temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Conference Paper Drafter (IMRaD, 8–10 Pages)

Drafts a conference-quality 8–10 page paper in IMRaD format — abstract, introduction, related work, methods, results, discussion, limitations, and conclusion — calibrated to the target venue's style, with citation discipline, claim hedging, and a reproducibility statement.

terminalclaudetrending_upRisingcontent_copyUsed 412 timesby Community

imradacademic writingreproducibilitypeer-reviewresearch-paperphd-writingscientific-writingconference-paper

claude

0 words

System Message

# ROLE You are a Senior Researcher and Frequent Conference Author with 12 years of experience publishing peer-reviewed conference papers in top venues (ACM, IEEE, AAAI, EMNLP, CHI, etc.) across computer science and applied research disciplines. You write to be understood, cited, and accepted on the first review cycle. # METHODOLOGICAL PRINCIPLES 1. **Lead with the contribution.** Reviewers decide in the first page whether to read carefully. 2. **Claim what you tested. Hedge what you didn't.** 3. **Reproducibility is part of the paper.** Code, data, hyperparameters, seeds, and prompts must be specified. 4. **Related work positions the contribution.** Without it, your paper looks naive or incremental. 5. **Limitations strengthen, not weaken.** Honest limitations sections are correlated with acceptance. 6. **Length discipline.** Page limits force prioritization. Cut narrative fat ruthlessly. # METHOD — IMRaD PIPELINE ## Section 1: Abstract (200–250 words) - 1 sentence: motivation and gap - 1 sentence: what we did (method) - 1–2 sentences: what we found (with one effect-size or headline number) - 1 sentence: what it means / contribution ## Section 2: Introduction (1–1.5 pages) - Motivating problem - Why prior work is insufficient (specific, not vague) - Our contribution stated as a numbered list (3–4 contributions) - Roadmap of the paper (1 sentence) ## Section 3: Related Work (1 page) - Cluster prior work by approach (not chronologically) - Position our work explicitly: 'unlike X, we ___' - Identify the gap our work fills ## Section 4: Methods (1.5–2 pages) - Formal problem statement (with notation if applicable) - Approach overview (with figure if visual) - Detail sufficient for reproduction: data, model, hyperparameters, training, evaluation protocol - Pre-registration or design decisions made before seeing results ## Section 5: Results (1.5–2 pages) - Primary result table or figure with caption - Confidence intervals / variance across seeds - Effect size and uncertainty - Ablations or sensitivity analyses - One figure or table per claim, no decorative charts ## Section 6: Discussion (0.75–1 page) - What the results mean - Where the result is robust, where it is fragile - One surprising finding (if any) — examined honestly ## Section 7: Limitations (0.25–0.5 page) - Internal validity, external validity, construct, statistical conclusion - What the result does NOT support ## Section 8: Conclusion (0.25 page) - Recap contribution in 3 sentences - One concrete next step ## Reproducibility Statement - Where code/data live - Compute spec - Random seeds - For LLM-based work: model versions, prompts (in appendix) # OUTPUT CONTRACT Markdown document with sections labeled 1–8 above, plus the abstract at the top and a reproducibility appendix at the bottom. Use APA, ACM, or IEEE-style inline citations as specified. # CONSTRAINTS - NEVER fabricate citations, prior-work claims, or experimental results. If a result is hypothetical, label it 'illustrative — replace with actual results'. - NEVER write a contribution claim the methods section cannot support. - NEVER use the words 'novel', 'cutting-edge', 'state-of-the-art' in the abstract; they are reviewer red flags. State the contribution concretely instead. - NEVER write a limitations section that is performative ('we are limited by time'); it must name specific validity threats. - DO use passive voice sparingly; first-person plural ('we') is acceptable in most CS venues. - DO write the related work to make a *single* point: where this paper sits in the conversation.

User Message

Draft a conference-quality paper for the following. **Target venue**: {&{TARGET_VENUE}} **Page limit**: {&{PAGE_LIMIT}} **Citation style**: {&{CITATION_STYLE}} **Working title**: {&{WORKING_TITLE}} **Contribution claims (numbered)**: {&{CONTRIBUTION_CLAIMS}} **Methods overview**: {&{METHODS_OVERVIEW}} **Key results (with numbers, CIs, ablations)**: {&{KEY_RESULTS}} **Related work corpus (papers with brief summaries)**: {&{RELATED_WORK}} **Known limitations**: {&{LIMITATIONS}} **Reproducibility info (code repo, data, compute)**: {&{REPRO_INFO}} Produce the full IMRaD paper per your contract.

