Outrank a Competitor Article from One URL

Prompt

Act as an SEO editor whose job is to outrank a specific competitor article without copying it and without inventing sources. Produce an outline, a differentiated angle, missing subtopics, and an E-E-A-T plan a human writer can execute.

Inputs:
- Competitor URL: [URL]
- Topic: [Topic]
- Audience: [Audience]
- Our site: [Our site]
- What we can uniquely say: [Unique]
- Constraints: [Constraints]
- Live page notes: [Page notes]

Generate:
1. How this analysis was built: If Live page notes contain pasted headings or counts, treat them as Provided. If the URL cannot be fetched, work from the slug, brand, and Topic only, and label every page-structure claim as Assumed. Never invent a quote, statistic, author bio, or citation from the competitor.
2. Competitor snapshot: Likely search intent. Likely outline shape (Assumed unless notes exist). What a ranking page on this topic usually does well. Where pages like this usually fail (thin method, no troubleshooting, no doneness cues, no "why it failed," no variations). Fairness rule: do not trash the competitor; out-execute them.
3. Differentiation: One sentence angle that is not "more comprehensive." Name the reader job we will finish that they leave hanging. Who we are not serving.
4. Missing subtopics (8-12): Each with why it maps to a real question, not a keyword dump. Star the 5 that should be in v1.
5. Better outline: H1. Then H2/H3 with: intent of the section, what the reader can do after it, media needed (photo, table, timer). Include intro promise, method, variations, troubleshooting, FAQs. No "in this article we will."
6. Title and SERP: 6 title tag options (under 60 characters, honest). 4 meta descriptions (under 155). 1 H1. Do not stuff the year unless the method changed.
7. E-E-A-T plan: Experience we must show (first-person method, photos, failures). Expertise signals (technique, not resume stuffing). Author/reviewer suggestion. What we will not claim. Citation policy: only cite sources the writer will actually attach; list 4 source types (for food: safety agency, technique reference, our test notes, equipment maker spec) and write "do not invent a study."
8. Brief for the writer: Word target. Table/checklist to include. Photos to shoot. 5 FAQs. Internal links as roles, not fake URLs. A do-not-copy reminder: no lifting sentences from the competitor URL.
9. Risk list: 5 ways this still loses (thin photos, same outline, nutrition overclaim, duplicate intros, no unique data). How to prevent each.

Constraints:
- Do not invent citations, quotes from the competitor, comment counts, backlinks, or word counts.
- Do not paste or closely paraphrase the competitor's unique wording.
- Nutrition, safety, or health claims: hedge or cut unless Inputs include a source.
- Outline must be executable by the named Audience in one read.
- If Live page notes are empty or "could not fetch," more Assumed labels, not more fake detail.
- Honor What we can uniquely say. Do not add lab tests, chef credentials, or photos the site does not have.

Instructions

Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.

Examples

Example Input

Competitor URL: https://www.simplyrecipes.com/how-to-make-scrambled-eggs-5092690
Topic: how to make scrambled eggs
Audience: home cooks
Our site: a home-cooking blog with test-kitchen notes, no celebrity chef; we can shoot our own photos
What we can uniquely say: we tested 3 pans, 2 heat levels, dairy vs no dairy, and we will describe what failed
Constraints: about 1,800 words; not medical nutrition advice; warm practical voice
Live page notes: could not fetch a full paste; if you can open the URL, use what you see and label it Provided; if you cannot, say so and proceed with Assumed labels. Do not invent citations.

Example Output

1. How this analysis was built
Live page notes say a full paste was not available. This run did not treat competitor headings, word counts, quotes, or author bio as Provided. Every page-structure claim below is Assumed from the slug (how-to-make-scrambled-eggs), the Simply Recipes brand, and the topic. No invented citations, comments, or statistics from that URL.

2. Competitor snapshot
Likely intent: I, "show me a reliable method tonight." Assumed outline shape for a ranking how-to: intro, ingredients, step method, a few tips, variations, FAQs. Ranking pages on this topic usually do well with clear heat cues, a photo sequence, and a default ratio of eggs to fat. They usually fail when the method is one heat setting, no doneness cue, no "why it failed," and no pan comparison. Fairness: Simply Recipes is a known recipe publisher; we out-execute with our own tests, we do not trash the brand.

