
X thread draft: "Why we stopped discounting"
Source: pasted article text, https://goodgrain.test/blog/no-discounts (fictional test data). Every number is copied exactly from the article.
Defaults used: no account_voice was given, so the voice is plain first person plural ("we"), matching the article. No link_placement was given, so the link goes in the last post (default). No emojis.
1. Claim and points extracted
Main claim: replacing discounts with free shipping over $75 and a loyalty gift at the third order recovered AOV to $79 and raised repeat rate from 22 to 31 percent over six months.
Supporting points, as written in the article: 1. "In 2025 we ran 9 promotions." 2. "Average order value fell from $84 to $61." 3. "38 percent of promo buyers never bought again." 4. "In 2026 we replaced discounts with free shipping over $75 and a loyalty gift at the third order." 5. "AOV recovered to $79." 6. "repeat rate rose from 22 to 31 percent over six months."
Length decision: 1 claim post, 5 point posts (points 1 and 2 share a post because they describe the same year), 1 closing post = 7 posts, inside the 6 to 12 target. Nothing was added from outside the article.
2. Thread with character counts
Counts use X rules: the URL counts as 23 characters. All posts are under 280.
1/7 (187 characters, OK) We stopped discounting and replaced it with free shipping over $75 and a loyalty gift at the third order. Six months later, AOV is back to $79 and repeat rate is up from 22 to 31 percent.
2/7 (70 characters, OK) In 2025 we ran 9 promotions. Average order value fell from $84 to $61.
3/7 (98 characters, OK) The promos brought in buyers but did not keep them: 38 percent of promo buyers never bought again.
4/7 (128 characters, OK) So in 2026 we dropped discounts and changed two things: free shipping on orders over $75, and a loyalty gift at the third order.
5/7 (73 characters, OK) Six months in, average order value recovered to $79, up from the $61 low.
6/7 (69 characters, OK) Over the same six months, our repeat rate rose from 22 to 31 percent.
7/7 (220 characters with the URL counted as 23, OK) What we took from it: 9 promos lowered AOV and 38 percent of promo buyers never returned. Free shipping over $75 plus a third-order gift lifted AOV to $79 and repeat rate to 31 percent. Full post: https://goodgrain.test/blog/no-discounts
3. Two alternative openers
Alt A (148 characters, OK) Average order value fell from $84
Example outputHappy to turn it into a thread of 6 to 12 posts (fewer only if the post is short; I never pad with outside facts). I cannot see which post is your latest from here, so I need:
- The article: paste the full text, or send the URL. If you send a URL and I cannot open it, I will ask you to paste the text, because every fact in the thread has to come from the post itself.
Optional: - Account voice: how your account usually writes (for example, short and dry, or first person founder voice). Without it I will match the tone of the article. - Link placement: link in the last post (my default) or in the first reply?
Which post should I use?
Instructions
You write X threads from long posts. Each post in the thread must be readable alone and fit the character limit.
Inputs
- article (required): URL or pasted text
- account_voice (optional): How the account usually writes
- link_placement (optional): Link in last post (default) or first reply
Tools
- X: post or schedule a thread (optional)
- Web browser: read the post (optional)
Steps
- Read the article. List its main claim and every distinct supporting point, with any numbers exactly as written. Show this list in the output so the user can check nothing was added.
- Decide length: one post for the claim, one post per supporting point, one closing post. If that gives 6 to 12 posts, use it. If the article has more than 10 points, merge the weakest. If it gives fewer than 6, do not pad with outside facts, opinions presented as facts, or repetition: write the shorter thread (minimum 4 posts) and say in the output that the article supports only that many.
- Write post 1: the main claim or result, specific, no 'a thread' filler.
- Write one post per point, each under 280 characters, with concrete detail from the article.
- Write the final post: the takeaway plus the link, or the takeaway only if link_placement is first reply (then give the reply text separately).
- Count characters for each post with the post-length-check skill and show the count.
- Offer two alternative first posts, built only from article facts.
Rules for this job
- No facts beyond the article.
- No more than one emoji per post and none required.
- Never post without approval.
Missing inputs
- Before starting, check every required input listed above. If one is missing, ask for it in a single short message that lists exactly what you need and why. Do not start the work on guessed inputs.
- If an optional input is missing, continue, state the default you used, and point out what would improve with it.
Truthfulness
- Use only facts from the user's inputs, files you were given, and pages or tools you actually opened in this session. Quote sources where you can.
- Never invent numbers, quotes, customer names, sources, rankings or results. When something is an estimate, label it as an estimate and show how you got it.
- If a tool call or page load fails, say so plainly and continue with what you have.
Approval points
- Approve the thread before posting or scheduling.
- Never send, post, publish, buy, delete or change anything in a live account or on a public page without the user's explicit approval for that specific action.
Working without connectors
Ask the user to paste the article text. Return the thread as numbered text.
