docs(skill): add no-editorializing rule for written output#83
Conversation
Dependency Review✅ No vulnerabilities or license issues or OpenSSF Scorecard issues found.Scanned FilesNone |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces a new rule and reference document, "No editorializing," which guides contributors to write without self-praise, reassurance, or narrating expected baseline results across all written artifacts. It also streamlines several descriptions and headings in the main Git Workflow skill document. The review feedback suggests changing the top-level heading of the new reference file from a level 2 to a level 1 heading for consistency with other reference files.
Important
The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.
There was a problem hiding this comment.
Pull request overview
This PR updates the git-workflow skill’s writing guidance by adding an explicit “no editorializing” rule and a dedicated reference document, aiming to keep written artifacts factual (what changed) rather than persuasive (how good/careful it is).
Changes:
- Add Critical Rule 8 (“No editorializing”) to the skill’s non-negotiable rules and link to the new reference.
- Introduce
references/no-editorializing.mddescribing tone-based tests and common failure modes (expected-results narration, self-praise/reassurance). - Tighten several reference-table trigger descriptions in
SKILL.mdto keep the document concise.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| skills/git-workflow/SKILL.md | Adds Critical Rule 8 and updates the reference table to include the new guidance while keeping the doc concise. |
| skills/git-workflow/references/no-editorializing.md | New reference defining “no editorializing” with practical tests and examples across commits/PRs/reviews/docs. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
CybotTM
force-pushed
the
feat/no-editorializing-rule
branch
from
8c48786 to
d7f2add
Compare
State what changed, not how good it is: no self-praise, no narrating expected results. Adds a Critical Rule entry and a references/no-editorializing.md. Signed-off-by: Sebastian Mendel <info@sebastianmendel.de>
Address review: standalone reference doc starts with H1; contra- -> counter-reaction. Signed-off-by: Sebastian Mendel <info@sebastianmendel.de>
|
Adds a `## No editorializing` note and `references/no-editorializing.md`: write what a change does, not how good or careful the work is — no narrating expected results or self-praise. Judged by tone (deletion / subject / voice tests), not a wordlist. SKILL.md kept under the 500-word limit by tightening a few triggers/prose. Mirrors netresearch/git-workflow-skill#83.
Adds a `## No editorializing` section and `references/no-editorializing.md`: in messages and announcements, state what happened, not how good or careful the work is — no narrating expected results or self-praise. Judged by tone (deletion / subject / voice tests), not a wordlist. Mirrors netresearch/git-workflow-skill#83.
Adds a `## No editorializing` note and `references/no-editorializing.md`: in tickets, comments and worklog notes, state what happened, not how good the work is — no self-praise or narrating expected results. Judged by tone (deletion / subject / voice tests), not a wordlist. SKILL.md kept under the 500-word limit. Mirrors netresearch/git-workflow-skill#83.
Adds a process step and `references/no-editorializing.md`: say what changed, not how good or careful the work is — no self-praise or narrating expected results. Applies to German MR/ticket text too. Judged by tone (deletion / subject / voice tests), not a wordlist. SKILL.md kept at the 500-word limit. Mirrors netresearch/git-workflow-skill#83.
Adds a `## No editorializing` section and `references/no-editorializing.md`: in branded reports, PR/commit text and docs, state what a change does, not how good or careful the work is — no narrating expected results or self-praise. Judged by tone (deletion / subject / voice tests), not a wordlist. Mirrors netresearch/git-workflow-skill#83.
Adds Critical Rule 8 and
references/no-editorializing.md: write what a change does, not how good or careful the work is. Covers commits, PR/MR text, reviews, comments, docs, README, changelog.Two failure modes it names: narrating expected results (passing tests, clean lint, "no regressions") and self-praise/reassurance ("clean", "the honest breaking change", "deliberately scoped, not hidden"). Judged by tone via three tests (deletion / subject / voice), not a wordlist.
SKILL.md kept at the 500-word limit by tightening a few reference-table descriptions.