@fitlab-ai/agent-infra 0.3.1 → 0.4.0

package/templates/.agents/skills/create-task/SKILL.zh-CN.md

@@ -33,12 +33,13 @@ description: >
 
 如果描述不清晰，**先向用户确认**再继续。
 
-**类型推断规则**：
-- 包含 "add"、"new"、"support"、"implement" -> `feature`
-- 包含 "fix"、"resolve"、"bug"、"error" -> `bugfix`
-- 包含 "refactor"、"optimize"、"improve"、"clean up" -> `refactor`
-- 包含 "document"、"javadoc"、"comment"、"readme" -> `docs`
-- 其他 -> `chore`
+**类型推断**：根据任务描述的语义，从以下候选值中选择最匹配的类型：
+
+- `feature` — 新增功能、新特性
+- `bugfix` — 修复缺陷、错误
+- `refactor` — 重构、优化、改进
+- `docs` — 文档相关
+- `chore` — 其他杂项任务
 
 **工作流映射**：
 - `feature` / `docs` / `chore` -> `feature-development`
@@ -53,7 +54,7 @@ description: >
 date +%Y%m%d-%H%M%S
 ```
 
-- 创建任务目录：`.agent-workspace/active/TASK-{yyyyMMdd-HHmmss}/`
+- 创建任务目录：`.agents/workspace/active/TASK-{yyyyMMdd-HHmmss}/`
 - 使用 `.agents/templates/task.md` 模板创建任务文件：`task.md`
 
 **重要**：
@@ -84,7 +85,7 @@ assigned_to: {当前 AI 代理}
 date "+%Y-%m-%d %H:%M:%S"
 ```
 
-更新 `.agent-workspace/active/{task-id}/task.md`：
+更新 `.agents/workspace/active/{task-id}/task.md`：
 - `current_step`：requirement-analysis
 - `assigned_to`：{当前 AI 代理}
 - `updated_at`：{当前时间}
@@ -108,7 +109,7 @@ date "+%Y-%m-%d %H:%M:%S"
 - 工作流：{workflow}
 
 产出文件：
-- 任务文件：.agent-workspace/active/{task-id}/task.md
+- 任务文件：.agents/workspace/active/{task-id}/task.md
 
 下一步 - 执行需求分析：
   - Claude Code / OpenCode：/analyze-task {task-id}
@@ -118,7 +119,7 @@ date "+%Y-%m-%d %H:%M:%S"
 
 ## 完成检查清单
 
-- [ ] 创建了任务文件 `.agent-workspace/active/{task-id}/task.md`
+- [ ] 创建了任务文件 `.agents/workspace/active/{task-id}/task.md`
 - [ ] 更新了 task.md 中的 `current_step` 为 requirement-analysis
 - [ ] 更新了 task.md 中的 `updated_at` 为当前时间
 - [ ] 更新了 task.md 中的 `assigned_to`

package/templates/.agents/skills/implement-task/SKILL.md

@@ -21,7 +21,7 @@ description: >
 ### 1. Verify Prerequisites
 
 Check required files:
-- `.agent-workspace/active/{task-id}/task.md` - Task file
+- `.agents/workspace/active/{task-id}/task.md` - Task file
 - At least one technical plan artifact: `plan.md` or `plan-r{N}.md`
 
 Note: `{task-id}` format is `TASK-{yyyyMMdd-HHmmss}`, e.g. `TASK-20260306-143022`
@@ -30,10 +30,10 @@ If either file is missing, prompt the user to complete the prerequisite step fir
 
 ### 2. Determine the Input Plan and Implementation Round
 
-Scan `.agent-workspace/active/{task-id}/` for technical plan files (`plan.md`, `plan-r{N}.md`):
+Scan `.agents/workspace/active/{task-id}/` for technical plan files (`plan.md`, `plan-r{N}.md`):
 - Read the highest-round plan file and record it as `{plan-artifact}`
 