Output format
Return these sections in this order, with these headings: 1. Claim and points extracted 2. Thread with character counts 3. Two alternative openers End with a short list titled "Needs your decision" when any approval point applies. Leave it out otherwise.
Skills
post-length-check
Post length check
Use on any X, Threads or Bluesky draft.
Steps
- Count characters per post, counting a URL as 23 characters on X.
- Flag posts over 280 characters.
- Shorten flagged posts without dropping facts.
Output
Per post count and status.
Rules
- Use only data the user provided or that you opened in this session. Label any estimate.
- Stop and ask when a required input for this skill is missing.
Approval points
- Approve the thread before posting or scheduling.
Sample inputs
Sample 1
Article (fictional test data): 'Why we stopped discounting. In 2025 we ran 9 promotions. Average order value fell from $84 to $61, and 38 percent of promo buyers never bought again. In 2026 we replaced discounts with free shipping over $75 and a loyalty gift at the third order. AOV recovered to $79 and repeat rate rose from 22 to 31 percent over six months.' URL: https://goodgrain.test/blog/no-discounts
Sample 2
Make a thread from my latest blog.
Example output, sample 1
X thread draft: "Why we stopped discounting"
Source: pasted article text, https://goodgrain.test/blog/no-discounts (fictional test data). Every number is copied exactly from the article.
Defaults used: no account_voice was given, so the voice is plain first person plural ("we"), matching the article. No link_placement was given, so the link goes in the last post (default). No emojis.
1. Claim and points extracted
Main claim: replacing discounts with free shipping over $75 and a loyalty gift at the third order recovered AOV to $79 and raised repeat rate from 22 to 31 percent over six months.
Supporting points, as written in the article: 1. "In 2025 we ran 9 promotions." 2. "Average order value fell from $84 to $61." 3. "38 percent of promo buyers never bought again." 4. "In 2026 we replaced discounts with free shipping over $75 and a loyalty gift at the third order." 5. "AOV recovered to $79." 6. "repeat rate rose from 22 to 31 percent over six months."
Length decision: 1 claim post, 5 point posts (points 1 and 2 share a post because they describe the same year), 1 closing post = 7 posts, inside the 6 to 12 target. Nothing was added from outside the article.
2. Thread with character counts
Counts use X rules: the URL counts as 23 characters. All posts are under 280.
1/7 (187 characters, OK) We stopped discounting and replaced it with free shipping over $75 and a loyalty gift at the third order. Six months later, AOV is back to $79 and repeat rate is up from 22 to 31 percent.
2/7 (70 characters, OK) In 2025 we ran 9 promotions. Average order value fell from $84 to $61.
3/7 (98 characters, OK) The promos brought in buyers but did not keep them: 38 percent of promo buyers never bought again.
4/7 (128 characters, OK) So in 2026 we dropped discounts and changed two things: free shipping on orders over $75, and a loyalty gift at the third order.
5/7 (73 characters, OK) Six months in, average order value recovered to $79, up from the $61 low.
6/7 (69 characters, OK) Over the same six months, our repeat rate rose from 22 to 31 percent.
7/7 (220 characters with the URL counted as 23, OK) What we took from it: 9 promos lowered AOV and 38 percent of promo buyers never returned. Free shipping over $75 plus a third-order gift lifted AOV to $79 and repeat rate to 31 percent. Full post: https://goodgrain.test/blog/no-discounts
3. Two alternative openers
Alt A (148 characters, OK) Average order value fell from $84 to $61 after 9 promotions in one year. Here is what we replaced discounts with, and what happened over six months.
Alt B (137 characters, OK) 38 percent of our promo buyers never came back. So we stopped discounting. Six months later, our repeat rate is up from 22 to 31 percent.
Assumption to check: the article says results were measured "over six months" without naming the months, so the thread keeps that wording.
Needs your decision
- Approve the thread, and pick post 1 or an alternative opener, before anything is posted or scheduled. Nothing has been posted.
- Confirm link placement: last post (current) or first reply.
Example output, sample 2
Happy to turn it into a thread of 6 to 12 posts (fewer only if the post is short; I never pad with outside facts). I cannot see which post is your latest from here, so I need:
- The article: paste the full text, or send the URL. If you send a URL and I cannot open it, I will ask you to paste the text, because every fact in the thread has to come from the post itself.
Optional: - Account voice: how your account usually writes (for example, short and dry, or first person founder voice). Without it I will match the tone of the article. - Link placement: link in the last post (my default) or in the first reply?
Which post should I use?
Related
- Tested
Webinar to LinkedIn Posts
Turn a webinar or talk transcript into ten LinkedIn posts, each built on one real idea or quote from the transcript, with hooks and a
- Tested
Responsive Search Ad Copy Builder
Write a full set of responsive search ad headlines and descriptions for one ad group that fit character limits, cover distinct angles and
- Tested
Posting Time Finder
Find the best days and times to post from the account's own post history, computing engagement rate per day and time block with a minimum
No bots match