@vincent119/go-copilot-rules 1.1.3 → 1.1.4

package/.agent_agy/rules/bash.instructions.md

@@ -0,0 +1,135 @@
+---
+description: 'Bash / Shell Script 撰寫與自動產生規範'
+trigger:
+  patterns:
+    - "**/*.sh"
+    - "**/*.bash"
+---
+
+# Bash / Shell Script 指南（for Copilot & VS Code Agent）
+
+本檔延伸自 .github/copilot-common.md 與 .github/copilot-vocabulary.yaml，統一格式、安全與用詞規範。
+
+---
+
+## 1. 通用原則
+
+- **以 Bash 為主（#!/usr/bin/env bash）**，僅在明確需要時使用 POSIX sh。
+- 生成內容必須：
+  - 可直接執行 (`chmod +x`)
+  - 通過 `shellcheck` 無嚴重警告
+  - 無未定義變數引用 (`set -u`)
+  - 正確處理錯誤與退出碼 (`set -e`, `set -o pipefail`)
+- 絕不假設執行環境，若需相依套件應先檢查 (`command -v ... || exit 1`)。
+
+---
+
+## 2. Header 與格式
+
+- 開頭必須含：
+  ```bash
+  #!/usr/bin/env bash
+  set -euo pipefail
+  IFS=$'\n\t'
+  ```
+- 每個函式前加上註解（用途與參數簡述）。
+- 變數名稱採 **UPPER_SNAKE_CASE**。
+- 函式名稱採 **snake_case**。
+- 內文縮排：**2 空白**。
+- 僅使用 ANSI 可攜語法，避免 bash 4+ 專屬語法於通用腳本中。
+
+---
+
+## 3. 錯誤處理與安全性
+
+- 永遠明確檢查外部命令結果：
+  ```bash
+  if ! curl -fsSL "$url" -o "$file"; then
+    echo "Download failed" >&2
+    exit 1
+  fi
+  ```
+- 禁止使用 `eval`、`source` 未信任來源。
+- 所有 `rm`, `mv`, `cp` 操作需加 `--` 防止意外解析參數。
+- 所有 `$VAR` 展開必加雙引號 `"${VAR}"`。
+
+---
+
+## 4. 函式與結構
+
+- 函式開頭與結尾間保持一行空白：
+  ```bash
+  do_task() {
+    echo "running"
+  }
+  ```
+- 禁止使用全域暫存變數，應以 `local` 管理。
+- 使用 `return` 控制函式內部流程，不直接 `exit`。
+- 使用 `trap` 處理中斷與清理：
+  ```bash
+  trap cleanup EXIT INT TERM
+  ```
+
+---
+
+## 5. CLI / 腳本行為
+
+- 若腳本有參數，必須支援 `-h|--help`。
+- 使用 `getopts` 或明確 `case "$1" in ...)` 處理參數。
+- 所有輸出均應可重導向 (`stdout` / `stderr` 區分明確)。
+- 避免互動式輸入；若必要，允許透過環境變數設定。
+
+---
+
+## 6. Logging 規範
+
+```bash
+log_info()  { echo "[INFO]  $*" >&2; }
+log_warn()  { echo "[WARN]  $*" >&2; }
+log_error() { echo "[ERROR] $*" >&2; }
+```
+
+- 錯誤訊息輸出到 `stderr`。
+- 禁止混用 `echo` 與 `printf` 不同風格輸出。
+- 重要訊息應加上時間戳（選用 `date +"%F %T"`）。
+
+---
+
+## 7. Copilot / Agent 智能產生行為
+
+- 優先保持原始腳本結構與縮排。
+- 生成函式或段落時：
+  - 若已存在同名函式 → 更新內容，不重複定義。
+  - 若需新增 → 插入於主邏輯前。
+- 自動產生變數時：
+  - 須以 `readonly` 或 `local` 宣告。
+  - 不可覆寫現有環境變數。
+- 若檔案包含：
+  - `#!/usr/bin/env bash` → 視為 Bash 語法基準。
+  - `#!/bin/sh` → 僅使用 POSIX 語法（避免 `[[ ]]`、`declare -A`）。
+
+---
+
+## 詞彙與術語（外部參照）
+
+- 本檔不內嵌詞彙表，統一參照 `.github/copilot-vocabulary.yaml`。
+- 若詞彙衝突，以 vocabulary 檔為準。
+- forbidden / preferred / mapping / normalization 詳見該檔。
+
+---
+
+## 8. Review Checklist
+
+- [ ] 通過 `shellcheck` 驗證
+- [ ] 無未加引號的變數展開
+- [ ] 有 `set -euo pipefail`
+- [ ] 所有外部命令有錯誤檢查
+- [ ] 無多餘 `sudo` 或 `eval`
+- [ ] 幫助訊息與參數解析正常
+
+---
+
+放置路徑：
+```
+.github/standards/bash.instructions.md
+```

