from Transcript

Distills a raw meeting transcript into decisions, action items with owners and dates, and open questions — flagging anything ambiguous instead of guessing.

✓ Claude Haiku 4.5Gemini 2.5 Flash
★ 95⧉ 810◌ 0LLM Atlas Team · 2mo ago
Education & Learning ¶ TEXT

Spaced-Repetition Flashcards from Notes

Converts study notes into atomic, well-formed Anki-style flashcards following the 20 rules of formulating knowledge — no orphan cards, no lists to memorize.

Claude Haiku 4.5Gemini 2.5 Flash
★ 86⧉ 680◌ 0LLM Atlas Team · 2mo ago
Writing ¶ TEXT

Humanize an AI-Sounding Draft

Strips the telltale AI cadence out of a draft — banned-word list, rhythm variation, and concrete detail injection — without losing the substance.

GPT-5✓ Claude Sonnet 4.5Gemini 2.5 Pro
★ 61⧉ 470◌ 0LLM Atlas Team · 1mo ago
Marketing & SEO ¶ TEXT

SEO Content Brief Generator

Builds a complete SEO content brief from a target keyword: search intent analysis, heading structure, entities to cover, and questions to answer.

GPT-5Gemini 2.5 Pro
★ 91⧉ 740◌ 0LLM Atlas Team · 2mo ago
Coding & Dev ¶ TEXT

Unit Test Generator with Real Edge Cases

Generates unit tests that actually probe boundaries and failure modes — not three happy-path tests with different variable names.

✓ Claude Sonnet 4.5Gemini 2.5 Pro
★ 92⧉ 750◌ 0LLM Atlas Team · 2mo ago
Data & Research ¶ TEXT

Spreadsheet Formula Engineer (Excel & Google Sheets)

Builds the formula you describe in plain English — then explains it part by part, states its breaking conditions, and offers a cleaner LET/helper-column alternative.

✓ GPT-5Claude Sonnet 4.5Gemini 2.5 Flash
★ 57⧉ 440◌ 0LLM Atlas Team · 1mo ago
Data & Research ¶ TEXT

Exploratory Data Analysis Plan

Builds a rigorous EDA plan for a new dataset: data quality gauntlet first, then targeted hypotheses, with the exact plots and the traps each one hides.

o3Gemini 2.5 Pro
★ 72⧉ 545◌ 0LLM Atlas Team · 2mo ago
Data & Research ¶ TEXT

Literature Review Synthesizer

Synthesizes multiple papers into a thematic review — where studies agree, where they conflict and why, and what nobody has studied yet.

Gemini 2.5 Pro
★ 57⧉ 420◌ 0LLM Atlas Team · 1mo ago
Education & Learning ¶ TEXT

Lesson Plan with Built-In Assessment

Designs a complete lesson plan working backward from what students should be able to DO — misconception traps, timed activities, and an exit ticket that measures the objective.

Gemini 2.5 Pro
★ 49⧉ 355◌ 0LLM Atlas Team · 1mo ago
Coding & Dev ¶ TEXT

Conventional Commit Message from a Diff

Writes a Conventional Commits message from a staged diff — correct type and scope, imperative subject under 72 chars, a body that explains why, and a warning when the diff should be split.

✓ Claude Sonnet 4.5Claude Haiku 4.5Gemini 2.5 Flash
★ 48⧉ 356◌ 0LLM Atlas Team · 1mo ago
Coding & Dev ¶ TEXT

API Reference Writer (From Source Code)

Turns source code into precise API reference documentation, with honest edge-case notes and runnable examples for every public function.

Gemini 2.5 Pro
★ 38⧉ 260◌ 0LLM Atlas Team · 1mo ago
Coding & Dev ¶ TEXT

Production Log Forensics

Turns a pile of multi-service log lines into a causal timeline: separates the first anomaly from downstream noise and tells you exactly which log to pull next.

✓ o3Gemini 2.5 Pro
★ 45⧉ 322◌ 0LLM Atlas Team · 1mo ago
Marketing & SEO ¶ TEXT

Keyword Clustering & Topical Map Builder

Groups a raw keyword list into intent-based clusters, maps them into a hub-and-spoke topical architecture, and flags which clusters need one page versus many.

GPT-5Gemini 2.5 Pro
★ 41⧉ 300◌ 0LLM Atlas Team · 1mo ago
Data & Research ¶ TEXT

Research Paper Deconstructor

Breaks an academic paper into what was claimed, what was actually shown, and how much to trust it — methods scrutiny, effect sizes over p-values, and the graveyard of caveats.

Claude Opus 4.5Gemini 2.5 Pro
★ 43⧉ 315◌ 0LLM Atlas Team · 1mo ago
Coding & Dev ¶ TEXT

Test Suite Auditor — Gaps, Flakiness, False Confidence

Audits an existing test suite for the tests that lie: assertion-free tests, mock-everything tests, flakiness time bombs, and the failure paths nobody covered.

Claude Opus 4.5Gemini 2.5 Pro
★ 29⧉ 197◌ 0LLM Atlas Team · 1mo ago
Agents & Automation ⚙ AGENT

RAG Groundedness Verifier (Claim-by-Claim)

The verification stage of a RAG pipeline: decomposes an answer into atomic claims and labels each SUPPORTED, CONTRADICTED, or NOT_FOUND against the sources — inference is not support.

✓ Claude Sonnet 4.5Gemini 2.5 Pro
★ 42⧉ 301◌ 0LLM Atlas Team · 1mo ago
LLM Atlas

A free map of prompts that actually work — tested on real models, starred by real people.

© 2026 LLM AtlasPrompts default to CC0 unless stated.