3. Differentiation
Angle: we cooked the same eggs in 3 pans, at 2 heat levels, with dairy and without, and we will say what failed. Reader job we finish: pick a pan and a heat so the curd matches what they want, not just "follow steps." Not serving: restaurant brunch volume, medical nutrition, or celebrity-chef technique theater.

4. Missing subtopics (* = v1)
*Pan choice (nonstick vs stainless vs cast iron) and what failed. *Low vs medium heat, same pan. *Dairy vs no dairy, same eggs. *Doneness cues (wet shine, large curd, dry). *Troubleshooting: watery, brown, rubber. When to salt. Stirring style (push vs scramble). Leftover and reheat honesty. Scaling 2 eggs vs 6. Butter vs oil. Serving window before they seize.
Each maps to a real "why did mine fail" question, not a keyword dump.

5. Better outline
H1: Scrambled Eggs: What Worked (and Failed) Across 3 Pans
Intro promise: after this you can pick pan, heat, and dairy so the curd matches what you want. No "in this article we will."
H2 Method default (intent: one path that works). After: cook 2-3 eggs without looking up mid-stir. Media: step photos, 1 timer cue.
H2 The test grid (intent: unique data). After: know which pan/heat pairing we would repeat. Media: table (3 pans x 2 heats x dairy/no dairy), failure notes.
H3 What failed (intent: trust). After: avoid the combo that browned or wept. Media: one ugly photo.
H2 Doneness cues. After: stop by look, not a clock alone. Media: 3 close-ups.
H2 Variations: no dairy, extra fat, more eggs. After: adjust without a new recipe. Media: none required.
H2 Troubleshooting. After: fix watery / brown / rubber. Media: checklist.
H2 FAQs. After: leftover questions answered.

6. Title and SERP
Title tags (under 60): Scrambled Eggs: 3 Pans, 2 Heats, What Failed | How to Make Scrambled Eggs That Match Your Pan | Scrambled Eggs Method, Tested in 3 Pans | Soft Scrambled Eggs Without Guessing Heat | Scrambled Eggs: Dairy vs No Dairy | Pan-by-Pan Scrambled Eggs
Metas (under 155): We tested 3 pans, 2 heat levels, and dairy vs none, and wrote down what failed. | A home-kitchen method with doneness photos, a test table, and the combos we would not repeat. | Pick a pan and a heat. Then cook scrambled eggs that match the curd you want. | What worked in nonstick, stainless, and cast iron, including the batches that went wrong.
H1: Scrambled Eggs: What Worked (and Failed) Across 3 Pans
No year stuffing.

7. E-E-A-T plan
Experience: first-person test notes, photos of success and failure, named pans we own. Expertise: heat, curd size, when to pull, not a resume. Author: the cook who ran the grid; reviewer optional if a second cook repeats one row. We will not claim nutrition, cholesterol advice, or food-safety times we did not source. Citation policy: only attach sources the writer will actually use. Four types: safety agency (if we discuss leftovers), a technique reference the writer owns, our test notes, equipment maker spec for the pans. Do not invent a study.

8. Brief for the writer
Word target: about 1,800. Include the 3x2x2 test table and a troubleshooting checklist. Photos to shoot: default method sequence, 3 doneness close-ups, 3 pan results, 1 failure. FAQs: Do I add milk? When do I salt? Stainless stuck, now what? Can I hold them? How do I scale to 6 eggs? Internal links as roles: breakfast hub, egg-doneness glossary, nonstick-care note. Do not copy or closely paraphrase sentences from the competitor URL.

9. Risk list
Thin photos: shoot the grid the same day as the words. Same outline as every how-to: lead with the test table, not a generic intro. Nutrition overclaim: no macros or health promises. Duplicate intros: one promise paragraph, then the method. No unique data: if a test row is missing, do not publish that cell; run it.