-Scan `.agent-workspace/active/{task-id}/` for implementation report files:
+Scan `.agents/workspace/active/{task-id}/` for implementation report files:
 - If neither `implementation.md` nor `implementation-r*.md` exists -> this is Round 1 and must create `implementation.md`
 - If `implementation.md` exists and no `implementation-r*.md` exists -> this is Round 2 and must create `implementation-r2.md`
 - If `implementation-r{N}.md` exists -> this is Round N+1 and must create `implementation-r{N+1}.md`
@@ -71,7 +71,7 @@ Follow the `implementation` step in `.agents/workflows/feature-development.yaml`
 3. **Test continuously**: Run tests after completing each step
 4. **Keep it simple**: Do not over-engineer or add unplanned features
 
-### 5. Run Test Verification (Failure Must Stop the Flow)
+### 5. Run Test Verification
 
 Execute the project's test command. Reference the `test` skill for the project-specific test command:
 
@@ -84,19 +84,16 @@ Execute the project's test command. Reference the `test` skill for the project-s
 # go test ./...     (Go)
 ```
 
-> **⚠️ Failure Branch — if tests fail, you must immediately take the failure path:**
->
-> - Output a summary of the test errors
-> - Ask the user whether to continue
-> - Stop immediately: do not create the implementation report, do not mark task.md as implementation-complete, and do not output the Step 8 "Implementation complete for task {task-id}." template
->
-> **You may continue to Steps 6, 7, and 8 only when all tests pass.**
+If tests fail:
+- Analyze the failure first, and prioritize fixing problems introduced by the current implementation, plus any test or documentation updates required to match the approved plan
+- Re-run the tests after each fix until they pass, or until you confirm the remaining issue is an external blocker outside the current task scope
+- Only stop when the failure is blocked by external dependencies, missing environment, or unclear requirements that cannot be resolved within the task; in that case, report the blocker and do not create the implementation report, update task.md as implementation-complete, or output the Step 8 completion template
 
-Ensure all tests pass. Proceed to Steps 6, 7, and 8 only when the entire test suite passes.
+Proceed to Steps 6, 7, and 8 only after the full test suite passes.
 
 ### 6. Output Implementation Report
 
-Create `.agent-workspace/active/{task-id}/{implementation-artifact}`.
+Create `.agents/workspace/active/{task-id}/{implementation-artifact}`.
 
 Requirements:
 - Do not overwrite any existing implementation report
@@ -111,7 +108,7 @@ Get the current time:
 date "+%Y-%m-%d %H:%M:%S"
 ```
 
-Update `.agent-workspace/active/{task-id}/task.md`:
+Update `.agents/workspace/active/{task-id}/task.md`:
 - `current_step`: implementation
 - `assigned_to`: {current AI agent}
 - `updated_at`: {current time}
@@ -136,7 +133,7 @@ Summary:
 - Tests passed: {count}/{total}
 
 Output file:
-- Implementation report: .agent-workspace/active/{task-id}/{implementation-artifact} (Round {implementation-round})
+- Implementation report: .agents/workspace/active/{task-id}/{implementation-artifact} (Round {implementation-round})
 
 Next step - code review:
   - Claude Code / OpenCode: /review-task {task-id}
@@ -207,7 +204,7 @@ Next step - code review:
 ## Completion Checklist
 
 - [ ] Completed all code implementation
-- [ ] Created implementation report `.agent-workspace/active/{task-id}/{implementation-artifact}`
+- [ ] Created implementation report `.agents/workspace/active/{task-id}/{implementation-artifact}`
 - [ ] All tests pass
 - [ ] Updated `current_step` to implementation in task.md
 - [ ] Updated `updated_at` to current time in task.md
@@ -224,7 +221,7 @@ After completing the checklist, **stop**. Do not auto-commit. Wait for code revi
 
