diff --git a/.amazonq/rules/triage-findings.md b/.amazonq/rules/triage-findings.md
deleted file mode 100644
index f6468cd..0000000
--- a/.amazonq/rules/triage-findings.md
+++ /dev/null
@@ -1,14 +0,0 @@
-# Triage Findings
-
-When the task is to triage review findings, follow this workflow:
-
-1. Merge all findings into one list.
-2. Remove duplicates.
-3. Sort by severity: `critical` -> `warning` -> `info`.
-4. Renumber from 1 after sorting.
-5. Fix real issues with the smallest safe change.
-6. Add false positives to `.gitea/ai-review/exclusions.json`.
-7. Add or update tests when behavior changes.
-8. Re-check the issue after each fix.
-
-Use the repo-local `triage-findings` skill for the same workflow when running in Codex.
diff --git a/.claude/skills/triage-findings/SKILL.md b/.claude/skills/triage-findings/SKILL.md
deleted file mode 100644
index ac823cf..0000000
--- a/.claude/skills/triage-findings/SKILL.md
+++ /dev/null
@@ -1,28 +0,0 @@
----
-name: triage-findings
-description: Triage findings, fix real issues, and exclude false positives.
----
-
-# Triage Findings
-
-## Use
-
-直接輸入：`triage-findings 問題原始檔(文字或截圖)`
-
-## Workflow
-
-1. Merge all findings.
-2. Sort by severity:
-   - critical
-   - warning
-   - info
-3. Renumber from 1.
-4. Fix real issues.
-5. Put false positives into `.gitea/ai-review/exclusions.json`.
-6. Add tests when behavior changes.
-
-## Output Rules
-
-- Keep the final list short.
-- Keep numbering contiguous.
-- Preserve file path, location, and fix.
diff --git a/.gemini/skills/triage-findings/SKILL.md b/.gemini/skills/triage-findings/SKILL.md
deleted file mode 100644
index ac823cf..0000000
--- a/.gemini/skills/triage-findings/SKILL.md
+++ /dev/null
@@ -1,28 +0,0 @@
----
-name: triage-findings
-description: Triage findings, fix real issues, and exclude false positives.
----
-
-# Triage Findings
-
-## Use
-
-直接輸入：`triage-findings 問題原始檔(文字或截圖)`
-
-## Workflow
-
-1. Merge all findings.
-2. Sort by severity:
-   - critical
-   - warning
-   - info
-3. Renumber from 1.
-4. Fix real issues.
-5. Put false positives into `.gitea/ai-review/exclusions.json`.
-6. Add tests when behavior changes.
-
-## Output Rules
-
-- Keep the final list short.
-- Keep numbering contiguous.
-- Preserve file path, location, and fix.
diff --git a/.github/copilot-instructions.md b/.github/copilot-instructions.md
deleted file mode 100644
index 92710d5..0000000
--- a/.github/copilot-instructions.md
+++ /dev/null
@@ -1,16 +0,0 @@
-# Triage Findings
-
-When the task is to triage review findings, follow this workflow:
-
-1. Merge all findings into one list.
-2. Remove duplicates.
-3. Sort by severity: `critical` -> `warning` -> `info`.
-4. Renumber from 1 after sorting.