package/.agent_agy/rules/go-core.copilot-instructions.md

@@ -1,8 +1,12 @@
 ---
-trigger: always_on
+trigger:
+  patterns:
+    - "**/*.go"
+    - "**/go.mod"
+    - "**/go.sum"
 ---
 
-# Go 核心開發規範（Always-On 精簡版）
+# Go 核心開發規範（精簡版）
 
 本檔僅包含**所有 Go 程式碼都需要的基礎規則**。進階主題（DDD、gRPC、Migration 等）已拆分為獨立 Skills，按需載入。
 

package/.agent_agy/skills/aws-eks-ami/SKILL.md

@@ -0,0 +1,120 @@
+---
+name: aws-eks-ami
+description: 查詢 Amazon EKS 專用 AMI (AL2023 x86_64)。支援多版本、多地區、中英文地名查詢。
+---
+
+# Amazon EKS AMI 查詢工具
+
+查詢 Amazon EKS 專用 AMI（Amazon Linux 2023、x86_64 架構），這些 AMI 包含所有必要的執行環境與工具，確保 Worker Node 能順利加入 EKS 叢集。
+
+## 使用時機
+
+當使用者詢問以下需求時，使用此技能：
+- 查詢特定 Kubernetes 版本的 EKS AMI
+- 獲取特定 AWS 地區的 AMI ID
+- 比較不同地區的 AMI 版本
+- 查詢最新可用的 EKS Node AMI
+
+## 查詢方式
+
+### 1. 預設查詢
+查詢 K8s 1.33 版本，東京地區 (ap-northeast-1)：
+```bash
+./scripts/get-aws-eks-ami.sh
+```
+
+### 2. 指定 Kubernetes 版本
+```bash
+K8S_VERSION='1.32' ./scripts/get-aws-eks-ami.sh
+```
+
+### 3. 指定地區（支援中英文）
+```bash
+# 使用英文地名
+REGION='Tokyo' K8S_VERSION='1.32' ./scripts/get-aws-eks-ami.sh
+
+# 使用中文地名
+REGION='東京' K8S_VERSION='1.31' ./scripts/get-aws-eks-ami.sh
+
+# 使用 AWS Region Code
+REGION='us-west-2' K8S_VERSION='1.32' ./scripts/get-aws-eks-ami.sh
+```
+
+## 支援的地區
+
+### 亞太地區 (APAC)
+| 地名 | 中文名 | Region Code |
+|------|--------|-------------|
+| Tokyo | 東京 | ap-northeast-1 |
+| Seoul | 首爾 | ap-northeast-2 |
+| Osaka | 大阪 | ap-northeast-3 |
+| Singapore | 新加坡 | ap-southeast-1 |
+| Sydney | 雪梨 | ap-southeast-2 |
+| Jakarta | 雅加達 | ap-southeast-3 |
+| Melbourne | 墨爾本 | ap-southeast-4 |
+| HongKong | 香港 | ap-east-1 |
+| Bangkok | 曼谷 | ap-southeast-1 |
+| Mumbai | 孟買 | ap-south-1 |
+| Taipei | 台北 | ap-northeast-1 * |
+
+*台北目前使用東京地區
+
+### 美洲地區
+| 地名 | Region Code |
+|------|-------------|
+| Virginia | us-east-1 |
+| Ohio | us-east-2 |
+| California | us-west-1 |
+| Oregon | us-west-2 |
+| Canada | ca-central-1 |
+| SaoPaulo | sa-east-1 |
+
+### 歐洲與中東
+| 地名 | Region Code |
+|------|-------------|
+| Ireland | eu-west-1 |
+| London | eu-west-2 |
+| Paris | eu-west-3 |
+| Frankfurt | eu-central-1 |
+| Stockholm | eu-north-1 |
+| Bahrain | me-south-1 |
+
+## 輸出格式
+
+腳本會以表格形式輸出，按建立時間從新到舊排序：
+- **Name**: AMI 完整名稱
+- **ImageId**: AMI ID (ami-xxxxx)
+- **Architecture**: 架構 (x86_64)
+- **CreationDate**: 建立日期
+
+## 注意事項
+
+1. **回覆使用者時，請提供最新（表格最上方）的 AMI ID**
+2. 確認使用者的 Kubernetes 版本與 EKS 叢集版本一致
+3. 不同地區的 AMI ID 不同，需針對目標地區查詢
+4. 建議使用最新版本的 AMI 以獲得安全更新
+5. 執行腳本需要安裝 AWS CLI 並配置好認證
+
+## 常見使用案例
+
+### 案例 1: 新建 EKS Node Group
+```bash
+# 查詢生產環境使用的最新 AMI
+REGION='Tokyo' K8S_VERSION='1.32' ./scripts/get-aws-eks-ami.sh
+```
+
+### 案例 2: 多地區部署
+```bash
+# 東京地區
+REGION='Tokyo' K8S_VERSION='1.32' ./scripts/get-aws-eks-ami.sh
+
+# 新加坡地區
+REGION='Singapore' K8S_VERSION='1.32' ./scripts/get-aws-eks-ami.sh
+```
+
+### 案例 3: 版本升級
+```bash
+# 比較不同版本的 AMI
+K8S_VERSION='1.31' ./scripts/get-aws-eks-ami.sh
+K8S_VERSION='1.32' ./scripts/get-aws-eks-ami.sh
+```

