Update code review skill guidelines for suggestions formatting

[MichalPetryka]

Copilot keeps making misformatted suggestions, I think this could help maybe?

[azure-pipelines]

Azure Pipelines:
Successfully started running 1 pipeline(s).
15 pipeline(s) were filtered out due to trigger conditions.
There may be pipelines that require an authorized user to comment /azp run to run.

[github-actions]

Workflow state for the Holistic Review Orchestrator.

{
  "version": 5,
  "last_dispatched_commit": "38160c47026cba6b2289ae35e4c1ec5b83975d3d",
  "last_dispatched_base_ref": "main",
  "last_dispatched_base_sha": "c536338d89a6ccc0bcbca46e44e3343d990e06aa",
  "last_reviewed_commit": "38160c47026cba6b2289ae35e4c1ec5b83975d3d",
  "last_reviewed_base_ref": "main",
  "last_reviewed_base_sha": "c536338d89a6ccc0bcbca46e44e3343d990e06aa",
  "last_recorded_worker_run_id": "29694238737",
  "review_attempt_commit": "",
  "review_attempt_base_ref": "",
  "review_attempt_count": 0,
  "max_review_attempts": 5,
  "review_history_format": "holistic-review-disclosure-v1",
  "review_history": [
    {
      "commit": "4811c2dc58990183bd849a7458cae7453f3a3332",
      "review_id": 4730929834
    },
    {
      "commit": "38160c47026cba6b2289ae35e4c1ec5b83975d3d",
      "review_id": 4731078458
    }
  ]
}

[github-actions]

Holistic Review

Motivation: The author observes that Copilot code review frequently produces misformatted suggestion blocks, and wants the code-review skill to explicitly instruct the reviewer to match the surrounding code's formatting and style. This is a reasonable, low-risk documentation improvement to the agent guidelines.

Approach: The change adds a new numbered guideline (item 10) to .github/skills/code-review/SKILL.md telling the reviewer that suggested code must match the surrounding code's formatting and style, and renumbers the former item 10 ("Label in-scope vs. follow-up") to item 11. The renumbering is correct and the list remains sequential. Because this file is a trusted-overlay agent-configuration path, the reviewed content was read from the PR head commit rather than the local worktree.

Summary: The intent is sound and the scope is minimal (a single markdown list item plus a renumber). The only issue is that the new sentence is grammatically broken ("Any code you suggest must be intended matching the surrounding code"), which is somewhat ironic for a guideline about producing polished output. Fixing the wording would make the instruction clearer and more effective. No functional or correctness concerns. Verdict: approve with a minor wording fix suggested inline.

Detailed Findings

One minor, non-blocking finding was filed inline on line 90: the new guideline text is grammatically malformed and should be reworded for clarity (see the inline suggestion).

Note

This review was generated by this repository's Holistic Review agentic workflow to complement the built-in Copilot review.

Generated by Holistic Review · 41.1 AIC · ⌖ 10.4 AIC · ⊞ 10K

[github-actions]

Holistic Review

Motivation: The author observes that Copilot code review frequently produces misformatted suggestion blocks, and wants the code-review skill to explicitly instruct the reviewer to match the surrounding code's formatting and style. This is a reasonable, low-risk documentation improvement to the agent guidelines.

Approach: The PR adds a new numbered guideline (item 10) to .github/skills/code-review/SKILL.md telling the reviewer that suggested code must match the surrounding code's indentation, formatting, and style, and renumbers the former item 10 ("Label in-scope vs. follow-up") to item 11. The new incremental commit corrects the wording of that guideline from the grammatically broken "must be intended matching the surrounding code" to "must be indented matching the surrounding code." Because this file is a trusted-overlay agent-configuration path, the reviewed content was read from the PR head commit rather than the local worktree.

Summary: The single incremental change since the prior review is a one-word wording fix that directly resolves the grammar issue flagged inline in that review. The guideline now reads clearly, the list numbering remains correct and sequential, and the scope remains minimal (a single markdown list item plus a renumber). No functional, correctness, or security concerns. Verdict: approve.

Assessment History

• review 4730929834 reviewed commit 4811c2d with an approve-with-minor-wording-fix verdict. The current verdict is approve. The assessment is essentially unchanged in motivation, approach, and risk; the only difference is that the minor inline wording finding from that review has now been addressed by the incremental commit (38160c4), so no findings remain.

Detailed Findings

No actionable findings. The incremental change ("intended" -> "indented matching") resolves the sole minor wording issue raised in the prior review.

Note

This review was generated by this repository's Holistic Review agentic workflow to complement the built-in Copilot review.

Generated by Holistic Review · 40.1 AIC · ⌖ 14.4 AIC · ⊞ 10K