Conversation
Add a "no em dashes, be concise, plain language" standard that applies to published documentation and to comments Claude posts to people (GitHub, Jira, Asana, Slack). Repo infrastructure stays out of scope. - docs/contributing/style-guide.md: new "Concise, human phrasing" and "Dashes" subsections. - .claude/skills/sumo-style/SKILL.md: mirror the concision rule. - AGENTS.md: new "Output tone" section so the rules reach connector comments, where the sumo-style skill does not load. Covers DOCS-988 action item 2 (team guidelines). Action item 1 (humanizer vs sumo-style evaluation) captured in a ticket comment. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
This was referenced Sep 3, 2026
kimsauce
changed the title
Scope the tone rules to the prose Claude posts for people to read in GitHub PR comments, GitHub issue comments, and Jira ticket comments. A comment should read as though a person wrote it. Removes the additions to docs/contributing/style-guide.md and to the sumo-style skill. Both applied the rules to published documentation, which reaches past the intended scope. Drops the em dash exception for a tooling-appended attribution marker, since no marker is appended to a comment now, and drops Asana and Slack from the surface list. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Vendors blader/humanizer v3.0.0 (MIT) at .claude/skills/humanizer/SKILL.md, copied verbatim so future version bumps are a clean overwrite. It rewrites the patterns that mark prose as machine-written, working from 25 numbered tells drawn from Wikipedia's "Signs of AI writing", and leaves code, paths, and link targets untouched. AGENTS.md now requires running it on the draft of every GitHub PR comment, GitHub issue comment, and Jira ticket comment, in the skill's embedded mode so only the final text comes back. Stated as a standing requirement rather than a step someone has to ask for. The three tone rules stay, since a skill invocation is model-initiated and therefore probabilistic. They hold whether or not the skill runs. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
…skill SKILL.md was copied in with only "license: MIT" in its frontmatter: no copyright line, no permission notice, and no pointer upstream. This repo is public and MIT licensed in its own right, so redistributing a third-party MIT file without its notice does not meet the license terms, and nothing in the directory told a maintainer the file was third-party at all. Adds a README recording the upstream URL, version 3.0.0, the commit it was copied from, and the file's sha256, plus the upstream copyright and permission notice verbatim. Also states the update rule: overwrite from upstream, never edit locally, so an update stays a clean overwrite. Copyright (c) 2025 Siqi Chen, per https://github.com/blader/humanizer. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Y1ruDS5yvfoJf9dC1Bst5q
kimsauce
changed the title
kimsauce
marked this pull request as ready for review
September 9, 2026 08:56
kimsauce
changed the title
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
1 participant
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.
Purpose of this pull request
A comment Claude Code posts should read as though a person wrote it. This makes that a requirement for GitHub PR comments, GitHub issue comments, and Jira ticket comments.
.claude/skills/humanizer/SKILL.mdvendors blader/humanizer v3.0.0 (MIT), copied verbatim so version bumps stay a clean overwrite. It rewrites the patterns that mark prose as machine-written, working from 25 numbered tells drawn from Wikipedia's "Signs of AI writing", and leaves code, commands, paths, and link targets untouched.AGENTS.mdgains an Output tone section requiring the skill on the draft of every comment, in its embedded mode so only the final text comes back. It also states three rules that hold whether or not the skill runs: no em dashes, be concise, plain language. On a PR, one more rule applies: put each point in an inline comment on the line it concerns, and keep a top-level summary comment only for feedback not tied to a specific line.The rules sit alongside the skill rather than inside it because a skill invocation is model-initiated, and so probabilistic. If the skill does not fire, the rules still apply.
Pairs with DOCS-1867 (#7099), which removes the attribution marker Claude appends to comments. Between them: the marker that labels a comment as automated, and the style that betrays it anyway.
Select the type of change
Ticket (if applicable)
https://sumologic.atlassian.net/browse/DOCS-988
🤖 Generated with Claude Code