From a5758735099b5ea8b2f27ffbd2276d08140b5061 Mon Sep 17 00:00:00 2001 From: tend-agent <270458913+tend-agent@users.noreply.github.com> Date: Sun, 9 Aug 2026 13:15:56 +0000 Subject: [PATCH 1/2] fix(review): don't cite a repo review policy that isn't written down --- plugins/tend-ci-runner/skills/review/SKILL.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/plugins/tend-ci-runner/skills/review/SKILL.md b/plugins/tend-ci-runner/skills/review/SKILL.md index 6375bb16..d95bc1b4 100644 --- a/plugins/tend-ci-runner/skills/review/SKILL.md +++ b/plugins/tend-ci-runner/skills/review/SKILL.md @@ -208,6 +208,8 @@ Don't explain what the code does — the author wrote it. Don't nitpick formatti **When confidence is low**, go beyond checking the implementation — question the approach: "Does this bypass or duplicate an existing API?" "What does this change *not* handle?" If the design involves a judgment call, flag it for human review as a COMMENT. +**Attribute a withheld approval to whatever actually decided it.** Cite repo guidance only when you can name the file and heading it lives in; a reader who goes looking for "this repo's review policy" and finds nothing written starts doubting the rest of the review too. When the call is your own judgment, say so plainly — "I'd want a human on this one, it changes what `--force` will delete" rather than "per this repo's review policy this is a hold-for-human surface". Judgment is a sufficient reason on its own; borrowed authority that doesn't exist is not. + **Self-authored PRs** (`PR_AUTHOR == BOT_LOGIN` — compare the literal bot login string, not "authored by someone senior" or "by the repo owner"): Still perform the full review (steps 2-3) — self-review catches real issues (lint failures, edge cases) and is intentionally valuable. Do NOT attempt `gh pr review --approve` — GitHub rejects self-approvals. Submit as COMMENT when there are concerns, or stay silent and skip to step 6. Always post CI failure analysis as a COMMENT, even on self-authored PRs. **Not confident enough to approve** (unfamiliar module, subtle logic): Add a `+1` reaction instead — no review needed unless there are specific observations. From a7f51a5340567ae469c3d26b40f7b810c43b9345 Mon Sep 17 00:00:00 2001 From: tend-agent <270458913+tend-agent@users.noreply.github.com> Date: Sun, 9 Aug 2026 13:23:43 +0000 Subject: [PATCH 2/2] fix(review): scope the citation rule to the withheld approval --- plugins/tend-ci-runner/skills/review/SKILL.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/plugins/tend-ci-runner/skills/review/SKILL.md b/plugins/tend-ci-runner/skills/review/SKILL.md index d95bc1b4..8b0648c6 100644 --- a/plugins/tend-ci-runner/skills/review/SKILL.md +++ b/plugins/tend-ci-runner/skills/review/SKILL.md @@ -208,7 +208,7 @@ Don't explain what the code does — the author wrote it. Don't nitpick formatti **When confidence is low**, go beyond checking the implementation — question the approach: "Does this bypass or duplicate an existing API?" "What does this change *not* handle?" If the design involves a judgment call, flag it for human review as a COMMENT. -**Attribute a withheld approval to whatever actually decided it.** Cite repo guidance only when you can name the file and heading it lives in; a reader who goes looking for "this repo's review policy" and finds nothing written starts doubting the rest of the review too. When the call is your own judgment, say so plainly — "I'd want a human on this one, it changes what `--force` will delete" rather than "per this repo's review policy this is a hold-for-human surface". Judgment is a sufficient reason on its own; borrowed authority that doesn't exist is not. +**Attribute a withheld approval to whatever actually decided it.** Cite repo guidance as the reason only when you can name the file and heading that guidance lives in; a reader who goes looking for "this repo's review policy" and finds nothing written starts doubting the rest of the review too. When the call is your own judgment, say so plainly — "I'd want a human on this one, it changes what `--force` will delete" rather than "per this repo's review policy this is a hold-for-human surface". Judgment is a sufficient reason on its own; borrowed authority that doesn't exist is not. **Self-authored PRs** (`PR_AUTHOR == BOT_LOGIN` — compare the literal bot login string, not "authored by someone senior" or "by the repo owner"): Still perform the full review (steps 2-3) — self-review catches real issues (lint failures, edge cases) and is intentionally valuable. Do NOT attempt `gh pr review --approve` — GitHub rejects self-approvals. Submit as COMMENT when there are concerns, or stay silent and skip to step 6. Always post CI failure analysis as a COMMENT, even on self-authored PRs.