 1. **Prerequisites**: Must have a reviewed technical plan (`plan.md` or `plan-r{N}.md` exists and is approved)
 2. **No auto-commit**: Do NOT execute `git commit` or `git add` automatically. Remind the user to commit manually
-3. **Test requirement**: All new code must have unit tests; test coverage must not decrease
+3. **Test requirement**: All new code must have unit tests; test coverage must not decrease. When removing a feature, delete the test fixtures and assertions that existed solely for that feature — do not mechanically flip assertions; every assertion must verify meaningful business logic, not merely confirm that data passes through unchanged
 4. **Code quality**: Follow project coding standards
 5. **Plan deviation**: If you need to deviate from the plan, document the reason in the implementation report
 6. **Versioning rule**: First-round implementation uses `implementation.md`; later re-implementations use `implementation-r{N}.md`
@@ -233,5 +230,5 @@ After completing the checklist, **stop**. Do not auto-commit. Wait for code revi
 
 - Task not found: Prompt "Task {task-id} not found"
 - Missing plan: Prompt "Technical plan not found, please run the plan-task skill first"
-- Test failure: Output test errors, ask user whether to continue, and stop immediately without creating the implementation report or outputting "Implementation complete for task {task-id}."
+- Test failure: Attempt to fix the issue and re-run tests first; stop only when an external blocker, missing environment, or unclear requirement prevents completion, and report that blocker
 - Build failure: Output build errors, stop implementation

package/templates/.agents/skills/implement-task/SKILL.zh-CN.md

@@ -19,7 +19,7 @@ description: >
 ### 1. 验证前置条件
 
 检查必要文件：
-- `.agent-workspace/active/{task-id}/task.md` - 任务文件
+- `.agents/workspace/active/{task-id}/task.md` - 任务文件
 - 至少一个技术方案产物：`plan.md` 或 `plan-r{N}.md`
 
 注意：`{task-id}` 格式为 `TASK-{yyyyMMdd-HHmmss}`，例如 `TASK-20260306-143022`
@@ -28,10 +28,10 @@ description: >
 
 ### 2. 确定输入方案与实现轮次
 
-扫描 `.agent-workspace/active/{task-id}/` 目录中的技术方案文件（`plan.md`、`plan-r{N}.md`）：
+扫描 `.agents/workspace/active/{task-id}/` 目录中的技术方案文件（`plan.md`、`plan-r{N}.md`）：
 - 读取最高轮次的方案文件，记为 `{plan-artifact}`
 
-扫描 `.agent-workspace/active/{task-id}/` 目录中的实现报告文件：
+扫描 `.agents/workspace/active/{task-id}/` 目录中的实现报告文件：
 - 如果不存在 `implementation.md` 且不存在 `implementation-r*.md` → 本轮为第 1 轮，产出 `implementation.md`
 - 如果存在 `implementation.md` 且不存在 `implementation-r*.md` → 本轮为第 2 轮，产出 `implementation-r2.md`
 - 如果存在 `implementation-r{N}.md` → 本轮为第 N+1 轮，产出 `implementation-r{N+1}.md`
@@ -69,7 +69,7 @@ description: >
 3. **持续测试**：每完成一个步骤后运行测试
 4. **保持简单**：不过度设计，不添加计划外的功能
 
