Show HN: 1pager: Fixing the AI verbosity problem

A skill that condenses any long document, directory, or chat into a strict one-page summary — bullet-first, least verbosity possible — humanizes it, and exports a .md

plus a .docx

(opens in Word and Google Docs).

LLMs are verbose by default. Left unedited, their output is long, padded, and full of tells (rule-of-three, "delve", em-dash sprees, generic upbeat closers).

The cost lands on the reader. As Camille Fournier argues in Guidelines for respectful use of AI, shipping unreviewed, bloated AI output creates a validation tax: colleagues have to read and verify text the author never bothered to trim. Long PRs, wall- of-text messages, and bloated docs are, in her words, "frankly, just rude." Brevity is a form of respect — shorter is better because it protects the reader's time.

This skill exists to do the trimming the author should have done: cut the output down to only what the reader needs to understand or decide, on a single page.

Strips to essentials— keeps the point, the decision/ask, the few supporting facts, real risks, and concrete next steps. Drops everything else.Drafts a strict 1-pager— bottom line first, then bullets. One page, hard ceiling (~350 words).** Humanizes**— removes AI-writing tells. Invokes the installedhumanizer

skill if present; otherwise falls back to the bundledreferences/humanizer.md

.Exports two files—<name>-1pager.md

and<name>-1pager.docx

.

1pager/
├── SKILL.md                     # the skill: condense → humanize → export
├── README.md                    # this file
├── scripts/
│   └── md_to_docx.py            # pure-stdlib Markdown → .docx (no dependencies)
└── references/
    └── humanizer.md             # bundled humanizer rules (fallback)

In Claude Code, the skill triggers when you ask to condense, shorten, or make a 1-pager out of something:

"Condense this design doc into a one-pager." "This thread is way too long — give me a tl;dr I can share." "Boil the docs/ folder down to a single page."

Point it at a directory and it combines the relevant files into one page by default (one page per file if you ask for that instead).

You can also run the converter directly:

python3 scripts/md_to_docx.py my-1pager.md my-1pager.docx

md_to_docx.py

supports the small Markdown subset a 1-pager needs: #

–####

headings, -

/*

bullets (two-space indent = sub-bullet), **bold**

, and code

(rendered monospace). It has no external dependencies — a .docx

is just a zip of XML, built with the Python standard library.