Add concise code review skill - #4471
Open
KSchlobohm wants to merge 3 commits into
Open
Conversation
Add repository-specific guidance for positive and negative tests, regression evidence, and terminology alignment while exempting community-authored catalog content. Assisted-by: GitHub Copilot (model: gpt-5.6-luna, autonomous) Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 60c0e36f-daf2-4c62-87ee-4da8fb1eaf12
Contributor
There was a problem hiding this comment.
Copilot review overview
🔵 Needs a closer look
The community-content terminology exceptions are incomplete.
Review tier: Balanced
Findings: None
What changed in this PR
Adds concise code-review guidance for testing, regression evidence, and terminology consistency.
Changes:
- Defines activation metadata and review expectations.
- Adds exceptions for community-authored catalog content.
| File | Description |
|---|---|
.github/skills/code-review/SKILL.md |
Adds the skill definition. Terminology exceptions should also cover integration catalogs and generated community documentation. |
Suppressed comments (2)
.github/skills/code-review/SKILL.md:11
- The exception omits
integrations/catalog.community.json, even though integrations are also externally contributed community content (integrations/CONTRIBUTING.md:40-42). As written, reviews would apply the terminology rule to community integration entries while exempting every other community catalog type. Include integrations in this list.
3. Ensure wording changes use terms consistently with the repository so they do not confuse or dilute meaning; this does not apply to community-authored content in Spec Kit's community catalog JSON files for bundles, extensions, presets, or workflows.
.github/skills/code-review/SKILL.md:11
- This exception misses the generated community documentation. The bundle, extension, and preset submission workflows copy the submitter-provided description into
docs/community/*.md(for example,.github/workflows/add-community-extension.md:209-220), so the skill would exempt the catalog value but still require repository terminology in its mirrored table row. Extend the exception to community-authored catalog content wherever it is rendered.
3. Ensure wording changes use terms consistently with the repository so they do not confuse or dilute meaning; this does not apply to community-authored content in Spec Kit's community catalog JSON files for bundles, extensions, presets, or workflows.
💡 Configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
Exclude community-authored catalog content and generated documentation from terminology alignment reviews. Assisted-by: GitHub Copilot (model: gpt-5.6-luna, autonomous) Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 60c0e36f-daf2-4c62-87ee-4da8fb1eaf12
Contributor
There was a problem hiding this comment.
Copilot review overview
🟡 Changes recommended
The testing requirement should be scoped to avoid false-positive review findings.
Once you've addressed the issues Copilot identified, you can request another Copilot review.
Review tier: Balanced
Findings: 1
New issues introduced by this change (1)
| Severity | Finding |
|---|---|
 |
.github/skills/code-review/SKILL.md — The blanket requirement for both positive and negative tests will create false-positive review… |
Require test cases to verify intended behavior and what each code change should prevent. Assisted-by: GitHub Copilot (model: gpt-5.6-luna, autonomous) Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: 60c0e36f-daf2-4c62-87ee-4da8fb1eaf12
Contributor
There was a problem hiding this comment.
Copilot review overview
🟢 Approval recommended
The documentation-only change was fully reviewed with no unresolved issues.
Review tier: Balanced
Findings: None
Issues resolved since last review (1)
| Severity | Finding |
|---|---|
|
.github/skills/code-review/SKILL.md — The blanket requirement for both positive and negative tests will create false-positive review… View resolved comment |
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.
Description
This pull request adds a new skill definition for code review guidelines. The new documentation outlines expectations for reviewing code changes, including test coverage, regression evidence, and terminology consistency.
Testing
Validated the skill through activation-alignment review, the skill-authoring checklist, a three-model reviewer matrix, and
git diff --check. No CLI, runtime, template, or packaging behavior changed, so the standard CLI, test-suite, and sample-project checks were not applicable.AI Disclosure
Assisted-by: GitHub Copilot (model: gpt-5.6-luna) as an orchestrator with other models consulted for feedback (model: gpt-5.6-sol, claude-opus-5, gemini-3.7-flash, autonomous)