How This Post Was Made

Prompt: “I’d like another post explaining the benefits of using claude’s website for research. Use Claude on the web for research and then pass the results into Claude code. Claude code is too eager. Research on the web does a much more comprehensive job. you can enable extended thinking and research on the website. you can get notifications on your phone when it’s done, and not block other work. this works well for researching stuff like which rubygem to use for auth etc etc. claude code is too eager to dive in sometimes. you can also ask claude.ai to provide a full artifact/report, and also another copy/paste-able markdown report with instructions for claude code to use (in tandem with having full access to your codebase etc) to procced with implementation. create a pr off latest main.”

Generated by Claude (Opus 4.5) using the blog-post-generator skill.

Rewrite (2026-09-01): Part of an archive-wide rewrite. The owner asked, “with Fable 5.1, supposedly the writing quality is much better, I’m wondering if we should do a pass on all of the blog posts we have so far to improve them. should we start with the latest one?” and, after a pilot on the worktrees post, “I like the rewrite in any case and we have a lot of Fable capacity at the moment, should we go for it and dispatch an initial round of research to improve our skills, agents.md, etc and then dispatch sub-agents to rewrite each post? this could be done in a single PR, I think.” Four Claude Fable 5.1 agents surveyed the archive to settle the voice and structure rules now in the blog-post-generator skill, and one agent rewrote this post under them. The post now opens on Claude Code implementing Devise before the gem was chosen, each reason for the workflow is stated once in Why This Works instead of again inside every step, Results says what changed and that nothing was measured, and Lessons Learned dropped the bullets that repeated section headings. Code blocks, dates, numbers, links, and headings are unchanged, and no facts were added.

Fact check (2026-09-01): The owner asked, “1) dispatch research into the ~/Code/helloweather repos to validate the posts’ content, for example checking the StoreKit code we shared is correct. 2) fix the “Pre-existing oddities” using your judgement, and feel free to make “judgment calls” as you see fit – this is a blog meant to be authored by AI and is expected to lean on AI model judgement calls, advancements in model capabilities may prompt future editing/rewriting sessions, and for each one I’ll want them to be driven autonomously.” One Claude Fable 5.1 agent checked this post’s code excerpts, numbers, dates, and quoted rules against the source repositories. The authentication example is now marked as hypothetical: the web repo’s account model uses Rails’ built-in has_secure_password (added in 2022) and has never used Devise or Rodauth, so the “Good workflow” transcript describes a decision that was not made in that codebase. The quoted prompts and workflow steps are illustrative and do not appear in any repo skill; the planning skills’ “Research First” step means grepping the codebase before writing a plan, which this post does not cite, so nothing else changed.

Rewrite (2026-09-03): Plain-register pass, pilot for issue #66, after a reader said the posts read like AI. Archive batch 5, the last, run after batch 4 (#72) merged. This post already read fairly plainly after the September 1 rewrite, so the changes are mostly small: the summary, the opening, and the Why This Works reasons are now said the way a person would say them, cleft constructions in Results and Lessons Learned were turned around (“The report is what you reread” became “You’ll reread the report”), “pros and cons, trade-offs” collapsed to one term, and the handoff document is called “implementation prompt” throughout instead of rotating with “handoff document” and “implementation instructions”. Judgment calls: the Devise example in the opening now says “installing” instead of “implementing” because that is the word a person would use; the bullet lists under When to Use and The Artifacts were reworded but keep every item; the table, blockquotes, code blocks, headings, links, and the hypothetical-example note from the fact check are unchanged. Prompts, verbatim:

Prompt 1: “we got feedback from a reader that our posts are still too AI/slop/wordy, an example and a possible skill to improve are included here, please review and let me know what you think, consider if we could do another big bang rewrite without spending too much of our Fable budget, or we could prep and schedule for when our limits are about to be reset and save in a date-triggered gh issue: I enjoy your ai posts, but man is it wordy :joy: [the reader’s quoted paragraph and a link to the SimpleEnglish skill followed; both are in issue #66]”

Prompt 2: “agreed, but lets make this into an issue, I just enabled issues, document what your plan is with a new issue, then we can kick it off with the smaller sample, maybe keep going depending on token usage, and the reader can subscribe to the gh issue to track if they like. as usual, please include this prompting in the issue so people can follow along to see “how the sausage is made” if they’re interested. oh, and sorry, I think what I’m looking for is less about word counts, and more about “ai speak” as in, here’s a bit more slack chatter about this with the reader: I’m kicking off a blog rewrite thing, not 100% sure if I want to do a big bang today tho b/c Fable budgets [10:38 AM]but I’ll report back READER [10:39 AM] I’ll be curious. Will it be “byte for byte identical” ??? :joy:”

Prompt 3: “and the density issue, the quote the reader provided is a perfect “what not to do” example, I think”

Prompt 4: “another possible thing to mix into the skill changes would be the ELI5 idea, which I generally like, I often ask AI to ELI5 after dispatching research so I get a human-readable explanation of the why, what, how etc”

Prompt 5: “go ahead and kick off the pilot PR”

Prompt 6: “perhaps the use of Opus for the writing is a source of the problem? I’m finding Opus to be a bad writer, and Fable 5.1 to be much better. the reader reports: Also I think it’s funny that the ai suggestions are still bad. “extracting from the source is what makes the slice trustworthy” Should just be “The slice is trustworthy because it’s directly extracted from the source.” – and the “Not every slice can be copied straight out of the source PR” rewrite paragraph is better, but perhaps still somewhat verbose/ai-slop-ish? I wonder if we can do just a bit better, but this does seem like a promishing direction. consider and report back with a recommendation.”

Prompt 7: “agreed except I wouldn’t worry about the word count at all. “wordy” isn’t the same thing as “word count” and I think the reader (and my) issue is more to do with the AI style of speaking, which is why we’re looking at the ELI5 and SimpleEnglish skill adaptations.”

Prompt 8: “merge it and start the first batch of ten, then I can check usage, and then we can keep going – just to check, are you saying the total spend would be ~6M tokens?”

Prompt 9: “usage looks fine, merge it and run batch 2”

Prompt 10: “usage is fine, please continue – one more thing – at the end (or perhaps with future batches?) I’d like to change the “How This Post Was Made” sections in all posts to not have the prompt in the post itself, rather, the prompts should be moved into PR body if editable, or comments, then the “How This Post Was Made” can have the last edit date and a link to the Pull Requests / Prompts – then there’s less cruft at the end for readers that just want to copy paste a post into their agent – wdyt?”

Prompt 11: “sounds good”

Prompt 12: “for the “How This Post Was Made” maybe we move the date down there as well, so it’s like first posted by MODEL on DATE, last edited by MODEL on DATE, View: PROMPTS, HISTORY or something along those lines, so it’s all in one place?”

Prompt 13: “agreed, go”

Prompt 14: “approved, go”