More in Writing, slides & images.
Raise a newsletter open rate to 43% with Claude Cowork edits
WorkedEvidence: Described by posterPosted Last checked
Kyle Poyar's Claude Cowork editorial skill helped push open rate to 43% across 87,430 subscribers and save about 2 hours a week.
How to use this
- Tap Copy prompt.
- Open the tool the case used (or a similar one) and paste the prompt; results may differ from the original.
- Paste it into the message box.
- Replace anything in [CAPITAL LETTERS IN BRACKETS] with your own details.
- Send it, then read the answer before acting on it.
New to this? What's a prompt?
A prompt is the message you send to the AI tool. Copy the one on this page, put your own details where it asks, and read the answer before you act on it.
Prompt
Improved prompt
Our fuller version of the source's prompt, with fill-in details and rules, or one written to avoid what went wrong. Not tested by the poster.
Our fuller version of the person's prompt. They didn't use this version, and we haven't tested it.
Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish. Goal: Edit my newsletter draft to match my voice, catch errors and improve packaging. Questions to ask me first: - Where is the draft (Docs link) and my style samples? - Which subject-line history should you use? - Any claims that must be fact-checked first? Inputs (fill in or confirm): - Draft: [GOOGLE DOC LINK] - Style samples: [FILES] - Performance history: [BEEHIIV / CSV] - Connectors: [DRIVE / CHROME / OPTIONAL] Rules: - Preserve my voice; do not replace the piece with generic AI tone. - Fact-check claims with sources. - Suggest subject lines from what actually performed. - Leave tracked suggestions; I accept or reject. Checkpoint: Roast the ending and structure in a short note before rewriting. If you get stuck: If a claim cannot be verified, flag it instead of inventing a source. Verify before you finish: Every factual edit cites a check, and style notes reference my samples. Output: Annotated draft, subject-line options, and meta title/description ideas. Done when: I can publish a tighter issue without a multi-hour self-edit.
Customize this prompt
Answer the questions below and we'll put your answers into the prompt for you. You can leave any of them empty.
Your file stays on your device. Nothing is uploaded to TriedPrompts.
Your file stays on your device. Nothing is uploaded to TriedPrompts.
Your prompt
Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish. Goal: Edit my newsletter draft to match my voice, catch errors and improve packaging. Questions to ask me first: - Where is the draft (Docs link) and my style samples? - Which subject-line history should you use? - Any claims that must be fact-checked first? Inputs (fill in or confirm): - Draft: [GOOGLE DOC LINK] - Style samples: [FILES] - Performance history: [BEEHIIV / CSV] - Connectors: [DRIVE / CHROME / OPTIONAL] Rules: - Preserve my voice; do not replace the piece with generic AI tone. - Fact-check claims with sources. - Suggest subject lines from what actually performed. - Leave tracked suggestions; I accept or reject. Checkpoint: Roast the ending and structure in a short note before rewriting. If you get stuck: If a claim cannot be verified, flag it instead of inventing a source. Verify before you finish: Every factual edit cites a check, and style notes reference my samples. Output: Annotated draft, subject-line options, and meta title/description ideas. Done when: I can publish a tighter issue without a multi-hour self-edit.
Scroll to see the whole prompt. Your answers show in green.
3 blanks are still empty: Draft; Performance history; Connectors. They'll stay in brackets in your prompt, so the chat tool may ask you about them.
What you type stays in this browser tab. We don't send it or save it, and it's gone when you leave the page. If you use a "Try this in" button, your answers go to that tool as part of the prompt.
Try this in:
This prompt has blanks to fill in, like [GOOGLE DOC LINK]. We'll copy it instead of filling it in, so you can edit it before you send.
The source used Claude Cowork, which can take actions in a browser or app. These are general chat tools, so results may differ, and a normal chat may only give you a plan.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google, Anthropic or xAI, and your results may not match the source.
The prompt they actually used
The exact prompt from the source.
Help me create a skill that would (a) create a style guide tailored to me, (b) fact check every claim via web search, (c) review the flow and grammar of the piece, and (d) suggest SEO titles/descriptions. The output is a publish-ready version with suggestions as tracked changes.
AI tool
Outcome
Kyle Poyar time-boxes a first draft to 2–3 hours, then runs a Claude Cowork /content-editor skill that checks grammar, style, fact-checks claims, suggests subject lines from past performance, and flags SEO/AEO meta. The first pass roasted an ending that "reads like a manifesto, not Kyle's voice." Across 87,430 subscribers the newsletter open rate reached 43%, and the workflow saves about 2 hours every week. The LinkedIn post is an Anthropic #ClaudePartner #ad.
Evidence: Described by posterThe person describes what happened in words, without screenshots or video.
Source
- Posted
- by Kyle Poyar
- Last checked
- Method:
- How we verify
https://www.linkedin.com/posts/kyle-poyar_claudepartner-ad-activity-7496199609984135168-pne4
Context: Date estimated from LinkedIn's 2-month stamp. Sponsored Anthropic #ClaudePartner #ad post; open rate and subscriber count are the author's. Improved prompt structures the quoted skill-creator request.
More in Writing, slides & images
Cut transcript-to-article time from 3.5 hours to 63 minutes with Claude Cowork
Lusher Advisory's Claude Cowork webinar-to-Substack run fell from 3 to 3.5 hours to about 63 minutes with ChatGPT QA and human edits.
WorkedClaude Cowork +1Evidence: Described by posterView CaseSwitch from ChatGPT to Claude Projects for client work and slides
After two ChatGPT years and two Claude-first months, Mollie Mueller runs client Projects, morning dashboards and decks in Claude.
WorkedClaude +1Evidence: Described by posterView CaseAutomate a weekly content workflow with Claude Cowork and get 3 hours back
Ramesh moved weekly content ops onto Claude Cowork and got about 3 hours back each Sunday versus the old Notion-and-Docs grind.
WorkedClaude CoworkEvidence: Described by posterView CaseWrite client content in brand voice with Claude projects and skills
Alex Cohen's marketing firm now uses Claude for 80% to 90% of its AI work, with a skill that strips overused AI phrases.
WorkedClaude +1Evidence: Article or interviewView CaseFind real quotes about caregiving hardships with ChatGPT
ChatGPT failed to find real quotes about caregiving hardships for Laurie Watanabe and admitted it made up a quote.
FailureChatGPTEvidence: Article or interviewView CasePreview flower arrangement options before cutting a stem with ChatGPT Images
A florist had ChatGPT Images 2.0 mock up arrangements from real flowers and vases: 'polished provocations' before cutting a stem.
WorkedChatGPTEvidence: Article or interviewView Case