-5. Fix real issues with the smallest safe change.
-6. Add false positives to `.gitea/ai-review/exclusions.json`.
-7. Add or update tests when behavior changes.
-8. Re-check the issue after each fix.
-
-Use the repo-local `triage-findings` skill for the same workflow when running in Codex.
-
-Trigger it with `/triage-findings`.
diff --git a/.github/skills/triage-findings/SKILL.md b/.github/skills/triage-findings/SKILL.md
deleted file mode 100644
index 01e14d5..0000000
--- a/.github/skills/triage-findings/SKILL.md
+++ /dev/null
@@ -1,28 +0,0 @@
----
-name: triage-findings
-description: Triage findings, fix real issues, and exclude false positives.
----
-
-# Triage Findings
-
-## Use
-
-`triage-findings 問題原始檔(文字或截圖)`
-
-## Workflow
-
-1. Merge all findings.
-2. Sort by severity:
-   - critical
-   - warning
-   - info
-3. Renumber from 1.
-4. Fix real issues.
-5. Put false positives into `.gitea/ai-review/exclusions.json`.
-6. Add tests when behavior changes.
-
-## Output Rules
-
-- Keep the final list short.
-- Keep numbering contiguous.
-- Preserve file path, location, and fix.
diff --git a/CLAUDE.md b/CLAUDE.md
deleted file mode 100644
index 3b5f291..0000000
--- a/CLAUDE.md
+++ /dev/null
@@ -1,14 +0,0 @@
-# Triage Findings
-
-Use the triage-finding workflow for review issue lists:
-
-1. Merge findings into one list.
-2. Remove duplicates.
-3. Sort by severity: `critical` -> `warning` -> `info`.
-4. Renumber from 1.
-5. Fix real issues with the smallest safe change.
-6. Put false positives into `.gitea/ai-review/exclusions.json`.
-7. Add or update tests when behavior changes.
-8. Re-check after each fix.
-
-The full reusable skill lives in `.claude/skills/triage-findings/SKILL.md`.
diff --git a/GEMINI.md b/GEMINI.md
deleted file mode 100644
index e4cfde8..0000000
--- a/GEMINI.md
+++ /dev/null
@@ -1,14 +0,0 @@
-# Triage Findings
-
-Use the triage-finding workflow for review issue lists:
-
-1. Merge findings into one list.
-2. Remove duplicates.
-3. Sort by severity: `critical` -> `warning` -> `info`.
-4. Renumber from 1.
-5. Fix real issues with the smallest safe change.
-6. Put false positives into `.gitea/ai-review/exclusions.json`.
-7. Add or update tests when behavior changes.
-8. Re-check after each fix.
-
-The reusable skill lives in `.gemini/skills/triage-findings/SKILL.md`.
diff --git a/README.md b/README.md
index f5e3ff5..d47a71e 100644
--- a/README.md
+++ b/README.md
@@ -11,7 +11,7 @@
 5. 從PR問題表格中取出所有舊問題，依照等級排序後 Comment 到 Push Request
 6. 從PR問題表格中取出所有新問題，排除嚴重等級的問題後 Comment 到 Push Request
 7. 從PR問題表格中取出所有新問題，將每個嚴重等級的問題 Comment 到 Push Request
-8. Commit 問題檔案
+8. Commit 問題檔案，將 workspace 中實際存在的同步檔覆蓋到記憶區；workspace 不存在但記憶區已存在的同步檔則移除後再同步，避免 `git add` 因缺檔 pathspec 失敗
 9. 如果PR問題表格中有嚴重問題，則不要讓 workflow 執行成功(exit 1)
 
