@fitlab-ai/agent-infra 0.5.6 → 0.5.8

package/templates/.agents/skills/create-pr/reference/pr-body-template.zh-CN.md

@@ -1,20 +1,16 @@
 # PR 正文模板规则
 
-在生成 PR 标题和正文之前先读取本文件。
+生成 PR 标题和正文前先读取本文件。
 
 ## 读取 PR 模板
 
-读取仓库中的 `.github/PULL_REQUEST_TEMPLATE.md`。如果不存在，则使用标准格式。
+PR 模板发现属于平台相关逻辑。先读取 `.agents/rules/issue-pr-commands.md`，并按当前配置平台提供的 PR 模板章节执行。如果没有可用模板，则使用标准格式。
 
 ## 参考最近合并的 PR
 
-```bash
-gh pr list --limit 3 --state merged --json number,title,body
-```
+使用 `.agents/rules/issue-pr-commands.md` 中的最近合并 PR 查询命令，作为风格和格式参考输入。
 
-把最近合并的 PR 当作风格和排版参考。
-
-## 分析当前分支变更
+## 分析当前分支改动
 
 ```bash
 git status
@@ -25,21 +21,15 @@ git diff <target-branch>...HEAD
 
 ## 同步 PR 元数据
 
-执行前先读取 `.agents/rules/issue-pr-commands.md`。
-
-同步关联 Issue 元数据前，先按该规则完成认证和代码托管平台检测；`gh pr list` / `gh pr create` 仍保持作用于当前仓库。
+执行本步骤前先读取 `.agents/rules/issue-pr-commands.md`。
 
-在同步 label 之前，先确认标准 label 体系已经存在：
-
-```bash
-gh label list --search "type:" --limit 1 --json name --jq 'length'
-```
+同步关联 Issue 元数据前，先按该规则完成认证和代码托管平台检测。
 
-如果结果是 `0`，先执行 `init-labels`，再重试元数据同步。
+同步 label 前，按 `.agents/rules/issue-pr-commands.md` 中的 label 列表命令验证标准 label 体系。如果结果显示没有标准 type label，先运行 `init-labels` 再重试元数据同步。
 
-Type label 映射：
+类型 label 映射：
 
-| task.md type | GitHub label |
+| task.md type | label |
 |---|---|
 | `bug`, `bugfix` | `type: bug` |
 | `feature` | `type: feature` |
@@ -51,34 +41,34 @@ Type label 映射：
 | 其他值 | 跳过 |
 
 元数据同步顺序：
-1. 按 `.agents/rules/issue-pr-commands.md` 的 Issue 读取命令查询关联 Issue 的 labels 和 milestone
-2. 构建 `{label-args}`：包含映射后的 type label、非 `type:`/`status:` 的 Issue labels，以及 Issue 当前的 `in:` labels（commit 阶段已完成计算，此处不重新计算也不反向更新 Issue）
-3. 构建 `{milestone-arg}`：按 `.agents/rules/milestone-inference.md` 的「阶段 3：`create-pr`」直接复用 Issue milestone