-### 5. 运行测试验证（失败时必须停止）
+### 5. 运行测试验证
 
 执行项目的测试命令。参考 `test` 技能获取项目特定的测试命令：
 
@@ -82,19 +82,16 @@ description: >
 # go test ./...     (Go)
 ```
 
-> **⚠️ 失败分支 — 如果测试失败，你必须立即走失败分支：**
->
-> - 输出测试错误摘要
-> - 询问用户是否继续处理
-> - 立即停止，不创建实现报告，不更新 task.md 为实现完成，也不要输出步骤 8 的「任务 {task-id} 实现完成。」模板
->
-> **只有测试全部通过时，才可以继续步骤 6、7 和 8。**
+如果测试失败：
+- 先分析失败原因，优先修复由本次实现引入的问题，以及为匹配已批准方案而需要同步调整的测试或文档
+- 修复后重新运行测试，直到测试通过，或明确确认存在超出当前任务范围的外部阻塞
+- 仅当问题属于外部阻塞、环境缺失或需求不明确且无法在当前任务内解决时，才向用户报告阻塞并停止；此时不要创建实现报告，不要更新 task.md 为实现完成，也不要输出步骤 8 的完成模板
 
-确保所有测试通过。只有全部通过时，才可以继续步骤 6、7 和 8。
+只有全部测试通过后，才可以继续步骤 6、7 和 8。
 
 ### 6. 输出实现报告
 
-创建 `.agent-workspace/active/{task-id}/{implementation-artifact}`。
+创建 `.agents/workspace/active/{task-id}/{implementation-artifact}`。
 
 要求：
 - 不要覆盖已有的实现报告
@@ -109,7 +106,7 @@ description: >
 date "+%Y-%m-%d %H:%M:%S"
 ```
 
-更新 `.agent-workspace/active/{task-id}/task.md`：
+更新 `.agents/workspace/active/{task-id}/task.md`：
 - `current_step`：implementation
 - `assigned_to`：{当前 AI 代理}
 - `updated_at`：{当前时间}
@@ -134,7 +131,7 @@ date "+%Y-%m-%d %H:%M:%S"
 - 测试通过：{数量}/{总数}
 
 产出文件：
-- 实现报告：.agent-workspace/active/{task-id}/{implementation-artifact}（Round {implementation-round}）
+- 实现报告：.agents/workspace/active/{task-id}/{implementation-artifact}（Round {implementation-round}）
 
 下一步 - 代码审查：
   - Claude Code / OpenCode：/review-task {task-id}
@@ -205,7 +202,7 @@ date "+%Y-%m-%d %H:%M:%S"
 ## 完成检查清单
 
 - [ ] 完成了所有代码实现
-- [ ] 创建了实现报告 `.agent-workspace/active/{task-id}/{implementation-artifact}`
+- [ ] 创建了实现报告 `.agents/workspace/active/{task-id}/{implementation-artifact}`
 - [ ] 所有测试通过
 - [ ] 更新了 task.md 中的 `current_step` 为 implementation
 - [ ] 更新了 task.md 中的 `updated_at` 为当前时间
@@ -222,7 +219,7 @@ date "+%Y-%m-%d %H:%M:%S"
 
 1. **前置条件**：必须有已审查的技术方案（`plan.md` 或 `plan-r{N}.md` 存在且已获批准）
 2. **禁止自动提交**：不要自动执行 `git commit` 或 `git add`。提醒用户手动提交
-3. **测试要求**：所有新代码必须有单元测试；测试覆盖率不得下降
+3. **测试要求**：所有新代码必须有单元测试；测试覆盖率不得下降。删除功能时，必须同时删除为该功能而存在的测试 fixture 和断言，不要机械地翻转断言方向；每条断言都应验证有意义的业务逻辑，仅确认数据原样通过的断言不构成有效测试
 4. **代码质量**：遵循项目编码规范
 5. **计划偏离**：如果需要偏离计划，在实现报告中记录原因
 6. **版本化规则**：首轮实现使用 `implementation.md`；后续重实现使用 `implementation-r{N}.md`
@@ -231,5 +228,5 @@ date "+%Y-%m-%d %H:%M:%S"
 