 # 設計
@@ -227,4 +227,4 @@ Amazon Q：直接輸入 `triage-findings 問題原始檔(文字或截圖)`
 
 ### 版本包含
 
-提交時一併包含 `triage-findings` skill 與各平台入口檔；已存在檔案一律覆蓋，同步到最新內容。
+提交時一併包含 `triage-findings` skill 與各平台入口檔；已存在檔案一律覆蓋，同步到最新內容；若 workspace 已移除某個同步檔，記憶區中的對應檔案也會一併刪除，讓 commit 結果與 workspace 保持一致。
diff --git a/TODO.md b/TODO.md
index ce30abd..2de90ba 100644
--- a/TODO.md
+++ b/TODO.md
@@ -38,9 +38,9 @@
 - 已驗收：log 已明確顯示 `.gitea/ai-review/findings.json` 與 `.gitea/ai-review/exclusions.json` 都是 `JSON 格式正確`。
 
 ## 階段八：記憶區 commit/push 與錯誤處理
-- 目標：記憶區能成功 commit/push，且一併包含 `triage-findings` skill 與各平台入口檔；skill 檔案已存在時一律以來源覆蓋，達到同步效果；錯誤時有明確 log，流程結束有總結訊息。
-- 驗收：log 有「persisted findings」、「commit=...」、「push=...」等訊息，且能看出 skill 相關檔案已一併提交並被覆蓋同步；錯誤時有「Runner failed: ...」等明確錯誤說明。
-- 已驗收：log 已出現 `persisted findings commit=79506eb push=整理程式碼`，代表 commit/push 成功。
+- 目標：記憶區能成功 commit/push，且一併包含 `triage-findings` skill 與各平台入口檔；skill 檔案已存在時一律以來源覆蓋，缺少的同步檔則從記憶區刪除，達到鏡像同步效果；錯誤時有明確 log，流程結束有總結訊息。
+- 驗收：log 有「persisted findings」、「commit=...」、「push=...」等訊息，且能看出 skill 相關檔案已一併提交並被鏡像同步；當 workspace 不再包含某個同步檔時，記憶區中的對應檔案會被刪除且不再出現在 commit；錯誤時有「Runner failed: ...」等明確錯誤說明。
+- 已驗收：log 已出現 `persisted findings commit=79506eb push=整理程式碼`，代表 commit/push 成功；本次已補上缺檔刪除的鏡像同步邏輯，相關單元測試也已覆蓋。
 
 ## 階段九：阻擋嚴重問題 PR（第 8 點）
 - 目標：如果 PR 問題表格中有嚴重（critical）問題，workflow 需直接 exit 1，不讓流程成功。
diff --git a/app/git.js b/app/git.js
index 02637fa..b21c3b5 100644
--- a/app/git.js
+++ b/app/git.js
@@ -65,16 +65,32 @@ export async function commitAndPush(workspace, repoDir, _spawnSync = spawnSync)
       run(['config', 'user.email', 'ai-review[bot]@gitea'], repoDir);
       run(['config', 'user.name', 'AI Review Bot'], repoDir);
 
-      // Always copy source files over the repo copy so skill files stay in sync.
+      const existingSyncPaths = [];
+      const missingSyncPaths = [];
+
+      // Mirror sync files from workspace into the repo copy.
       for (const relPath of SYNC_PATHS) {
         const src = path.join(workspace, relPath);
         const dest = path.join(repoDir, relPath);
-        if (!fs.existsSync(src)) continue;
-        fs.mkdirSync(path.dirname(dest), { recursive: true });
-        fs.copyFileSync(src, dest);
+        if (fs.existsSync(src)) {
+          fs.mkdirSync(path.dirname(dest), { recursive: true });
+          fs.copyFileSync(src, dest);
+          existingSyncPaths.push(relPath);
+          continue;
+        }
+
+        if (fs.existsSync(dest)) {
+          fs.rmSync(dest, { force: true });
+        }
+        missingSyncPaths.push(relPath);
       }
 
-      run(['add', ...SYNC_PATHS], repoDir);
+      if (existingSyncPaths.length > 0) {
+        run(['add', ...existingSyncPaths], repoDir);
+      }
+      if (missingSyncPaths.length > 0) {
+        run(['rm', '--cached', '--ignore-unmatch', '--', ...missingSyncPaths], repoDir);
+      }
 
       const status = run(['status', '--porcelain'], repoDir);
       if (!status) {
diff --git a/app/git.test.js b/app/git.test.js
index e1131e3..9807d01 100644
--- a/app/git.test.js
+++ b/app/git.test.js
@@ -101,6 +101,20 @@ describe('commitAndPush', () => {
     assert.ok(!addCall.args.includes('README.md'));
   });
 
+  it('removes missing sync paths from the repo copy', async () => {
+    const missingPath = path.join(workspace, '.amazonq/rules/triage-findings.md');
+    fs.rmSync(missingPath, { force: true });
+    fs.rmSync(path.join(workspace, 'repo', '.amazonq/rules/triage-findings.md'), { force: true });
+    const spawn = makeSpawn();
+
+    await commitAndPush(workspace, path.join(workspace, 'repo'), spawn);
+
+    const rmCall = spawn.calls.find(c => c.args[0] === 'rm');
+    assert.ok(rmCall, 'expected git rm to run');
+    assert.ok(rmCall.args.includes('.amazonq/rules/triage-findings.md'));
+    assert.equal(fs.existsSync(path.join(workspace, 'repo', '.amazonq/rules/triage-findings.md')), false);
+  });
+
   it('overwrites existing repo copies with workspace files', async () => {
     const repoDir = path.join(workspace, 'repo');
     fs.writeFileSync(path.join(repoDir, '.github/skills/triage-findings/SKILL.md'), 'stale');