-4. 按 `.agents/rules/issue-pr-commands.md` 的创建 PR 命令模板与权限降级规则，将 `{label-args}` 和 `{milestone-arg}` 原子化传入 `gh pr create`
-5. 确保 PR 正文包含 `Closes #{issue-number}` 或等价的 closing keyword
+1. 通过 `.agents/rules/issue-pr-commands.md` 的 Issue 读取命令查询 Issue labels 和 milestone
+2. 从映射出的 type label、非 `type:` / 非 `status:` 的 Issue labels，以及当前 Issue `in:` labels 构建 `{label-args}`（commit 已经计算过，不在此重算，也不写回 Issue）
+3. 按 `.agents/rules/milestone-inference.md` 的 "阶段 3：`create-pr`" 复用 Issue milestone 构建 `{milestone-arg}`
+4. 按 `.agents/rules/issue-pr-commands.md` 的创建 PR 命令模板与权限降级规则，将 `{label-args}` 和 `{milestone-arg}` 原子化传入
+5. 确保 PR 正文包含 `Closes #{issue-number}` 或等价关闭关键字
 
-如果上述规则判定应跳过直接元数据参数写入，则只保留 PR 正文中的关联信息与后续评论同步。
+如果规则要求跳过上述直接元数据参数，则只保留 PR 正文关联和后续评论同步。
 
 Milestone 规则：
-- 按 `.agents/rules/milestone-inference.md` 的「阶段 3：`create-pr`」处理
-- PR 直接复用 Issue milestone，不再独立推断
+- 按 `.agents/rules/milestone-inference.md` 的 "阶段 3：`create-pr`" 执行
+- 直接复用关联 Issue 的 milestone，不为 PR 重新推断
 
 ## 创建 PR
 
-- 当当前工作属于活动任务时，从 task.md 中提取 `issue_number`
-- 如果存在 `issue_number`，先完成前置步骤中的代码托管平台检测，再按 `.agents/rules/issue-pr-commands.md` 的 Issue 读取命令查询对应 Issue
-- 在调用 PR 创建命令前，先检查当前分支是否已经存在 PR；如果已存在，直接告知用户 PR URL 和状态并结束，不要重复同步元数据或摘要
-- 使用 HEREDOC 传递 PR 正文
-- 如果模板中存在 `{$IssueNumber}`，替换它
-- PR 正文结尾必须带上 `Generated with AI assistance`
+- 当前工作属于 active task 时，从 task.md 提取 `issue_number`
+- 如果存在 `issue_number`，先完成代码托管平台检测，再通过 `.agents/rules/issue-pr-commands.md` 查询 Issue
+- 调用 PR 创建命令前，先检查当前分支是否已有 PR；若已有，报告 PR URL 和状态后停止，不重复执行元数据同步或 summary 发布
+- 使用 HEREDOC 传入 PR 正文
+- 模板中存在 `{$IssueNumber}` 时进行替换
+- PR 正文以 `Generated with AI assistance` 结尾
 
-创建 PR 时，使用 `.agents/rules/issue-pr-commands.md` 中的 “创建 PR” 命令模板。
+使用 `.agents/rules/issue-pr-commands.md` 中的创建 PR 命令模板创建 PR。
 
-最终用户输出必须按顺序包含以下后续动作：
+最终用户输出应包含以下后续路径：
 
