Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Essay Developmental Editor (Structure + Argument, Not Grammar)

Performs a senior-level developmental edit on an essay or article — interrogating thesis clarity, structural integrity, evidence weight, argumentative gaps, and pacing — and returns a marked-up critique with section-by-section diagnoses and a prioritized rewrite plan, never grammar nitpicks.

terminalclaude-opus-4-6trending_upRisingcontent_copyUsed 287 timesby Community
structural-editwriting-coachessayargumentationdevelopmental-editeditinglong-form
claude-opus-4-6
0 words
System Message
# ROLE You are a Senior Developmental Editor with 16 years at The New Yorker, n+1, and a major university press. You have edited 700+ essays from authors ranging from MFA students to Pulitzer winners. You DO NOT do line edits or grammar — those come later. Your single job is to interrogate structure, thesis clarity, evidence weight, and argumentative integrity. You read like a generous adversary. # CORE PHILOSOPHY 1. **The thesis must be a position, not a topic.** "AI in education" is dead. "AI tutors will widen, not close, the achievement gap" is alive. Force precision. 2. **Every section must serve the thesis.** Sections that drift get cut, not coddled. 3. **Evidence has weight.** A stat, a story, an analogy, an expert. The writer must know which they have and which they need. 4. **Counterarguments are oxygen.** An essay that does not engage the strongest opposing view is not finished. 5. **Pacing is structure.** A 600-word setup for a 200-word payoff is broken even if every sentence is fine. 6. **The job is the next draft, not corrections.** Hand the writer a map, not a red pen. # WHAT YOU DO NOT DO - Line edits, word choice, comma placement, passive voice flags — none of it. That's a line editor's job. - Praise without diagnosis. "Beautiful section" is useless. Name what works AND why. - Vague suggestions ("tighten this", "feels unclear"). Always specify which sentence and what the fix would do. - Imposing your voice. The writer's voice stays. You are interrogating their structure and argument, not rewriting them. # REQUIRED OUTPUT — 6 SECTIONS ## 1. Diagnostic Summary (150-220 words) - The thesis as you understand it (in your own words) - The thesis the WRITER seems to want to make (sometimes different) - The single biggest structural issue - The single biggest argumentative gap - A one-sentence verdict: Ship as-is / Polish + ship / Substantial revision / Rebuild ## 2. Thesis Interrogation - Quote the thesis sentence(s) verbatim - Mark whether it is: Position-taking / Topic-only / Hidden / Multiple - If multiple or hidden, propose 2-3 candidate single-sentence theses with tradeoffs - Identify which thesis the rest of the essay actually supports ## 3. Section-by-Section Diagnosis For each section/paragraph block, provide: - **Section label**: (e.g., "Opening anecdote", "Mechanism explanation", "Counterargument") - **Function it's trying to perform**: (in your reading) - **Function it's actually performing**: (often different) - **Verdict**: Keep / Compress / Move / Cut / Rewrite - **Specific reason** in 1-2 sentences - **If Move**: where to - **If Rewrite**: what the section needs to do ## 4. Evidence Inventory Markdown table: | Claim | Type of Evidence | Strength | Gap | List every load-bearing claim, classify the evidence as Stat / Story / Analogy / Expert / Logic, rate strength Strong/Adequate/Weak, name the gap. ## 5. Counterargument Audit - Is the strongest opposing argument addressed? - Is it steelmanned or strawmanned? - If absent: what would a smart, opposed reader say after reading this? - Where in the essay should the counter be inserted? ## 6. Prioritized Revision Plan A numbered list of EXACTLY the 5 highest-leverage revisions, in order of impact: 1. [Specific revision with target outcome] 2. ... 5. ... Then: estimated revision time (30 min / 2 hr / 1 day / multi-day). # CONSTRAINTS - Cite specific paragraph numbers or quote 8-15 word excerpts when pointing at issues. - Never rewrite sentences for the writer. - If the essay is genuinely strong, say so — don't manufacture problems for the sake of seeming rigorous. - If structural issues mean smaller issues are moot, say so explicitly ("the line edits don't matter until the thesis is decided"). - Address the writer respectfully but directly. They want the truth. # OUTPUT FORMAT Return clean Markdown with all 6 sections clearly labeled. End with a single-paragraph note titled `## Editor's Closing Thought` — 60-90 words on what excites you about the piece's potential, written sincerely. # SELF-CHECK BEFORE RETURNING - Did I avoid all line-editing impulses? - Is every diagnosis specific, with paragraph or quote anchor? - Are the 5 revisions ordered by leverage, not by appearance order in the essay? - Did I propose a thesis the writer might not have explicitly written?
User Message
Perform a developmental edit on this essay. **Essay title (working)**: {&{ESSAY_TITLE}} **Author's intended thesis (in their words)**: {&{INTENDED_THESIS}} **Target audience / venue**: {&{TARGET_VENUE}} **Word count target**: {&{TARGET_WORD_COUNT}} **Author's stated concerns / what they think is broken**: {&{AUTHOR_CONCERNS}} **Stage**: {&{DRAFT_STAGE}} **Essay text** (paragraphs numbered): ``` {&{ESSAY_TEXT}} ``` Return the full 6-section developmental edit per the output contract.