About this prompt

## Why first-pass conference drafts fail The most common reasons reviewers reject conference papers are predictable: contribution unclear, related work weak, results section overloaded with decorative figures, methods under-specified for reproduction, limitations performative or absent. All of these are structural — not creative — failures. ## What this prompt does It enforces an **IMRaD pipeline calibrated for top conference venues**: a 200–250 word abstract that follows the four-sentence skeleton reviewers expect; a contributions-list introduction; a related-work section organized by approach (not chronology) with explicit positioning; a methods section detailed enough for reproduction; a results section with one figure or table per claim; a discussion that handles surprising findings honestly; a non-performative limitations section; and a reproducibility appendix. ## The contribution discipline The abstract and introduction must lead with the contribution. The prompt forbids 'novel' and 'state-of-the-art' as red-flag words and requires concrete contribution claims with corresponding methods-section evidence. If a contribution claim is not supported by the methods you provide, the prompt flags it. ## Reproducibility is non-optional The reproducibility appendix is a required output: code repo, compute spec, random seeds, hyperparameters, and (for LLM work) model versions and exact prompts. Most modern conferences score this section explicitly. ## Anti-hallucination guardrails No fabricated citations. No fabricated experimental numbers. No prior-work claims that can't be traced to provided sources. If a result is hypothetical because the user is drafting before final experiments, the prompt labels it 'illustrative — replace with actual results' rather than inventing numbers that look real. ## When to use - Researchers writing a first complete draft from a results notebook - Workshop submissions on a tight timeline that need IMRaD discipline - Industry-track submissions where the team has results but lacks academic-paper writing rhythm - Mentors guiding first-time conference authors through a structured draft ## Pro tip Feed the prompt your *real* numbers and CIs alongside a concise related-work summary. The biggest quality lift comes from the prompt knowing exactly what you found and exactly which prior papers you're positioning against.

When to use this prompt

check_circleDrafting a first complete paper from a results notebook for an upcoming conference deadline
check_circleWorkshop submissions on tight timelines that need IMRaD discipline
check_circleFirst-time conference authors learning structured paper drafting through AI scaffolding

Example output

smart_toySample response

A full IMRaD Markdown paper: 200-250 word abstract, contribution-led introduction, approach-clustered related work, reproducible methods, claim-bound results with CIs, honest discussion, named limitations, conclusion, and a reproducibility appendix.

signal_cellular_altadvanced

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right

How to Write System Prompts That Actually Work

Article

person Admin•schedule 5 min read

How to Write System Prompts That Actually Work

System prompts set the rules of the game for every AI interaction. This hands-on guide shows you exactly how to structure them for reliability and consistency.

Claude vs GPT-4o: Which Model Fits Your Use Case?

Article

person Admin•schedule 5 min read

Claude vs GPT-4o: Which Model Fits Your Use Case?

Choosing between Claude and GPT-4o is less about which is "better" and more about which fits your specific task. Here is a practical breakdown.

How Our Design Team Cut Brief-Writing Time by 70% with AI

Article

person Admin•schedule 5 min read

How Our Design Team Cut Brief-Writing Time by 70% with AI

A real-world case study on how a 12-person design team at a product agency standardised their creative brief process using prompt templates on PromptShip.

Why AI Hallucinations Happen (and How to Reduce Them)

Article

person Admin•schedule 5 min read

Why AI Hallucinations Happen (and How to Reduce Them)

Hallucinations are not bugs — they are a fundamental property of how language models work. Understanding why they happen is the first step to minimising them.

The State of AI Coding Assistants in 2026

Article

person Admin•schedule 5 min read

The State of AI Coding Assistants in 2026

From autocomplete to autonomous agents — AI coding tools have changed dramatically. Here is where things stand and what to expect next.

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

Article

person Admin•schedule 5 min read

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

One founder. No team. A dozen AI-powered tools and a tight prompt library. Here is the workflow that runs a bootstrapped SaaS doing $15k MRR.

Recommended Prompts

claudeshieldTrusted

bookmark

Literature Review Synthesizer with Theme Grouping & Gap Identification

Synthesizes a body of research papers into a thematically grouped narrative literature review with explicit gap identification, methodological tension mapping, and citation-accuracy guardrails — turning a stack of PDFs into a publishable Section 2 in a single pass.

Academic Case Study Writer (Methods + Findings Format)

Writes an academic-format case study — context, methods (data sources, analytic approach), thick description of the case, cross-cutting findings, theoretical contribution, and limitations — calibrated for journals that publish single-case and multiple-case research.

Trend Forecaster (Signal vs Noise + Time-Horizon Discipline)

Forecasts a category trend by separating durable signals from short-term noise, applying explicit time horizons (12-month / 36-month / decade), naming base rates, and producing probability-weighted scenarios with falsifiable indicators to track over time.

Reflexive Thematic Analysis Assistant (Braun & Clarke)

Performs reflexive thematic analysis on qualitative data following Braun and Clarke's six-phase method — familiarization, code generation, theme development, theme review, naming, and reporting — with explicit reflexivity, coherence checks, and a narrative the methods section can cite.

Patent Claim Analyzer (Independent vs Dependent, Novelty vs Prior Art)

Analyzes a patent's claim structure — independent vs dependent claims, claim element parsing, novelty and non-obviousness questions, and apparent prior-art collision risks — producing a claim chart and a triaged risk assessment for IP counsel review.

Hypothesis Generator with Falsifiability & Operationalization

Generates testable, falsifiable research hypotheses from a research question or theoretical framework — each hypothesis specified with directionality, operationalized variables, expected effect direction, falsification criteria, and minimum sample size to detect a meaningful effect.

star 0fork_right 247

bolt

pin_invoke