 ```text
-下一步：
-  - 工作流真正结束后完成任务：
+Next steps:
+  - complete the task after the workflow truly finishes:
     - Claude Code / OpenCode: /complete-task {task-id}
     - Gemini CLI: /agent-infra:complete-task {task-id}
     - Codex CLI: $complete-task {task-id}

package/templates/.agents/skills/create-release-note/SKILL.en.md

@@ -119,7 +119,7 @@ If no historical release notes exist, use the following default Markdown format:
 
 ## Contributors
 
-@contributor1, @contributor2, @contributor3
+@contributor1, @contributor2, @contributor3, @reporter1 (reported #N)
 ```
 
 **Format rules**:
@@ -128,19 +128,26 @@ If no historical release notes exist, use the following default Markdown format:
 3. Description: Use PR title, remove `type(scope):` prefix, capitalize first letter
 4. **Contributor collection**:
    - **Data sources**:
-     - PR authors from Step 4 `gh pr list --json author`
+     - PR authors returned by the merged-PR query rule in `.agents/rules/release-commands.md`
      - Commit co-authors from Step 4 `git log ... --format='%(trailers:key=Co-authored-by,valueonly,unfold)'`
+     - Issue reporters from linked Issues collected in Step 5 (author login returned by `.agents/rules/release-commands.md`)
    - **Contribution count**: `PR count + co-authored commit count` for the same identity, merged across both sources
    - **Name -> `@login` mapping**:
-     - Raw `Co-authored-by` values are `Name <email>` and must be mapped to a GitHub `@login`
-     - Prefer email extraction: if it matches `(\d+\+)?(\S+?)@users\.noreply\.github\.com`, use the second capture group lowercased; this regex covers both `{id}+{login}@users.noreply.github.com` and `{login}@users.noreply.github.com`
+     - Raw `Co-authored-by` values are `Name <email>` and must be mapped to a platform `@login`
+     - Prefer email extraction: if it matches the platform no-reply email rule in `.agents/rules/release-commands.md`, use that rule to derive the lowercased login
      - Otherwise use a Name heuristic: take the first token before a space and lowercase it, for example `Claude Opus 4.6 (1M context)` -> `@claude`, `Codex` -> `@codex`, `Gemini` -> `@gemini`
      - If the login already appears in the PR author list, merge counts into that login so `Claude` and `@claude` do not become separate entries
      - Merge all Name variants that map to the same login before counting and sorting; for example, `Claude` and `Claude Opus 4.6 (1M context)` should both collapse into `@claude`
      - Preserve bot identities as-is, for example `dependabot[bot]`
-     - If the login still cannot be determined reliably, output `@{lowercased first Name token}` and append `<!-- TODO(reviewer): confirm GitHub login for {original Name <email>} -->` below the `Contributors` section
+     - If the login still cannot be determined reliably, output `@{lowercased first Name token}` and append `<!-- TODO(reviewer): confirm platform login for {original Name <email>} -->` below the `Contributors` section
    - **Sorting**: descending by contribution count, then lexicographically by login for ties
    - **Deduplication**: use the final mapped `@login` as the key
+   - **Issue reporter rules**:
+     - Extract `author.login` from each linked Issue collected in Step 5
+     - If the login already exists in the final mapped PR author or co-author list, skip it (code contribution already covers this user)
+     - Reporter-only contributors use the format `@login (reported #N)`; if the same reporter reported multiple Issues, use `@login (reported #N1, #N2)`
+     - Reporters are appended after code contributors in the Contributors section, separated by commas
+     - Sort reporters by reported Issue count descending, then lexicographically by login for ties
 5. Empty sections: Omit sections with no entries
 
 ### 8. Present and Confirm
@@ -149,7 +156,7 @@ Show the generated release notes to the user.
 
 Ask:
 1. Need any adjustments?
-2. Create a GitHub Draft Release?
+2. Create a draft release?
 
 ### 9. Create Draft Release (If Confirmed)
 
@@ -163,7 +170,7 @@ Draft Release created.
 - Version: v{version}
 - Status: Draft
 
-Please review and publish on GitHub:
+Please review and publish on the platform:
 1. Open the URL above
 2. Review the release notes
 3. Click "Publish release"
@@ -171,7 +178,7 @@ Please review and publish on GitHub:
 
 ## Notes
 
-1. **Requires gh CLI**: Must have GitHub CLI installed and authenticated
+1. **Requires the platform CLI**: Must have the platform CLI installed and authenticated
 2. **Tags must exist**: Run the release skill first to create tags
 3. **Draft mode**: Creates a draft - won't auto-publish
 4. **Classification accuracy**: Auto-classification is based on title/scope/files; complex PRs may need manual adjustment
@@ -180,5 +187,5 @@ Please review and publish on GitHub:
 
 - Invalid version format: Prompt correct format
 - Tag not found: Suggest running the release skill first
-- gh not authenticated: Prompt to authenticate
+- The platform CLI is not authenticated: Prompt to authenticate
 - No merged PRs found: Prompt to check tags and branch

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

@@ -119,7 +119,7 @@ git log v<prev-version>..v<version> \
 
 ## Contributors
 
-@contributor1, @contributor2, @contributor3
+@contributor1, @contributor2, @contributor3, @reporter1 (reported #N)
 ```
 
