DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to find a shared skeleton across a series of drafts with Humanizer Stack

Scan several recent pieces so a new draft does not repeat the shape of the last three.

  • Content
  • Intermediate
  • 45 minutes
  • From the README
  • Claude Code

Who it is forA content lead publishing a regular series of posts or lessons who notices every piece opens and closes the same way.

The problemStructural convergence makes a series detectable and flat, and it is hard to see from inside a single draft.

The outcomeA side-by-side view of the structural scan results for recent pieces, with a note on which shape each new draft should take.

What you need first

  • Claude Code installed, since the passes are packaged as Claude Code Skills
  • git and a terminal to clone the repo and run install.sh
  • Python 3 to run the scanners
  • A draft file in plain text or Markdown to work on

Steps

  1. git clone https://github.com/NulightJens/humanizer-stack.git
  2. cd humanizer-stack
  3. python3 skills/structural-humanizer/scripts/structural_scan.py post-1.md (inferred, check the README)
  4. Run the same command on the last three published pieces and compare the results, focusing on audit 6, shape convergence.
  5. In Claude Code, send: run the structural pass on draft.md, then vary one or two interventions from the earlier pieces.

Prompt for your agent

Using the humanizer-stack repo at <repo path>, run structural_scan.py on each file in <series folder> and compare the results for audit 6, shape convergence. Output a short table of the shared patterns and one suggested shape for <new draft file> that differs from them. Verify that the suggestion changes at least one structural choice and does not add a new fixed template.

Caveat. The scanner only flags grep-able structural tells, so judging whether a whole series shares one skeleton still needs a human reader.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page