package/.agent_agy/skills/aws-eks-ami/scripts/get-aws-eks-ami.sh

@@ -0,0 +1,130 @@
+#!/bin/bash
+set -euo pipefail
+
+# 預設值
+K8S_VERSION="${K8S_VERSION:-1.33}"
+REGION="${REGION:-${AWS_REGION:-ap-northeast-1}}"
+
+# 將人類可讀的地名轉換為 AWS Region Code
+case "$(echo "$REGION" | tr '[:upper:]' '[:lower:]')" in
+  # 亞太地區 - 東北亞
+  "tokyo" | "東京" )
+    TARGET_REGION="ap-northeast-1"
+    ;;
+  "seoul" | "首爾" )
+    TARGET_REGION="ap-northeast-2"
+    ;;
+  "osaka" | "大阪" )
+    TARGET_REGION="ap-northeast-3"
+    ;;
+  "taipei" | "台北" | "臺北" )
+    TARGET_REGION="ap-northeast-1"  # 台北目前使用東京地區
+    ;;
+
+  # 亞太地區 - 東南亞
+  "singapore" | "新加坡" )
+    TARGET_REGION="ap-southeast-1"
+    ;;
+  "bangkok" | "曼谷" )
+    TARGET_REGION="ap-southeast-1"  # 曼谷使用新加坡地區
+    ;;
+  "sydney" | "雪梨" )
+    TARGET_REGION="ap-southeast-2"
+    ;;
+  "jakarta" | "雅加達" )
+    TARGET_REGION="ap-southeast-3"
+    ;;
+  "melbourne" | "墨爾本" )
+    TARGET_REGION="ap-southeast-4"
+    ;;
+
+  # 亞太地區 - 其他
+  "hongkong" | "hong kong" | "香港" )
+    TARGET_REGION="ap-east-1"
+    ;;
+  "mumbai" | "孟買" )
+    TARGET_REGION="ap-south-1"
+    ;;
+
+  # 美洲地區
+  "virginia" | "維吉尼亞" | "us-east" )
+    TARGET_REGION="us-east-1"
+    ;;
+  "ohio" | "俄亥俄" )
+    TARGET_REGION="us-east-2"
+    ;;
+  "california" | "加州" | "北加州" )
+    TARGET_REGION="us-west-1"
+    ;;
+  "oregon" | "奧勒岡" )
+    TARGET_REGION="us-west-2"
+    ;;
+  "canada" | "加拿大" )
+    TARGET_REGION="ca-central-1"
+    ;;
+  "saopaulo" | "聖保羅" )
+    TARGET_REGION="sa-east-1"
+    ;;
+
+  # 歐洲與中東
+  "ireland" | "愛爾蘭" )
+    TARGET_REGION="eu-west-1"
+    ;;
+  "london" | "倫敦" )
+    TARGET_REGION="eu-west-2"
+    ;;
+  "paris" | "巴黎" )
+    TARGET_REGION="eu-west-3"
+    ;;
+  "frankfurt" | "法蘭克福" )
+    TARGET_REGION="eu-central-1"
+    ;;
+  "stockholm" | "斯德哥爾摩" )
+    TARGET_REGION="eu-north-1"
+    ;;
+  "bahrain" | "巴林" )
+    TARGET_REGION="me-south-1"
+    ;;
+
+  *)
+    # 預設直接使用傳入的字串（假設它是正確的 Region Code）
+    TARGET_REGION="$REGION"
+    ;;
+esac
+
+echo "================================================="
+echo "🔍 查詢 Amazon EKS AMI"
+echo "================================================="
+echo "Kubernetes 版本: ${K8S_VERSION}"
+echo "AWS 區域: ${TARGET_REGION}"
+echo "AMI 類型: Amazon Linux 2023 (x86_64)"
+echo "================================================="
+echo ""
+
+# 檢查 AWS CLI 是否安裝
+if ! command -v aws &> /dev/null; then
+    echo "❌ 錯誤: 找不到 AWS CLI"
+    echo "請先安裝 AWS CLI: https://aws.amazon.com/cli/"
+    exit 1
+fi
+
+# 查詢 AMI
+aws ec2 describe-images \
+  --region "${TARGET_REGION}" \
+  --owners amazon \
+  --filters "Name=name,Values=amazon-eks-node-al2023-x86_64-standard-${K8S_VERSION}-*" \
+            "Name=state,Values=available" \
+            "Name=architecture,Values=x86_64" \
+            "Name=is-public,Values=true" \
+  --query 'reverse(sort_by(Images, &CreationDate))[].{
+      Name: Name,
+      ImageId: ImageId,
+      Architecture: Architecture,
+      CreationDate: CreationDate,
+      PlatformDetails: PlatformDetails
+  }' \
+  --output table
+
+echo ""
+echo "✅ 查詢完成"
+echo "💡 提示: 表格最上方的 AMI 為最新版本"