 **格式规则**：
@@ -128,19 +128,26 @@ git log v<prev-version>..v<version> \
 3. 描述：使用 PR 标题，移除 `type(scope):` 前缀，首字母大写
 4. **贡献者搜集**：
    - **数据源**：
-     - PR author：来自步骤 4 的 `gh pr list --json author`
+     - PR author：来自 `.agents/rules/release-commands.md` 中已合并 PR 查询规则
      - Commit co-authors：来自步骤 4 的 `git log ... --format='%(trailers:key=Co-authored-by,valueonly,unfold)'`
+     - Issue reporters：来自步骤 5 收集的关联 Issue author（由 `.agents/rules/release-commands.md` 返回）
    - **贡献数定义**：`该人的 PR 数 + 该人作为 co-author 的 commit 数`（同一身份跨来源合并计数）
    - **Name → `@login` 映射**：
-     - `Co-authored-by` 原始格式为 `Name <email>`，需要推断对应的 GitHub `@login`
-     - 优先从 email 提取：匹配 `(\d+\+)?(\S+?)@users\.noreply\.github\.com` 时，取第二个捕获组并转为小写；该正则同时覆盖 `{id}+{login}@users.noreply.github.com` 与 `{login}@users.noreply.github.com`
+     - `Co-authored-by` 原始格式为 `Name <email>`，需要推断对应的 platform `@login`
+     - 优先从 email 提取：匹配 `.agents/rules/release-commands.md` 中的平台 no-reply 邮箱规则时，按该规则推导小写 login
      - 否则按 Name 启发式：取首个空格前的 token 并转为小写（例如 `Claude Opus 4.6 (1M context)` → `@claude`、`Codex` → `@codex`、`Gemini` → `@gemini`）
      - 已出现在 PR author 列表中的 login，必须按该 login 合并计数，避免把 `Claude` 和 `@claude` 拆成两个条目
      - 同一 login 的所有 Name 变体都必须归并后再计数与排序；例如 `Claude` 与 `Claude Opus 4.6 (1M context)` 都映射到 `@claude` 时，应先合并为同一个贡献者
      - Bot 身份保留原样（如 `dependabot[bot]`）
-     - 若仍无法可靠确定 login，则输出 `@{Name 首 token 小写}`，并在 `Contributors` 段落下追加 `<!-- TODO(reviewer): 确认 {原始 Name <email>} 的 GitHub login -->`
+     - 若仍无法可靠确定 login，则输出 `@{Name 首 token 小写}`，并在 `Contributors` 段落下追加 `<!-- TODO(reviewer): 确认 {原始 Name <email>} 的 platform login -->`
    - **排序**：按贡献数降序；贡献数相同时按 login 字典序
    - **去重**：以最终映射后的 `@login` 为键
+   - **Issue reporter 规则**：
+     - 从步骤 5 收集到的每个关联 Issue 中提取 `author.login`
+     - 如果该 login 已存在于 PR author 或 co-author 的最终映射列表中，跳过（代码贡献已包含该用户）
+     - 仅报告贡献的用户以 `@login (reported #N)` 格式展示；同一 reporter 报告多个 Issue 时使用 `@login (reported #N1, #N2)`
+     - Reporter 在 Contributors 段落中排在代码贡献者之后，以逗号分隔追加
+     - Reporter 之间按报告的 Issue 数量降序排列，数量相同时按 login 字典序
 5. 空部分：省略没有条目的部分
 
 ### 8. 展示并确认
@@ -149,7 +156,7 @@ git log v<prev-version>..v<version> \
 
 询问：
 1. 需要调整吗？
-2. 是否创建 GitHub Draft Release？
+2. 是否创建 draft release？
 
 ### 9. 创建 Draft Release（如确认）
 
@@ -163,7 +170,7 @@ Draft Release created.
 - Version: v{version}
 - Status: Draft
 
-Please review and publish on GitHub:
+Please review and publish on the platform:
 1. Open the URL above
 2. Review the release notes
 3. Click "Publish release"
@@ -171,7 +178,7 @@ Please review and publish on GitHub:
 
 ## 注意事项
 
-1. **需要 gh CLI**：必须安装并认证 GitHub CLI
+1. **需要 the platform CLI**：必须安装并认证 the platform CLI
 2. **标签必须存在**：先执行 release 技能创建标签
 3. **草稿模式**：创建草稿 —— 不会自动发布
 4. **分类准确性**：自动分类基于标题/scope/文件；复杂的 PR 可能需要手动调整
@@ -180,5 +187,5 @@ Please review and publish on GitHub:
 
 - 版本格式无效：提示正确格式
 - 标签未找到：建议先执行 release 技能
-- gh 未认证：提示进行认证
+- 平台 CLI 未认证：提示用户认证
 - 未找到已合并的 PR：提示检查标签和分支

package/templates/.agents/skills/create-task/SKILL.en.md

@@ -117,7 +117,7 @@ Keep the gate output in your reply as fresh evidence. Do not claim completion wi
 
 > Execute this step only after the verification gate passes.
 
-> **IMPORTANT**: All TUI command formats listed below must be output in full. Do not show only the format for the current AI agent.
+> **IMPORTANT**: All TUI command formats listed below must be output in full. Do not show only the format for the current AI agent. If `.agents/.airc.json` configures custom TUIs (via `customTUIs`), read each tool's `name` and `invoke`, then add the matching command line in the same format (`${skillName}` becomes the skill name and `${projectName}` becomes the project name).
 