 - 任务未找到：提示 "Task {task-id} not found"
 - 缺少计划：提示 "Technical plan not found, please run the plan-task skill first"
-- 测试失败：输出测试错误，询问用户是否继续；立即停止，不要创建实现报告，也不要输出 "任务 {task-id} 实现完成。"
+- 测试失败：先尝试修复并重新运行测试；只有在存在外部阻塞、环境缺失或需求不明确时才停止，并输出阻塞原因
 - 构建失败：输出构建错误，停止实现

package/templates/.agents/skills/import-codescan/SKILL.md

@@ -1,43 +1,44 @@
 ---
 name: import-codescan
 description: >
-  导入 Code Scanning（CodeQL）告警并创建修复任务。
-  当用户要求导入 Code Scanning 告警时触发。参数：告警编号。
+  Import a Code Scanning (CodeQL) alert and create a remediation task.
+  Triggered when the user asks to import a Code Scanning alert.
+  Argument: alert number.
 ---
 
-# 导入 Code Scanning 告警
+# Import Code Scanning Alert
 
-导入指定的 Code Scanning（CodeQL）告警并创建修复任务。
+Import the specified Code Scanning (CodeQL) alert and create a remediation task.
 
-## 行为边界 / 关键规则
+## Boundary / Critical Rules
 
-- 本技能仅负责导入告警并创建任务骨架 —— 不直接修改业务代码或关闭告警
-- 不要自动提交。绝不自动执行 `git commit` 或 `git add`
-- 执行本技能后，你**必须**立即更新 task.md 中的任务状态
+- This skill only imports the alert and creates a task skeleton; it does not directly modify business code or dismiss the alert
+- Do NOT auto-commit. Never execute `git commit` or `git add` automatically
+- After executing this skill, you **must** immediately update task status in task.md
 
-## 执行流程
+## Execution Flow
 
-### 1. 获取告警信息
+### 1. Retrieve Alert Information
 
 ```bash
 gh api repos/{owner}/{repo}/code-scanning/alerts/<alert-number>
 ```
 
-提取关键信息：
-- `number`：告警编号
-- `state`：状态（open/dismissed/fixed）
-- `rule`：规则信息（id、severity、description、security_severity_level）
-- `tool`：扫描工具信息（name、version）
-- `most_recent_instance`：位置（path、start_line、end_line）、消息
-- `html_url`：GitHub 告警链接
+Extract key information:
+- `number`: alert number
+- `state`: state (`open` / `dismissed` / `fixed`)
+- `rule`: rule information (`id`, `severity`, `description`, `security_severity_level`)
+- `tool`: scanning tool information (`name`, `version`)
+- `most_recent_instance`: location (`path`, `start_line`, `end_line`) and message
+- `html_url`: GitHub alert link
 
-### 2. 创建任务目录和文件
+### 2. Create the Task Directory and File
 
-检查是否已存在该告警的任务。如果不存在，创建：
+Check whether a task for this alert already exists. If not, create one:
 
-目录：`.agent-workspace/active/TASK-{yyyyMMdd-HHmmss}/`
+Directory: `.agents/workspace/active/TASK-{yyyyMMdd-HHmmss}/`
 
-任务元数据：
+Task metadata:
 ```yaml
 id: TASK-{yyyyMMdd-HHmmss}
 codescan_alert_number: <alert-number>
@@ -46,58 +47,58 @@ rule_id: <rule-id>
 tool: <tool-name>
 ```
 
-### 3. 更新任务状态
+### 3. Update Task Status
 
-获取当前时间：
+Get the current time:
 
 ```bash
 date "+%Y-%m-%d %H:%M:%S"
 ```
 
-更新 task.md：`current_step` -> `requirement-analysis`。
-- **追加**到 `## Activity Log`（不要覆盖之前的记录）：
+Update task.md: `current_step` -> `requirement-analysis`.
+- **Append** to `## Activity Log` (do NOT overwrite previous entries):
   ```
   - {yyyy-MM-dd HH:mm:ss} — **Import Code Scanning Alert** by {agent} — Code Scanning alert #{alert-number} imported
   ```
 
