Repository navigation
Teach plain-writing to write like me - #255
Merged
Merged
Conversation
haacked
marked this pull request as ready for review
October 23, 2026 23:57
…nown - ai/skills/plain-writing/scripts/plain-writing-lint.py: "No X" counts only when X is a noun phrase, so "No idea what…", "No need to…", and "No it is not." aren't flagged - ai/skills/plain-writing/SKILL.md: a source of unknown authorship keeps every fact Claude-Session: https://claude.ai/code/session_014r1UL24kL2ipTAeC3mmxPP
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
When Claude drafts a Slack message, review comment, or PR description for me, it reads like AI wrote it. It's too long, it spells out every mechanism, and it states everything as fact with no room for me being wrong.
plain-writingmade this worse, because it told every pass to keep every fact and the draft's level of detail.Now
plain-writingkeeps every fact only when I wrote the text. When Claude wrote the draft, it keeps what the reader needs to act on and leaves out what they'd ask about if they needed it. Messages to colleagues also loadreferences/voice.md, which has my length targets, how I hedge and ask questions, and samples from my pre-2023 GitHub comments. I only quoted public repos, since this repo is public. The linter now also flags sentences that open with "Nothing" or "No X", which I almost never write (21 of 33,281 sentences in my old comments).Test plan
python3 ai/skills/plain-writing/scripts/tests/test_plain_writing_lint.pyplain-writingand compare them with the samples invoice.mdhttps://claude.ai/code/session_014r1UL24kL2ipTAeC3mmxPP