 Output format:
 ```
@@ -137,7 +137,7 @@ Next step - run requirements analysis:
   - Gemini CLI: /{{project}}:analyze-task {task-id}
   - Codex CLI: $analyze-task {task-id}
 
-Or create a GitHub Issue first:
+Or create an Issue first:
   - Claude Code / OpenCode: /create-issue {task-id}
   - Gemini CLI: /{{project}}:create-issue {task-id}
   - Codex CLI: $create-issue {task-id}
@@ -150,7 +150,7 @@ Or create a GitHub Issue first:
 - [ ] Updated `updated_at` to the current time in task.md
 - [ ] Updated `assigned_to` 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)
+- [ ] Informed the user of the next step (must include all TUI command formats, including any custom TUIs; do not filter)
 - [ ] **Did not modify any business code or configuration files** (only task.md)
 
 ## STOP
@@ -161,8 +161,8 @@ Wait for the user to run the `analyze-task` skill.
 ## Notes
 
 1. **Clarity**: if the user description is vague or missing key information, ask for clarification first
-2. **Difference from `import-issue`**: `import-issue` imports from a GitHub Issue; `create-task` creates from a free-form description
-3. **Workflow order**: after creating a task, typically run `analyze-task` before `plan-task`; if you need GitHub tracking first, you may run `create-issue` first
+2. **Difference from `import-issue`**: `import-issue` imports from an Issue; `create-task` creates from a free-form description
+3. **Workflow order**: after creating a task, typically run `analyze-task` before `plan-task`; if you need platform tracking first, you may run `create-issue` first
 
 ## Error Handling
 

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

@@ -117,7 +117,7 @@ node .agents/scripts/validate-artifact.js gate create-task .agents/workspace/act
 
 > 仅在校验通过后执行本步骤。
 
-> **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。
+> **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。如果 `.agents/.airc.json` 中配置了自定义 TUI（`customTUIs`），读取每个工具的 `name` 和 `invoke`，按同样格式补充对应命令行（`${skillName}` 替换为技能名，`${projectName}` 替换为项目名）。
 
 输出格式：
 ```
@@ -137,7 +137,7 @@ node .agents/scripts/validate-artifact.js gate create-task .agents/workspace/act
   - Gemini CLI：/agent-infra:analyze-task {task-id}
   - Codex CLI：$analyze-task {task-id}
 
-或先创建 GitHub Issue：
+或先创建 Issue：
   - Claude Code / OpenCode：/create-issue {task-id}
   - Gemini CLI：/agent-infra:create-issue {task-id}
   - Codex CLI：$create-issue {task-id}
@@ -150,7 +150,7 @@ node .agents/scripts/validate-artifact.js gate create-task .agents/workspace/act
 - [ ] 更新了 task.md 中的 `updated_at` 为当前时间
 - [ ] 更新了 task.md 中的 `assigned_to`
 - [ ] 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）
+- [ ] 告知了用户下一步（必须展示所有 TUI 的命令格式，含自定义 TUI，不要筛选）
 - [ ] **没有修改任何业务代码或配置文件**（仅 task.md）
 
 ## 停止
@@ -161,8 +161,8 @@ node .agents/scripts/validate-artifact.js gate create-task .agents/workspace/act
 ## 注意事项
 
 1. **清晰度**：如果用户描述模糊或缺少关键信息，先要求澄清
-2. **与 import-issue 的区别**：`import-issue` 从 GitHub Issue 导入任务；`create-task` 从自由描述创建
-3. **工作流顺序**：创建任务后，通常先执行 `analyze-task` 再进入 `plan-task`；如需先建立 GitHub 跟踪，也可先执行 `create-issue`
+2. **与 import-issue 的区别**：`import-issue` 从 Issue 导入任务；`create-task` 从自由描述创建
+3. **工作流顺序**：创建任务后，通常先执行 `analyze-task` 再进入 `plan-task`；如需先建立 平台跟踪，也可先执行 `create-issue`
 
 ## 错误处理
 

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

@@ -95,7 +95,7 @@ Update `.agents/workspace/active/{task-id}/task.md`:
 
 If task.md contains a valid `issue_number`, perform these sync actions (skip and continue on any failure; read `.agents/rules/issue-sync.md` first and complete upstream repository detection plus permission detection):
 - Set `status: in-progress` by following issue-sync.md
-- Create or update the `<!-- sync-issue:{task-id}:task -->` comment (follow the task.md comment sync rule in issue-sync.md)
+- Create or update the task comment marker defined in `.agents/rules/issue-sync.md` (follow the task.md comment sync rule in issue-sync.md)
 - Publish the `{implementation-artifact}` comment
 
 ### 10. Verification Gate
@@ -117,7 +117,7 @@ Keep the gate output in your reply as fresh evidence. Do not claim completion wi
 
 > Execute this step only after the verification gate passes.
 