package/.agent_agy/skills/changelog-generator/SKILL.md

@@ -0,0 +1,82 @@
+---
+name: changelog-generator
+description: Transform Git commits into user-facing changelogs. Auto-categorize, filter noise, generate professional Release Notes.
+---
+
+# Changelog Generator
+
+Convert technical commits into user-friendly release notes. Supports GitHub Release, App Store updates, email notifications, and more.
+
+## When to Use
+
+Version releases, product update summaries, App Store submissions, public CHANGELOG maintenance.
+
+## Core Features
+
+1. **Auto-categorize**: feat→Added, fix→Fixed, perf→Improved
+2. **Filter noise**: Exclude CI/CD, tests, refactors, docs
+3. **Language transform**: Technical terms → User value descriptions
+4. **Follow standards**: Semantic Versioning + Keep a Changelog
+
+## Usage
+
+```bash
+# Basic usage
+Generate changelog for commits from the last 7 days
+Create release notes for v2.5.0
+
+# Specify range
+Create changelog for commits between 3/1 and 3/15
+Generate changelog for commits after v2.4.0
+```
+
+## Output Format
+
+```markdown
+## [X.Y.Z] - YYYY-MM-DD
+
+### ✨ Added
+- Feature description (emphasize user value)
+
+### 🔧 Changed
+- Improvement description (explain benefits)
+
+### 🐛 Fixed
+- Fix description (problem solved)
+
+### ⚠️ Breaking Changes
+- Change description (impact & migration guide)
+```
+
+## Filter Rules
+
+**Exclude**: CI/CD, version bumps, refactors, tests, comments, logs, non-impactful dependency updates
+**Include**: All changes affecting end users
+
+## Writing Principles
+
+1. One item per logical change
+2. No commit hashes, PR numbers, internal module names
+3. Avoid vague terms (improve/update), be specific about impact
+4. Use past tense, affirmative tone
+5. Emphasize "what was solved" or "what was gained"
+
+## Example
+
+**Input**: Last 7 days commits
+**Output**:
+```markdown
+## [2.5.0] - 2024-03-10
+
+### ✨ Added
+- **Team Workspaces**: Create separate workspaces and invite team members
+- **Keyboard Shortcuts**: Press ? to view all shortcuts
+
+### 🔧 Changed
+- 2x faster file sync across devices
+- Search now includes file content
+
+### 🐛 Fixed
+- Fixed large image upload failures
+- Resolved notification count errors
+```