-### 4. 告知用户
+### 4. Inform User
 
-> **重要**：以下「下一步」中列出的所有 TUI 命令格式必须完整输出，不要只展示当前 AI 代理对应的格式。
+> **IMPORTANT**: All TUI command formats listed below must be output in full. Do not show only the format for the current AI agent.
 
 ```
-Code Scanning 告警 #{alert-number} 已导入。
+Code Scanning alert #{alert-number} imported.
 
-告警信息：
-- 严重程度：{severity}
-- 规则：{rule-id}
-- 位置：{file-path}:{line-number}
+Alert information:
+- Severity: {severity}
+- Rule: {rule-id}
+- Location: {file-path}:{line-number}
 
-任务信息：
-- 任务 ID：{task-id}
+Task information:
+- Task ID: {task-id}
 
-下一步：
-  - Claude Code / OpenCode：/analyze-task {task-id}
-  - Gemini CLI：/agent-infra:analyze-task {task-id}
-  - Codex CLI：$analyze-task {task-id}
+Next step:
+  - Claude Code / OpenCode: /analyze-task {task-id}
+  - Gemini CLI: /{{project}}:analyze-task {task-id}
+  - Codex CLI: $analyze-task {task-id}
 ```
 
-## 注意事项
+## Notes
 
-1. **严重程度优先级**：Critical/High -> 立即处理。Medium -> 计划处理。Low -> 可延后。
-2. **范围**：本技能仅负责导入告警并创建任务；风险评估由 `analyze-task` 负责。
-3. **后续动作**：导入后先执行 `analyze-task`，分析完成后再决定修复或关闭。
+1. **Severity priority**: Critical/High -> handle immediately. Medium -> schedule handling. Low -> can be deferred.
+2. **Scope**: this skill only imports the alert and creates the task; risk assessment is handled by `analyze-task`.
+3. **Follow-up**: after import, run `analyze-task` first, then decide whether to fix or dismiss.
 
-## 完成检查清单
+## Completion Checklist
 
-- [ ] 获取并记录了告警关键信息
-- [ ] 创建或确认了对应的任务目录与任务文件
-- [ ] 更新了 task.md 中的 `current_step` 为 requirement-analysis
-- [ ] 更新了 task.md 中的 `updated_at` 为当前时间
-- [ ] 追加了 Activity Log 条目到 task.md
-- [ ] 告知了用户下一步（必须展示所有 TUI 的命令格式，不要筛选）
+- [ ] Retrieved and recorded the key alert information
+- [ ] Created or confirmed the corresponding task directory and task file
+- [ ] Updated `current_step` to requirement-analysis in task.md
+- [ ] Updated `updated_at` to the current time in task.md
+- [ ] Appended an Activity Log entry to task.md
+- [ ] Informed the user of the next step (must include all TUI command formats; do not filter)
 
-## 错误处理
+## Error Handling
 
-- 告警未找到：提示 "Code Scanning alert #{number} not found"
-- 告警已关闭：询问用户是否继续分析
-- 网络/权限错误：提示相应信息
+- Alert not found: output "Code Scanning alert #{number} not found"
+- Alert already closed: ask the user whether to continue with analysis
+- Network/permission error: output the corresponding error information

package/templates/.agents/skills/import-codescan/SKILL.zh-CN.md

@@ -35,7 +35,7 @@ gh api repos/{owner}/{repo}/code-scanning/alerts/<alert-number>
 
 检查是否已存在该告警的任务。如果不存在，创建：
 
-目录：`.agent-workspace/active/TASK-{yyyyMMdd-HHmmss}/`
+目录：`.agents/workspace/active/TASK-{yyyyMMdd-HHmmss}/`
 