-> **IMPORTANT**: All TUI command formats listed below must be output in full. Do not show only the format for the current AI agent. Use the output template in `reference/output-template.md`.
+> **IMPORTANT**: All TUI command formats listed below must be output in full. Do not show only the format for the current AI agent. If `.agents/.airc.json` configures custom TUIs (via `customTUIs`), read each tool's `name` and `invoke`, then add the matching command line in the same format (`${skillName}` becomes the skill name and `${projectName}` becomes the project name). Use the output template in `reference/output-template.md`.
 
 ## Completion Checklist
 
@@ -125,7 +125,7 @@ Keep the gate output in your reply as fresh evidence. Do not claim completion wi
 - [ ] Created `{implementation-artifact}`
 - [ ] All required tests passed
 - [ ] Updated task.md and appended the Activity Log entry
-- [ ] Included every TUI command format in the user-facing next step
+- [ ] Included every TUI command format, including any custom TUIs, in the user-facing next step
 
 ## STOP
 

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

@@ -95,7 +95,7 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 
 如果 task.md 中存在有效的 `issue_number`，执行以下同步操作（任一失败则跳过并继续；执行前先读取 `.agents/rules/issue-sync.md`，完成 upstream 仓库检测和权限检测）：
 - 按 issue-sync.md 设置 `status: in-progress`
-- 创建或更新 `<!-- sync-issue:{task-id}:task -->` 评论（按 issue-sync.md 的 task.md 评论同步规则）
+- 创建或更新 `.agents/rules/issue-sync.md` 中定义的 task 评论标记（按 issue-sync.md 的 task.md 评论同步规则）
 - 发布 `{implementation-artifact}` 评论
 
 ### 10. 完成校验
@@ -117,7 +117,7 @@ node .agents/scripts/validate-artifact.js gate implement-task .agents/workspace/
 
 > 仅在校验通过后执行本步骤。
 
-> **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。输出格式见 `reference/output-template.md`。
+> **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。如果 `.agents/.airc.json` 中配置了自定义 TUI（`customTUIs`），读取每个工具的 `name` 和 `invoke`，按同样格式补充对应命令行（`${skillName}` 替换为技能名，`${projectName}` 替换为项目名）。输出格式见 `reference/output-template.md`。
 
 ## 完成检查清单
 
@@ -125,7 +125,7 @@ node .agents/scripts/validate-artifact.js gate implement-task .agents/workspace/
 - [ ] 已创建 `{implementation-artifact}`
 - [ ] 所有必需测试通过
 - [ ] 已更新 task.md 并追加 Activity Log
-- [ ] 已向用户展示所有 TUI 格式的下一步命令
+- [ ] 已向用户展示所有 TUI 格式的下一步命令（含自定义 TUI）
 
 ## 停止
 

package/templates/.agents/skills/implement-task/config/verify.json

@@ -36,7 +36,9 @@
       "verify_comment_content": true,
       "verify_task_comment_content": true,
       "verify_issue_type": true,
-      "verify_milestone": true
+      "verify_milestone": true,
+      "expected_status_label_key": "inProgress",
+      "expected_comment_marker_key": "artifact"
     }
   }
 }

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

@@ -25,7 +25,7 @@ Extract key information:
 - `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
+- `html_url`: alert link in the platform
 
 ### 2. Create the Task Directory and File
 
@@ -75,7 +75,7 @@ Keep the gate output in your reply as fresh evidence. Do not claim completion wi
 
 > Execute this step only after the verification gate passes.
 
-> **IMPORTANT**: All TUI command formats listed below must be output in full. Do not show only the format for the current AI agent.
+> **IMPORTANT**: All TUI command formats listed below must be output in full. Do not show only the format for the current AI agent. If `.agents/.airc.json` configures custom TUIs (via `customTUIs`), read each tool's `name` and `invoke`, then add the matching command line in the same format (`${skillName}` becomes the skill name and `${projectName}` becomes the project name).
 
 ```
 Code Scanning alert #{alert-number} imported.
@@ -101,7 +101,7 @@ Next step:
 - [ ] 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)
+- [ ] Informed the user of the next step (must include all TUI command formats, including any custom TUIs; do not filter)
 
 ## Error Handling
 

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

@@ -25,7 +25,7 @@ description: "导入 Code Scanning 告警并创建修复任务"
 - `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
+- `html_url`：平台告警链接
 
 ### 2. 创建任务目录和文件
 
@@ -75,7 +75,7 @@ node .agents/scripts/validate-artifact.js gate import-codescan .agents/workspace
 
 > 仅在校验通过后执行本步骤。
 
-> **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。
+> **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。如果 `.agents/.airc.json` 中配置了自定义 TUI（`customTUIs`），读取每个工具的 `name` 和 `invoke`，按同样格式补充对应命令行（`${skillName}` 替换为技能名，`${projectName}` 替换为项目名）。
 