package/.agent_agy/skills/k8s-debug/SKILL.md

@@ -0,0 +1,75 @@
+---
+name: k8s-debug
+description: Kubernetes troubleshooting workflow - Pod status, logs, events, exec, and resource monitoring.
+---
+
+# K8s Debugging Workflow
+
+Systematic approach to diagnose and fix Kubernetes application issues.
+
+## 1. Check Pod Status
+
+Identify pods in error states (CrashLoopBackOff, ImagePullBackOff, etc.):
+
+```bash
+kubectl get pods -o wide
+kubectl describe pod <POD_NAME>
+```
+
+## 2. View Logs
+
+Check container logs for errors and stack traces:
+
+```bash
+# Current logs
+kubectl logs <POD_NAME> [-c <CONTAINER>]
+
+# Previous crash logs
+kubectl logs <POD_NAME> --previous
+```
+
+## 3. Check Events
+
+Review cluster events for scheduling/mounting/health check failures:
+
+```bash
+kubectl get events --sort-by=.lastTimestamp
+```
+
+## 4. Exec into Container
+
+Debug filesystem, environment, or network issues:
+
+```bash
+kubectl exec -it <POD_NAME> -- sh
+
+# Inside container:
+env                          # Check environment variables
+curl localhost:8080          # Test HTTP endpoints
+nc -zv <HOST> <PORT>         # Test network connectivity
+```
+
+## 5. Port Forward
+
+Forward pod port to local for testing:
+
+```bash
+kubectl port-forward <POD_NAME> 8080:8080
+```
+
+## 6. Monitor Resources
+
+Check for OOM or CPU throttling:
+
+```bash
+kubectl top pod <POD_NAME>
+```
+
+## Common Issues
+
+| Issue | Command | Solution |
+|-------|---------|----------|
+| CrashLoopBackOff | `logs --previous` | Check startup errors |
+| ImagePullBackOff | `describe pod` | Verify image name/credentials |
+| Pending | `get events` | Check resource limits/node capacity |
+| OOMKilled | `top pod` | Increase memory limits |

package/.agent_agy/skills/release-workflow/SKILL.md

@@ -0,0 +1,85 @@
+---
+name: release-workflow
+description: Standard release workflow - Test, tag, push. Supports Go, Python, Node.js, Bash, YAML projects.
+---
+
+# Release Workflow
+
+Standard process for releasing new versions across different project types.
+
+## Workflow Steps
+
+### 1. Check Git Status
+
+Ensure clean working directory:
+
+```bash
+git status --porcelain
+```
+
+### 2. Run Tests
+
+Execute tests based on project type:
+
+```bash
+# Go
+go test -v ./...
+
+# Python
+pytest
+
+# Node.js
+npm test
+
+# Bash
+bash -n script.sh
+
+# YAML
+yamllint .
+```
+
+### 3. Determine Version
+
+Review existing tags and decide next version:
+
+```bash
+git tag --sort=-v:refname | head -n 5
+```
+
+**Ask user**: "What should the next version tag be? (e.g., v1.0.1)"
+
+### 4. Create Tag
+
+```bash
+git tag <VERSION>
+```
+
+### 5. Push Tag
+
+```bash
+git push origin <VERSION>
+```
+
+### 6. Verify (Optional)
+
+```bash
+git ls-remote --tags origin | grep <VERSION>
+```
+
+## Version Guidelines
+
+| Change Type | Version Bump | Example |
+|------------|--------------|---------|
+| Breaking changes | Major | v1.0.0 → v2.0.0 |
+| New features | Minor | v1.0.0 → v1.1.0 |
+| Bug fixes | Patch | v1.0.0 → v1.0.1 |
+
+## Common Patterns
+
+```bash
+# Full workflow one-liner
+git status --porcelain && \
+go test -v ./... && \
+git tag v1.0.1 && \
+git push origin v1.0.1
+```