 任务元数据：
 ```yaml

package/templates/.agents/skills/import-dependabot/SKILL.md

@@ -1,44 +1,45 @@
 ---
 name: import-dependabot
 description: >
-  导入 Dependabot 安全告警并创建修复任务。
-  当用户要求导入 Dependabot 告警时触发。参数：告警编号。
+  Import a Dependabot security alert and create a remediation task.
+  Triggered when the user asks to import a Dependabot alert.
+  Argument: alert number.
 ---
 
-# 导入 Dependabot 安全告警
+# Import Dependabot Security Alert
 
-导入指定的 Dependabot 安全告警并创建修复任务。
+Import the specified Dependabot security alert and create a remediation task.
 
-## 行为边界 / 关键规则
+## Boundary / Critical Rules
 
-- 本技能仅负责导入告警并创建任务骨架 —— 不直接修改业务代码或关闭告警
-- 不要自动提交。绝不自动执行 `git commit` 或 `git add`
-- 执行本技能后，你**必须**立即更新 task.md 中的任务状态
+- This skill only imports the alert and creates a task skeleton; it does not directly modify business code or dismiss the alert
+- Do NOT auto-commit. Never execute `git commit` or `git add` automatically
+- After executing this skill, you **must** immediately update task status in task.md
 
-## 执行流程
+## Execution Flow
 
-### 1. 获取告警信息
+### 1. Retrieve Alert Information
 
 ```bash
 gh api repos/{owner}/{repo}/dependabot/alerts/<alert-number>
 ```
 
-提取关键信息：
-- `number`：告警编号
-- `state`：状态（open/dismissed/fixed）
-- `security_advisory`：安全公告详情（ghsa_id、cve_id、severity、summary、description）
-- `dependency`：受影响的依赖（包名、生态系统、清单路径）
-- `security_vulnerability`：受影响版本范围、首个修复版本
+Extract key information:
+- `number`: alert number
+- `state`: state (`open` / `dismissed` / `fixed`)
+- `security_advisory`: advisory details (`ghsa_id`, `cve_id`, `severity`, `summary`, `description`)
+- `dependency`: affected dependency (package name, ecosystem, manifest path)
+- `security_vulnerability`: affected version range and first patched version
 
-### 2. 创建任务目录和文件
+### 2. Create the Task Directory and File
 
-检查 `.agent-workspace/active/` 中是否已存在该告警的任务。
-- 如果找到，询问用户是否重新导入
-- 如果未找到，创建新任务
+Check whether `.agents/workspace/active/` already has a task for this alert.
+- If found, ask the user whether to re-import
+- If not found, create a new task
 
-创建目录：`.agent-workspace/active/TASK-{yyyyMMdd-HHmmss}/`
+Create directory: `.agents/workspace/active/TASK-{yyyyMMdd-HHmmss}/`
 
-任务元数据需包含：
+Task metadata must include:
 ```yaml
 id: TASK-{yyyyMMdd-HHmmss}
 security_alert_number: <alert-number>
@@ -47,61 +48,61 @@ cve_id: <CVE-ID>
 ghsa_id: <GHSA-ID>
 ```
 
-### 3. 更新任务状态
+### 3. Update Task Status
 
-获取当前时间：
+Get the current time:
 
 ```bash
 date "+%Y-%m-%d %H:%M:%S"
 ```
 
-更新 task.md：`current_step` -> `requirement-analysis`。
-- **追加**到 `## Activity Log`（不要覆盖之前的记录）：
+Update task.md: `current_step` -> `requirement-analysis`.
+- **Append** to `## Activity Log` (do NOT overwrite previous entries):
   ```
   - {yyyy-MM-dd HH:mm:ss} — **Import Dependabot Alert** by {agent} — Dependabot alert #{alert-number} imported
   ```
 
-### 4. 告知用户
+### 4. Inform User
 
-> **重要**：以下「下一步」中列出的所有 TUI 命令格式必须完整输出，不要只展示当前 AI 代理对应的格式。
+> **IMPORTANT**: All TUI command formats listed below must be output in full. Do not show only the format for the current AI agent.
 
 ```
-安全告警 #{alert-number} 已导入。
+Security alert #{alert-number} imported.
 