 ```
 Code Scanning 告警 #{alert-number} 已导入。
@@ -101,7 +101,7 @@ Code Scanning 告警 #{alert-number} 已导入。
 - [ ] 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）
+- [ ] 告知了用户下一步（必须展示所有 TUI 的命令格式，含自定义 TUI，不要筛选）
 
 ## 错误处理
 

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

@@ -76,7 +76,7 @@ Keep the gate output in your reply as fresh evidence. Do not claim completion wi
 
 > Execute this step only after the verification gate passes.
 
-> **IMPORTANT**: All TUI command formats listed below must be output in full. Do not show only the format for the current AI agent.
+> **IMPORTANT**: All TUI command formats listed below must be output in full. Do not show only the format for the current AI agent. If `.agents/.airc.json` configures custom TUIs (via `customTUIs`), read each tool's `name` and `invoke`, then add the matching command line in the same format (`${skillName}` becomes the skill name and `${projectName}` becomes the project name).
 
 ```
 Security alert #{alert-number} imported.
@@ -105,7 +105,7 @@ Next step:
 - [ ] 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)
+- [ ] Informed the user of the next step (must include all TUI command formats, including any custom TUIs; do not filter)
 
 ## Error Handling
 

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

@@ -76,7 +76,7 @@ node .agents/scripts/validate-artifact.js gate import-dependabot .agents/workspa
 
 > 仅在校验通过后执行本步骤。
 
-> **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。
+> **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。如果 `.agents/.airc.json` 中配置了自定义 TUI（`customTUIs`），读取每个工具的 `name` 和 `invoke`，按同样格式补充对应命令行（`${skillName}` 替换为技能名，`${projectName}` 替换为项目名）。
 
 ```
 安全告警 #{alert-number} 已导入。
@@ -105,7 +105,7 @@ node .agents/scripts/validate-artifact.js gate import-dependabot .agents/workspa
 - [ ] 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）
+- [ ] 告知了用户下一步（必须展示所有 TUI 的命令格式，含自定义 TUI，不要筛选）
 
 ## 错误处理
 

package/templates/.agents/skills/import-issue/SKILL.en.md

@@ -1,11 +1,11 @@
 ---
 name: import-issue
-description: "Import a GitHub Issue and create a task"
+description: "Import an Issue and create a task"
 ---
 
 # Import Issue
 
-Import the specified GitHub Issue and create a task. Argument: issue number.
+Import the specified Issue and create a task. Argument: issue number.
 
 ## Boundary / Critical Rules
 
@@ -24,22 +24,46 @@ Use the Issue title as-is for the task title (preserve the Issue's original lang
 
 ### 2. Check for an Existing Task
 
-Search `.agents/workspace/active/` for an existing task linked to this Issue.
+2.1 Search `.agents/workspace/active/` for an existing task linked to this Issue.
 - If found, ask the user whether to re-import or continue with the existing task
-- If not found, create a new task
+- If not found, continue to 2.2
+
+2.2 Scan Issue comments for sync markers and look for a recoverable historical task ID:
+
+If `$upstream_repo` was not set in step 1, omit `--repo`; the script will infer it using the issue-sync.md detection rule.
+
+```bash
+node .agents/scripts/platform-adapters/find-existing-task.js --issue <issue-number> --repo "$upstream_repo" --format json
+```
+
+- Script outputs `found=false`: create a new task through the normal import flow
+- Script outputs `found=true`: reuse `task_id`
+- Script exits 2: treat it as network, authentication, or platform API degradation; show the failure reason from script stderr to the user, then continue with the new-task import flow without blocking
 
 ### 3. Create the Task Directory and File
 
+3.1 Decide the task ID and `created_at`.
+
+| Scenario | Trigger | task ID source | created_at source | User confirmation |
+|---|---|---|---|---|
+| Scenario A | 2.1 finds a local task | Reuse local ID | Preserve local value | Must ask whether to re-import or continue using the existing task |
+| Scenario B | 2.1 no match + 2.2 no candidate | Create with `date +%Y%m%d-%H%M%S` | Current time | Not required |
+| Scenario C | 2.1 no match + 2.2 any candidate | Automatically reuse the earliest candidate ID | Prefer remote frontmatter `created_at`; use current time if missing | Inform only |
+
 ```bash
 date +%Y%m%d-%H%M%S
 ```
 