package/.agent_agy/skills/skill-creator/SKILL.md

@@ -0,0 +1,88 @@
+---
+name: skill-creator
+description: Guide for creating effective skills. Use when creating/updating skills to extend Claude's capabilities with workflows, tools, or domain knowledge.
+---
+
+# Skill Creator
+
+Skills extend Claude with specialized workflows, tools, and domain knowledge through modular packages.
+
+## What Skills Provide
+
+- Specialized multi-step workflows
+- Tool integrations and file format handling
+- Domain expertise and business logic
+- Bundled resources (scripts, references, assets)
+
+## Core Principles
+
+**Be Concise**: Context window is shared. Assume Claude is smart—only add what's truly needed.
+
+**Set Appropriate Freedom**:
+- **High** (text instructions): Multiple valid approaches
+- **Medium** (pseudocode/scripts): Preferred patterns with flexibility
+- **Low** (specific scripts): Fragile operations requiring consistency
+
+## Skill Structure
+
+```bash
+skill-name/
+├── SKILL.md (required)
+│   ├── YAML: name + description
+│   └── Markdown: instructions
+└── Optional resources:
+    ├── scripts/     - Executable code
+    ├── references/  - Docs loaded as needed
+    └── assets/      - Output templates/files
+```
+
+**Resources**:
+- `scripts/`: Reusable code (Python/Bash)
+- `references/`: Domain docs, schemas, APIs
+- `assets/`: Templates, images, boilerplates
+
+**Exclude**: README, CHANGELOG, docs not needed by Claude
+
+## Progressive Disclosure
+
+3-tier loading:
+1. **Metadata** (~100 words) - Always loaded
+2. **SKILL.md body** (<500 lines) - When triggered
+3. **Resources** - On demand
+
+**Patterns**:
+```markdown
+# Core workflow in SKILL.md
+* Advanced: See [ADVANCED.md]
+* API: See [API.md]
+```
+
+Organize by domain/framework:
+```
+cloud-deploy/
+├── SKILL.md
+└── references/
+    ├── aws.md
+    └── gcp.md
+```
+
+## Creation Process
+
+1. **Understand**: Clarify use cases with examples
+2. **Plan**: Identify reusable scripts/references/assets
+3. **Initialize**: `scripts/init_skill.py <name> --path <dir>`
+4. **Edit**:
+   - Add resources (scripts/references/assets)
+   - Write SKILL.md with:
+     - **Frontmatter**: `name` + `description` (trigger conditions)
+     - **Body**: Instructions and workflows
+5. **Package**: `scripts/package_skill.py <path>`
+6. **Iterate**: Test and refine
+
+## Writing Guidelines
+
+- Use imperative/infinitive tense
+- `description`: Include what + when to use
+- Keep SKILL.md <500 lines
+- Test scripts before packaging
+- Remove unused example files

package/.agent_agy/skills/test-coverage/SKILL.md

@@ -0,0 +1,51 @@
+---
+name: test-coverage
+description: Run tests with coverage reports for Go, Python, and Node.js projects.
+---
+
+# Test Coverage
+
+Generate test coverage reports across multiple languages.
+
+## Go
+
+```bash
+# Run tests with coverage
+go test -v -coverprofile=coverage.out ./...
+
+# Terminal summary
+go tool cover -func=coverage.out
+
+# HTML report
+go tool cover -html=coverage.out -o coverage.html
+```
+
+## Python
+
+Requires `pytest` and `pytest-cov`:
+
+```bash
+pytest --cov=. --cov-report=term --cov-report=html
+```
+
+HTML report: `htmlcov/index.html`
+
+## Node.js
+
+Using Jest:
+
+```bash
+npm test -- --coverage
+```
+
+HTML report: `coverage/lcov-report/index.html`
+
+## Coverage Goals
+
+| Metric | Target |
+|--------|--------|
+| Overall | >80% |
+| Critical paths | >90% |
+| New code | 100% |
+
+**Cleanup**: Remove `coverage.out`, `htmlcov/`, `coverage/` after review.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@vincent119/go-copilot-rules",
-  "version": "1.1.3",
+  "version": "1.1.4",
   "description": "Professional Go development rules and skills for GitHub Copilot, Cursor, and other AI coding assistants",
   "keywords": [
     "copilot",