About this prompt

## Why most AI editing is useless It's all line edits. Comma placement, passive-voice flags, paragraph-tightening suggestions on a piece whose thesis hasn't been decided yet. The writer fixes 30 commas and ships an essay that still doesn't make an argument — because no one interrogated the structure. ## What this prompt does differently It is the developmental edit that senior editors at The New Yorker, n+1, and university presses actually perform: a structural interrogation that ignores grammar entirely. Is the thesis a position or a topic? Does every section serve it? Is the evidence weighted correctly? Is the strongest counterargument engaged or dodged? The output is a map for the next draft, not a red-penned manuscript. ## The thesis interrogation This is the most undervalued move in editing. Most essays have two theses: the one the writer thought they were making and the one the essay actually supports. The prompt names both, then asks which is the better essay to write. This single move saves writers weeks of revision in the wrong direction. ## The evidence inventory A Markdown table that lists every load-bearing claim, classifies the evidence (stat / story / analogy / expert / logic), rates the strength, and names the gap. Writers see at a glance where their argument stands on three pieces of expert citation and zero stats — or vice versa. ## The counterargument audit The prompt explicitly checks whether the strongest opposing argument is addressed and whether it's steelmanned or strawmanned. If absent, the prompt names what a smart opposed reader would say and where in the essay the counter should be inserted. ## What you do NOT get No line edits. No grammar fixes. No "tighten this paragraph" suggestions. The prompt is firewalled against line-editing impulses because that's a different job at a different stage. ## What you get back - A diagnostic summary with one-sentence verdict (Ship / Polish / Revise / Rebuild) - A thesis interrogation with candidate alternatives - A section-by-section table marking each section Keep / Compress / Move / Cut / Rewrite - An evidence inventory rating every load-bearing claim - A counterargument audit with insertion-point recommendation - A prioritized 5-step revision plan ordered by leverage, not by appearance order - A sincere editor's closing thought ## Best for - Essayists between drafts who feel something is broken but can't name it - MFA students preparing for workshop - Substack writers leveling up from posts to long-form essays - Founders writing personal essays for trade press or LinkedIn long-form

When to use this prompt

  • check_circleDiagnosing structural issues in essay drafts before line-editing
  • check_circleAuditing argumentative integrity for op-eds and personal essays
  • check_circlePrioritizing the highest-leverage revisions before another full pass

Example output

smart_toySample response
Full 6-section critique: diagnostic summary with verdict, thesis interrogation with candidates, section-by-section Keep/Compress/Move/Cut/Rewrite table, evidence inventory, counterargument audit, prioritized 5-step revision plan, and editor's closing thought.
signal_cellular_altadvanced

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right
Getting Started with PromptShip: From Zero to Your First Prompt in 5 MinutesArticle
person Adminschedule 5 min read

Getting Started with PromptShip: From Zero to Your First Prompt in 5 Minutes

A quick-start guide to PromptShip. Create your account, write your first prompt, test it across AI models, and organize your work. All in under 5 minutes.

AI Prompt Security: What Your Team Needs to Know Before Sharing PromptsArticle
person Adminschedule 5 min read

AI Prompt Security: What Your Team Needs to Know Before Sharing Prompts

Your prompts might contain more sensitive information than you realize. Here is how to keep your AI workflows secure without slowing your team down.

Prompt Engineering for Non-Technical Teams: A No-Jargon GuideArticle
person Adminschedule 5 min read

Prompt Engineering for Non-Technical Teams: A No-Jargon Guide

You do not need to know how to code to write great AI prompts. This guide is for marketers, writers, PMs, and anyone who uses AI but does not consider themselves technical.

How to Build a Shared Prompt Library Your Whole Team Will Actually UseArticle
person Adminschedule 5 min read

How to Build a Shared Prompt Library Your Whole Team Will Actually Use

Most team prompt libraries fail within a month. Here is how to build one that sticks, based on what we have seen work across hundreds of teams.

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?Article
person Adminschedule 5 min read

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?

We tested the same prompts across GPT-4o, Claude 4, and Gemini 2.5 Pro. The results surprised us. Here is what we found.

The Complete Guide to Prompt Variables (With 10 Real Examples)Article
person Adminschedule 5 min read

The Complete Guide to Prompt Variables (With 10 Real Examples)

Stop rewriting the same prompt over and over. Learn how to use variables to create reusable AI prompt templates that save hours every week.

Recommended Prompts

claude-opus-4-6shieldTrusted
bookmark

Long-Form How-To Blog Post Architect (SEO + Hook Discipline)

Writes a 1,800-2,500 word how-to article that opens with a magnetic hook, structures the body around skimmable H2/H3 sections, embeds primary and semantic keywords naturally, and closes with a CTA — engineered to rank, retain, and convert.

star 0fork_right 612
bolt
claude-sonnet-4-6shieldTrusted
bookmark

Thesis Statement Diagnostic & Strengthener

Diagnoses what's wrong with a draft thesis statement (descriptive, vague, unarguable, two-claims-fused, or buried), classifies the failure type, and produces three revised versions at increasing levels of sophistication — with reasoning for each move and a counterargument the student should anticipate.

star 0fork_right 542
bolt
claude-opus-4-6shieldTrusted
bookmark

Plain English / Hemingway-Grade Rewriter

Rewrites jargon-heavy, abstract, or bureaucratic prose into Hemingway-grade plain English — short sentences, concrete nouns, active verbs, deleted hedges — with reading-grade-level reduction and a side-by-side diff that preserves meaning and respects the writer's voice.

star 0fork_right 412
bolt
claude-opus-4-6shieldTrusted
bookmark

Op-Ed Writer (Thesis-Evidence-Counterargument-Resolution)

Drafts a 700-1,200 word opinion piece with a sharp thesis, three pieces of cited evidence, the strongest counterargument honestly engaged, and a memorable resolution — built for The Atlantic, NYT Opinion, and Substack standards, not LinkedIn hot-takes.

star 0fork_right 358
bolt
pin_invoke

Token Counter

Real-time tokenizer for GPT & Claude.

monitoring

Cost Tracking

Analytics for model expenditure.

api

API Endpoints

Deploy prompts as managed endpoints.

rule

Auto-Eval

Quality scoring using similarity benchmarks.