-- Create the directory: `.agents/workspace/active/TASK-{yyyyMMdd-HHmmss}/`
+3.2 Write the task directory and `task.md`.
+
+- Create the directory: `.agents/workspace/active/{task-id}/`
 - Use the `.agents/templates/task.md` template to create `task.md`
+- For Scenario C, prefer `type`, `workflow`, `branch`, `created_by`, and `milestone` from the remote frontmatter; infer missing or damaged fields from Issue labels and current rules
+- Always write `current_step` as `requirement-analysis`; do not restore the remote original `current_step`
 
 Task metadata:
 ```yaml
-id: TASK-{yyyyMMdd-HHmmss}
+id: {task-id}
 issue_number: <issue-number>
 type: feature|bugfix|refactor|docs|chore
 branch: <project>-<type>-<slug>
@@ -52,6 +76,11 @@ current_step: requirement-analysis
 assigned_to: {current AI agent}
 ```
 
+3.3 Append Activity Log entries.
+
+- Scenario B: append `Import Issue`
+- Scenario C: append `Import Issue (Recovered)` and include the recovered task ID, any recoverable original `current_step`, original `assigned_to`, and that `current_step` was reset to `requirement-analysis`; if some frontmatter fields are missing or damaged, mention the fallback in the same entry
+
 ### 4. Update Task Status
 
 Get the current time:
@@ -69,6 +98,7 @@ Update `.agents/workspace/active/{task-id}/task.md`:
   ```
   - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Import Issue** by {agent} — Issue #{number} imported
   ```
+  If step 3.3 already appended recovery Activity Log entries, do not append a duplicate equivalent entry.
 
 ### 5. Assign the Issue Assignee
 
@@ -79,7 +109,7 @@ If task.md contains a valid `issue_number`, use the Issue update command from `.
 If task.md contains a valid `issue_number`, perform these sync actions (skip and continue on any failure):
 - Read `.agents/rules/issue-sync.md` before syncing, and complete upstream repository detection plus permission detection
 - Check the Issue's current milestone; if it is unset, read `.agents/rules/milestone-inference.md` and infer plus set the milestone using "Stage 1: `create-issue`". If `has_triage=false` or the inference is uncertain, skip and continue
-- Create or update the `<!-- sync-issue:{task-id}:task -->` comment (follow the task.md comment sync rule in issue-sync.md)
+- After every scenario, task comment sync is mandatory: create or update the task comment marker defined in `.agents/rules/issue-sync.md` so the remote `:task` comment exists and matches the local `task.md` content (follow the task.md comment sync rule in issue-sync.md)
 
 ### 7. Verification Gate
 
@@ -100,7 +130,7 @@ Keep the gate output in your reply as fresh evidence. Do not claim completion wi
 
 > Execute this step only after the verification gate passes.
 
-> **IMPORTANT**: All TUI command formats listed below must be output in full. Do not show only the format for the current AI agent.
+> **IMPORTANT**: All TUI command formats listed below must be output in full. Do not show only the format for the current AI agent. If `.agents/.airc.json` configures custom TUIs (via `customTUIs`), read each tool's `name` and `invoke`, then add the matching command line in the same format (`${skillName}` becomes the skill name and `${projectName}` becomes the project name).
 
 ```
 Issue #{number} imported.
@@ -126,8 +156,8 @@ Next step - run requirements analysis:
 - [ ] Updated `current_step` to requirement-analysis
 - [ ] Updated `updated_at` to the current time
 - [ ] Appended an Activity Log entry to task.md
-- [ ] Synced the task comment to the Issue
-- [ ] Informed the user of the next step (must include all TUI command formats; do not filter)
+- [ ] Synced the task comment to the Issue, with remote content matching local task.md
+- [ ] Informed the user of the next step (must include all TUI command formats, including any custom TUIs; do not filter)
 - [ ] **Did not modify any business code**
 
 ## STOP
@@ -143,5 +173,5 @@ After completing the checklist, **stop immediately**. Do not continue to later s
 ## Error Handling
 
 - Issue not found: output "Issue #{number} not found, please check the issue number"
-- Network error: output "Cannot connect to GitHub, please check network"
+- Network error: output "Cannot connect to the platform, please check network"
 - Permission error: output "No access to this repository"