-漏洞信息：
-- 严重程度：{severity}
-- CVE/GHSA：{cve-id} / {ghsa-id}
-- 受影响包：{package-name}
+Vulnerability information:
+- Severity: {severity}
+- CVE/GHSA: {cve-id} / {ghsa-id}
+- Affected package: {package-name}
 
-任务信息：
-- 任务 ID：{task-id}
+Task information:
+- Task ID: {task-id}
 
-产出文件：
-- 任务文件：.agent-workspace/active/{task-id}/task.md
+Output file:
+- Task file: .agents/workspace/active/{task-id}/task.md
 
-下一步：
-  - Claude Code / OpenCode：/analyze-task {task-id}
-  - Gemini CLI：/agent-infra:analyze-task {task-id}
-  - Codex CLI：$analyze-task {task-id}
+Next step:
+  - Claude Code / OpenCode: /analyze-task {task-id}
+  - Gemini CLI: /{{project}}:analyze-task {task-id}
+  - Codex CLI: $analyze-task {task-id}
 ```
 
-## 注意事项
+## Notes
 
-1. **严重程度优先级**：Critical/High -> 立即处理。Medium -> 计划处理。Low -> 可延后。
-2. **范围**：本技能仅负责导入告警并创建任务；风险评估由 `analyze-task` 负责。
-3. **后续动作**：导入后先执行 `analyze-task`，分析完成后再决定修复或关闭。
+1. **Severity priority**: Critical/High -> handle immediately. Medium -> schedule handling. Low -> can be deferred.
+2. **Scope**: this skill only imports the alert and creates the task; risk assessment is handled by `analyze-task`.
+3. **Follow-up**: after import, run `analyze-task` first, then decide whether to fix or dismiss.
 
-## 完成检查清单
+## Completion Checklist
 
-- [ ] 获取并记录了告警关键信息
-- [ ] 创建或确认了对应的任务目录与任务文件
-- [ ] 更新了 task.md 中的 `current_step` 为 requirement-analysis
-- [ ] 更新了 task.md 中的 `updated_at` 为当前时间
-- [ ] 追加了 Activity Log 条目到 task.md
-- [ ] 告知了用户下一步（必须展示所有 TUI 的命令格式，不要筛选）
+- [ ] Retrieved and recorded the key alert information
+- [ ] Created or confirmed the corresponding task directory and task file
+- [ ] Updated `current_step` to requirement-analysis in task.md
+- [ ] Updated `updated_at` to the current time in task.md
+- [ ] Appended an Activity Log entry to task.md
+- [ ] Informed the user of the next step (must include all TUI command formats; do not filter)
 
-## 错误处理
+## Error Handling
 
-- 告警未找到：提示 "Security alert #{number} not found"
-- 告警已关闭：询问用户是否继续分析
-- 网络/权限错误：提示相应信息
+- Alert not found: output "Security alert #{number} not found"
+- Alert already closed: ask the user whether to continue with analysis
+- Network/permission error: output the corresponding error information

package/templates/.agents/skills/import-dependabot/SKILL.zh-CN.md

@@ -32,11 +32,11 @@ gh api repos/{owner}/{repo}/dependabot/alerts/<alert-number>
 
 ### 2. 创建任务目录和文件
 
-检查 `.agent-workspace/active/` 中是否已存在该告警的任务。
+检查 `.agents/workspace/active/` 中是否已存在该告警的任务。
 - 如果找到，询问用户是否重新导入
 - 如果未找到，创建新任务
 
-创建目录：`.agent-workspace/active/TASK-{yyyyMMdd-HHmmss}/`
+创建目录：`.agents/workspace/active/TASK-{yyyyMMdd-HHmmss}/`
 
 任务元数据需包含：
 ```yaml
@@ -77,7 +77,7 @@ date "+%Y-%m-%d %H:%M:%S"
 - 任务 ID：{task-id}
 
 产出文件：
-- 任务文件：.agent-workspace/active/{task-id}/task.md
+- 任务文件：.agents/workspace/active/{task-id}/task.md
 
 下一步：
   - Claude Code / OpenCode：/analyze-task {task-id}