feat(transcript-fixer): add timestamp repair and section splitting scripts

New scripts:
- fix_transcript_timestamps.py: Repair malformed timestamps (HH:MM:SS format)
- split_transcript_sections.py: Split transcript by keywords and rebase timestamps
- Automated tests for both scripts

Features:
- Timestamp validation and repair (handle missing colons, invalid ranges)
- Section splitting with custom names
- Rebase timestamps to 00:00:00 for each section
- Preserve speaker format and content integrity
- In-place editing with backup

Documentation updates:
- Add usage examples to SKILL.md
- Clarify dictionary iteration workflow (save stable patterns only)
- Update workflow guides with new script references
- Add script parameter documentation

Use cases:
- Fix ASR output with broken timestamps
- Split long meetings into focused sections
- Prepare sections for independent processing

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

transcript-fixer/scripts/tests/test_fix_transcript_timestamps.py

@@ -0,0 +1,54 @@
+#!/usr/bin/env python3
+"""Tests for transcript timestamp normalization and rebasing."""
+
+import sys
+import unittest
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from fix_transcript_timestamps import repair_timestamps
+
+
+class TestFixTranscriptTimestamps(unittest.TestCase):
+    def test_rollover_fix(self):
+        text = (
+            "甲 58:50\n"
+            "内容 A\n"
+            "乙 59:58\n"
+            "内容 B\n"
+            "丙 00:05\n"
+            "内容 C\n"
+        )
+        result = repair_timestamps(
+            text,
+            output_format="hhmmss",
+            rollover_backjump_seconds=15 * 60,
+            jitter_seconds=5,
+            rebase_to_zero=False,
+        )
+        self.assertIn("甲 00:58:50", result.repaired_text)
+        self.assertIn("乙 00:59:58", result.repaired_text)
+        self.assertIn("丙 01:00:05", result.repaired_text)
+        self.assertEqual(len(result.anomalies), 0)
+
+    def test_rebase_to_zero(self):
+        text = (
+            "甲 01:31:10\n"
+            "内容 A\n"
+            "乙 01:31:12\n"
+            "内容 B\n"
+        )
+        result = repair_timestamps(
+            text,
+            output_format="hhmmss",
+            rollover_backjump_seconds=15 * 60,
+            jitter_seconds=5,
+            rebase_to_zero=True,
+        )
+        self.assertIn("甲 00:00:00", result.repaired_text)
+        self.assertIn("乙 00:00:02", result.repaired_text)
+
+
+if __name__ == "__main__":
+    unittest.main()

transcript-fixer/scripts/tests/test_split_transcript_sections.py

@@ -0,0 +1,45 @@
+#!/usr/bin/env python3
+"""Tests for transcript section splitting."""
+
+import sys
+import unittest
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+from split_transcript_sections import (
+    SectionSpec,
+    sanitize_filename_component,
+    split_text_by_markers,
+)
+
+
+class TestSplitTranscriptSections(unittest.TestCase):
+    def test_split_text_by_markers(self):
+        text = (
+            "预热内容\n"
+            "开始安装\n"
+            "装环境内容\n"
+            "我们复盘一下。\n"
+            "复盘内容\n"
+        )
+        parts = split_text_by_markers(
+            text,
+            first_section_name="课前聊天",
+            sections=[
+                SectionSpec(name="正式上课", marker="开始安装"),
+                SectionSpec(name="课后复盘", marker="我们复盘一下。"),
+            ],
+        )
+        self.assertEqual(parts[0][0], "课前聊天")
+        self.assertEqual(parts[1][0], "正式上课")
+        self.assertEqual(parts[2][0], "课后复盘")
+        self.assertTrue(parts[1][1].startswith("开始安装"))
+        self.assertTrue(parts[2][1].startswith("我们复盘一下。"))
+
+    def test_sanitize_filename_component(self):
+        self.assertEqual(sanitize_filename_component("课后/复盘"), "课后-复盘")
+
+
+if __name__ == "__main__":
+    unittest.main()