From 530b4cf6a009970589bdf44a78effc2b9e5ba053 Mon Sep 17 00:00:00 2001
From: Willem Jiang <willem.jiang@gmail.com>
Date: Mon, 31 Aug 2026 23:40:08 +0800
Subject: [PATCH] fix(ci): keep fixing the skill reviewer error (#5122)

* fix(ci):resolve the skill_review errors

* fix(ci): split skill creator fixes from waiver rollout

* fix(skill-creator): address review findings
---
 .../eval-viewer/generate_review.py            | 29 ++-----------------
 .../scripts/aggregate_benchmark.py            |  4 +--
 2 files changed, 4 insertions(+), 29 deletions(-)

diff --git a/skills/public/skill-creator/eval-viewer/generate_review.py b/skills/public/skill-creator/eval-viewer/generate_review.py
index 26e2c193e..f8aad2d49 100644
--- a/skills/public/skill-creator/eval-viewer/generate_review.py
+++ b/skills/public/skill-creator/eval-viewer/generate_review.py
@@ -16,15 +16,11 @@ import argparse
 import base64
 import json
 import mimetypes
-import os
 import re
-import signal
-import subprocess
 import sys
-import time
 import webbrowser
 from functools import partial
-from http.server import HTTPServer, BaseHTTPRequestHandler
+from http.server import BaseHTTPRequestHandler, HTTPServer
 from pathlib import Path
 
 # Files to exclude from output listings
@@ -285,25 +281,6 @@ def generate_html(
 # HTTP server (stdlib only, zero dependencies)
 # ---------------------------------------------------------------------------
 
-def _kill_port(port: int) -> None:
-    """Kill any process listening on the given port."""
-    try:
-        result = subprocess.run(
-            ["lsof", "-ti", f":{port}"],
-            capture_output=True, text=True, timeout=5,
-        )
-        for pid_str in result.stdout.strip().split("\n"):
-            if pid_str.strip():
-                try:
-                    os.kill(int(pid_str.strip()), signal.SIGTERM)
-                except (ProcessLookupError, ValueError):
-                    pass
-        if result.stdout.strip():
-            time.sleep(0.5)
-    except subprocess.TimeoutExpired:
-        pass
-    except FileNotFoundError:
-        print("Note: lsof not found, cannot check if port is in use", file=sys.stderr)
 
 class ReviewHandler(BaseHTTPRequestHandler):
     """Serves the review HTML and handles feedback saves.
@@ -435,14 +412,12 @@ def main() -> None:
         print(f"\n  Static viewer written to: {args.static}\n")
         sys.exit(0)
 
-    # Kill any existing process on the target port
     port = args.port
-    _kill_port(port)
     handler = partial(ReviewHandler, workspace, skill_name, feedback_path, previous, benchmark_path)
     try:
         server = HTTPServer(("127.0.0.1", port), handler)
     except OSError:
-        # Port still in use after kill attempt — find a free one
+        # If the requested port is unavailable, use a free local port.
         server = HTTPServer(("127.0.0.1", 0), handler)
         port = server.server_address[1]
 
diff --git a/skills/public/skill-creator/scripts/aggregate_benchmark.py b/skills/public/skill-creator/scripts/aggregate_benchmark.py
index 7a117bdd7..891644e43 100755
--- a/skills/public/skill-creator/scripts/aggregate_benchmark.py
+++ b/skills/public/skill-creator/scripts/aggregate_benchmark.py
@@ -195,12 +195,12 @@ def aggregate_results(results: dict) -> dict:
 
         pass_rates = [r["pass_rate"] for r in runs]
         times = [r["time_seconds"] for r in runs]
-        tokens = [r.get("tokens", 0) for r in runs]
+        token_counts = [r.get("tokens", 0) for r in runs]
 
         run_summary[config] = {
             "pass_rate": calculate_stats(pass_rates),
             "time_seconds": calculate_stats(times),
-            "tokens": calculate_stats(tokens)
+            "tokens": calculate_stats(token_counts)
         }
 
     # Calculate delta between the first two configs (if two exist)