sno-ai/sno-station-skills / skills/J-peer-review-and-audit/peer-review/skill
peer-review
VerifiedAdversarial review and fix loop for code, specs, plans, and migration manifests.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 32.7 KB |
| agents/openai.yaml | config | 216 B |
| assets/adversarial-plan-review.prompt.md | markdown | 11.0 KB |
| assets/adversarial-review.prompt.md | markdown | 12.0 KB |
| assets/adversarial-test-review.prompt.md | markdown | 3.5 KB |
| references/code-layers.md | markdown | 5.4 KB |
| references/doc-layers.md | markdown | 5.5 KB |
| references/python-advanced-patterns.md | markdown | 7.8 KB |
| references/python-standards.md | markdown | 8.3 KB |
| references/ts-standards.md | markdown | 7.1 KB |
| scripts/lib/sno-model.sh | script | 1.5 KB |
| scripts/review-backfill.shexecutable | script | 4.7 KB |
| scripts/review-findings.shexecutable | script | 11.7 KB |
| scripts/review-receipt.shexecutable | script | 5.3 KB |
| scripts/run-adversarial-review.shexecutable | script | 57.6 KB |
| scripts/selftest/cursor-process-group.t | other | 2.0 KB |
| scripts/selftest/run-cross-vendor.sh | script | 14.5 KB |
| scripts/selftest/run-model-settings.shexecutable | script | 5.1 KB |
| scripts/selftest/run-selftest.shexecutable | script | 39.2 KB |
scripts/selftest/cursor-process-group.t
View on GitHub#!/usr/bin/env bash
# The isolated reviewer works without setsid and retires its helper process.
set -Eeuo pipefail
here="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
root="$(mktemp -d)"
trap '[[ ! -f "$root/helper.pid" ]] || kill "$(cat "$root/helper.pid")" 2>/dev/null || true; rm -rf -- "$root"' EXIT
mkdir -p "$root/bin" "$root/tmp" "$root/home/.config/cursor" "$root/home/.local/share"
printf '{}\n' > "$root/home/.config/cursor/auth.json"
printf 'export const value = 1;\n' > "$root/target.ts"
cat > "$root/bin/setsid" <<'STUB'
#!/usr/bin/env bash
printf 'setsid: command not found\n' >&2
exit 127
STUB
cat > "$root/bin/cursor-agent" <<'STUB'
#!/usr/bin/env bash
cat >/dev/null
sleep 60 &
printf '%s\n' "$!" > "$HELPER_PID_FILE"
printf '{"is_error":false,"result":"Verdict: approve\\nCursor process group checked"}\n'
STUB
cat > "$root/bin/sno" <<'STUB'
#!/usr/bin/env bash
if [[ "${1:-}" == subscription-quota-check ]]; then
printf '%s\n' '{"ok":true,"from":{"vendor":"anthropic"},"candidates":[{"agent":"cursor","provider":"openai","vendor":"openai"}]}'
fi
exit 0
STUB
chmod +x "$root/bin/setsid" "$root/bin/cursor-agent" "$root/bin/sno"
status=0
env PATH="$root/bin:$PATH" HOME="$root/home" TMPDIR="$root/tmp" \
REVIEW_CALLER=claude-code REVIEW_REVIEWER=cursor MAX_RETRIES=0 POLL_SECS=1 \
TIMEOUT_SECS=10 STALL_SECS=10 HELPER_PID_FILE="$root/helper.pid" \
STATS_FILE="$root/stats.jsonl" FINDINGS_FILE="$root/findings.jsonl" \
REVIEW_OUTPUT_FILE="$root/report.md" XDG_CONFIG_HOME="$root/home/.config" \
timeout 15 bash "$here/../run-adversarial-review.sh" "$root/target.ts" \
> "$root/out" 2> "$root/err" || status=$?
[[ "$status" == 0 ]] || { cat "$root/err" >&2; printf 'FAIL reviewer exit: %s\n' "$status" >&2; exit 1; }
grep -Fxq 'Cursor process group checked' "$root/report.md"
[[ -f "$root/helper.pid" ]]
pid="$(cat "$root/helper.pid")"
state="$(ps -o stat= -p "$pid" 2>/dev/null || true)"
[[ -z "$state" || "$state" == *Z* ]] || { printf 'FAIL helper remains running\n' >&2; exit 1; }
printf 'PASS isolated Cursor review and helper cleanup\n'
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |