@fitlab-ai/agent-infra 0.6.4 → 0.7.0

package/templates/.agents/skills/commit/reference/task-status-update.en.md

@@ -20,9 +20,11 @@ For every task-related commit, append this Activity Log entry in `task.md`:
 
 Before selecting the next step, verify:
 - `current_step` and the latest workflow progress in `task.md`
-- whether the latest `review.md` / `review-r{N}.md` passed without findings
+- whether the latest `review-code.md` / `review-code-r{N}.md` passed without findings
 - whether there are still pending fixes, review work, or PR creation steps
 
+**Gate read (project-level PR flow policy)**: Before running this step, read `.agents/.airc.json`'s `requiresPullRequest` field. Treat missing or `true` as "PR flow enabled" (default); treat explicit `false` as "PR flow disabled". All branches that depend on this field follow the same rule.
+
 Choose exactly one case:
 
 | Decision Basis | Required Case |
@@ -30,17 +32,19 @@ Choose exactly one case:
 | all workflow steps completed + latest review approved with no findings + all tests passed | Case 1: final commit |
 | unfinished steps, pending fixes, or waiting on others still exist | Case 2: more work remains |
 | this commit prepares the task for code review | Case 3: ready for review |
-| code is committed, review is done, and the next step is PR creation | Case 4: ready for PR |
+| code is committed, review is done, **and the project enables the PR flow**, with PR creation as the next step | Case 4: ready for PR |
 
 Never apply more than one case. Match the single next-step branch first, then update the task.
 
+**Gate downgrade**: When `requiresPullRequest === false`, Case 4 must never be entered; commits that would otherwise fall into Case 4 collapse into Case 1 (final commit -> `/complete-task`).
+
 ### Case 1: Final Commit
 
 Prerequisites:
 - [ ] all code committed
 - [ ] all tests passed
 - [ ] code review approved
-- [ ] all workflow steps completed
+- [ ] all workflow steps completed (for the `pr_tasks` list under each yaml `commit` step, count those items toward completion only when `requiresPullRequest !== false`)
 
 Required next-step commands:
 
@@ -71,9 +75,9 @@ Required next-step commands:
 
 ```text
 Next step - code review:
-  - Claude Code / OpenCode: /review-task {task-id}
-  - Gemini CLI: /agent-infra:review-task {task-id}
-  - Codex CLI: $review-task {task-id}
+  - Claude Code / OpenCode: /review-code {task-id}
+  - Gemini CLI: /agent-infra:review-code {task-id}
+  - Codex CLI: $review-code {task-id}
 ```
 
 ### Case 4: Ready for PR

package/templates/.agents/skills/commit/reference/task-status-update.zh-CN.md

@@ -20,9 +20,11 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 
 在决定下一步之前，先确认：
 - `task.md` 中的 `current_step` 和最新工作流进度
-- 最新的 `review.md` / `review-r{N}.md` 是否无问题通过
+- 最新的 `review-code.md` / `review-code-r{N}.md` 是否无问题通过
 - 是否仍然存在待修复项、待审查工作或待创建 PR 的步骤
 
+**门控读取（项目级 PR 流程策略）**：在执行本步骤前，读取 `.agents/.airc.json` 的 `requiresPullRequest` 字段；当字段缺失或为 `true` 时视为「启用 PR 流程」（默认），仅当显式为 `false` 时视为「关闭 PR 流程」。所有依赖该字段的分支按此规则判定。
+
 必须且只能选择一个分支：
 
 | 判断依据 | 必选分支 |
@@ -30,17 +32,19 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 | 所有工作流步骤都已完成 + 最新审查无问题通过 + 所有测试通过 | 场景 1：最终提交 |
 | 仍有未完成步骤、待修复项或等待他人的动作 | 场景 2：还有后续工作 |
 | 这次提交是为了把任务交给代码审查 | 场景 3：准备进入审查 |
-| 代码已提交、审查已完成，下一步是创建 PR | 场景 4：准备创建 PR |
+| 代码已提交、审查已完成，且**项目启用 PR 流程**，下一步是创建 PR | 场景 4：准备创建 PR |
 
 绝对不要同时套用多个分支。先匹配唯一的下一步分支，再更新任务。
 
+**门控降级**：当 `requiresPullRequest === false` 时，场景 4 永远不被进入；原本会落入场景 4 的提交统一收敛到场景 1（最终提交 → `/complete-task`）。
+
 ### 场景 1：最终提交
 
 前置条件：
 - [ ] 所有代码都已提交
 - [ ] 所有测试通过
 - [ ] 代码审查已通过
-- [ ] 所有工作流步骤已完成
+- [ ] 所有工作流步骤已完成（对 yaml `commit` 步骤的 `pr_tasks` 列表，仅在 `requiresPullRequest !== false` 时计入）
 
 必带下一步命令：
 
@@ -71,9 +75,9 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 
 ```text
 下一步 - 代码审查：
-  - Claude Code / OpenCode: /review-task {task-id}
-  - Gemini CLI: /agent-infra:review-task {task-id}
-  - Codex CLI: $review-task {task-id}
+  - Claude Code / OpenCode: /review-code {task-id}
+  - Gemini CLI: /agent-infra:review-code {task-id}
+  - Codex CLI: $review-code {task-id}
 ```
 
 ### 场景 4：准备创建 PR

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

@@ -40,9 +40,11 @@ If not found in `active/`, check `blocked/` and `completed/`:
 
 ### 2. Verify Completion Prerequisites (Failure Must Stop)
 
+**Gate read (project-level PR flow policy)**: Before running this step, read `.agents/.airc.json`'s `requiresPullRequest` field. Treat missing or `true` as "PR flow enabled" (default); treat explicit `false` as "PR flow disabled". The completion check below is pruned accordingly.
+
 Before marking complete, verify ALL of these:
-- [ ] All workflow steps are complete (check workflow progress in task.md)
-- [ ] Code has been reviewed (`review.md` or `review-r{N}.md` exists, and the latest review verdict is Approved; or review was done externally)
+- [ ] All workflow steps are complete (check workflow progress in task.md; **for the `pr_tasks` list under each yaml `commit` step, count those items toward the missing-work decision only when `.agents/.airc.json:requiresPullRequest !== false`**)
+- [ ] Code has been reviewed (`review-code.md` or `review-code-r{N}.md` exists, and the latest review verdict is Approved; or review was done externally)
 - [ ] Code has been committed (no uncommitted changes related to this task)
 - [ ] Tests are passing
 
@@ -109,7 +111,7 @@ Check whether `task.md` includes a valid `issue_number`. If not, skip this step
 > Issue sync rules live in `.agents/rules/issue-sync.md`. Read that file before syncing, and complete upstream repository detection plus permission detection.
 
 If a valid `issue_number` exists:
-- First scan and backfill unpublished `task.md`, `analysis*.md`, `plan*.md`, `implementation*.md`, `review*.md`, and `refinement*.md` comments using the backfill rules in `.agents/rules/issue-sync.md` (`task.md` uses the idempotent update path)
+- First scan and backfill unpublished `task.md`, `analysis*.md`, `review-analysis*.md`, `plan*.md`, `review-plan*.md`, `code*.md`, and `review-code*.md` comments using the backfill rules in `.agents/rules/issue-sync.md` (`task.md` uses the idempotent update path)
 - Backfill checked `## Requirements` items to the Issue body by following the requirements-checkbox sync steps in issue-sync.md
 - Do not set any `status:` label — status labels are automatically cleared when the Issue is closed
 - Finally create or update the summary comment marked with the summary marker defined in `.agents/rules/issue-sync.md`

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

@@ -40,9 +40,11 @@ tail .agents/workspace/active/{task-id}/task.md
 
 ### 2. 验证完成前置条件（未满足则必须停止）
 
+**门控读取（项目级 PR 流程策略）**：在执行本步骤前，读取 `.agents/.airc.json` 的 `requiresPullRequest` 字段；当字段缺失或为 `true` 时视为「启用 PR 流程」（默认），仅当显式为 `false` 时视为「关闭 PR 流程」。下面的工作流步骤完成判定按此规则裁剪。
+
 标记完成之前，验证以下所有条件：
-- [ ] 所有工作流步骤已完成（检查 task.md 中的工作流进度）
-- [ ] 代码已审查（`review.md` 或 `review-r{N}.md` 存在，且最新审查结论为 Approved；或已在外部完成审查）
+- [ ] 所有工作流步骤已完成（检查 task.md 中的工作流进度；**对 yaml 中 commit 步骤的 `pr_tasks` 列表，仅在 `.agents/.airc.json:requiresPullRequest !== false` 时计入未完成判定**）
+- [ ] 代码已审查（`review-code.md` 或 `review-code-r{N}.md` 存在，且最新审查结论为 Approved；或已在外部完成审查）
 - [ ] 代码已提交（没有与此任务相关的未提交变更）
 - [ ] 测试通过
 
@@ -109,7 +111,7 @@ ls .agents/workspace/completed/{task-id}/task.md
 > Issue 同步规则见 `.agents/rules/issue-sync.md`。执行同步前先读取该文件，完成 upstream 仓库检测和权限检测。
 
 如果存在有效的 `issue_number`：
-- 先按 `.agents/rules/issue-sync.md` 的补发规则扫描并补发未发布的 `task.md`、`analysis*.md`、`plan*.md`、`implementation*.md`、`review*.md`、`refinement*.md` 评论（`task.md` 走幂等更新路径）
+- 先按 `.agents/rules/issue-sync.md` 的补发规则扫描并补发未发布的 `task.md`、`analysis*.md`、`review-analysis*.md`、`plan*.md`、`review-plan*.md`、`code*.md`、`review-code*.md` 评论（`task.md` 走幂等更新路径）
 - 按 issue-sync.md 的需求复选框同步步骤，兜底同步 `## 需求` 中已勾选的条目到 Issue body
 - 不要设置 `status:` label — Issue 关闭后 status label 会被自动清除
 - 最后创建或更新 `.agents/rules/issue-sync.md` 中定义的 summary 评论标记对应的 summary 评论

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

@@ -13,6 +13,22 @@ Version stamp rule: when creating or updating `task.md` frontmatter, read `.agen
 
 ## Execution Flow
 
+### Pre-gate: Project-level PR Flow Check
+
+**Gate read (project-level PR flow policy)**: Before running any numbered step, read `.agents/.airc.json`'s `requiresPullRequest` field. Treat missing or `true` as "PR flow enabled" (default); treat explicit `false` as "PR flow disabled".
+
+Branch on the result:
+- missing / `true` -> continue to Step 1 below
+- explicit `false` -> output the message below and **stop immediately**. Do not run any subsequent numbered step, do not trigger any PR-creation command, do not modify `pr_number` in `task.md`, and do not publish a PR summary comment:
+
+```
+This project does not enable the PR flow (`.agents/.airc.json` sets `requiresPullRequest: false`).
+No Pull Request is required; run instead:
+  - Claude Code / OpenCode: /complete-task {task-id}
+  - Gemini CLI: /agent-infra:complete-task {task-id}
+  - Codex CLI: $complete-task {task-id}
+```
+
 ### 1. Parse Command Arguments
 
 Identify arguments from the command input:
@@ -57,7 +73,7 @@ For PRs where `{task-id}` is available, sync the core metadata immediately:
 
 ### 7. Publish the Review Summary
 
-Read the latest context artifacts when they exist: `plan.md` / `plan-r{N}.md`, `implementation.md` / `implementation-r{N}.md`, `review.md` / `review-r{N}.md`, and `refinement.md` / `refinement-r{N}.md`.
+Read the latest context artifacts when they exist: `plan.md` / `plan-r{N}.md`, `review-plan.md` / `review-plan-r{N}.md`, `code.md` / `code-r{N}.md`, and `review-code.md` / `review-code-r{N}.md`.
 
 Aggregate a reviewer-facing summary from those artifacts and maintain a single idempotent summary comment via the hidden marker.
 

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

@@ -13,6 +13,22 @@ description: "创建 Pull Request 到目标分支"
 
 ## 执行流程
 
+### 前置门控：项目级 PR 流程检查
+
+**门控读取（项目级 PR 流程策略）**：在执行编号步骤前，读取 `.agents/.airc.json` 的 `requiresPullRequest` 字段；当字段缺失或为 `true` 时视为「启用 PR 流程」（默认），仅当显式为 `false` 时视为「关闭 PR 流程」。
+
+按读取结果分支：
+- 缺失 / `true` → 继续到下方第 1 步
+- 显式 `false` → 输出以下消息后**立即停止**，不要执行任何后续编号步骤、不要触发任何 PR 创建命令、不要修改 `task.md` 的 `pr_number`、不要发布 PR 摘要评论：
+
+```
+当前项目未启用 PR 流程（`.agents/.airc.json` 中 `requiresPullRequest: false`）。
+无需创建 Pull Request，请直接运行：
+  - Claude Code / OpenCode：/complete-task {task-id}
+  - Gemini CLI：/agent-infra:complete-task {task-id}
+  - Codex CLI：$complete-task {task-id}
+```
+
 ### 1. 解析命令参数
 
 从命令参数中识别：
@@ -57,7 +73,7 @@ description: "创建 Pull Request 到目标分支"
 
 ### 7. 发布审查摘要
 
-读取最新的上下文产物：`plan.md` / `plan-r{N}.md`、`implementation.md` / `implementation-r{N}.md`、`review.md` / `review-r{N}.md`、`refinement.md` / `refinement-r{N}.md`（存在时）。
+读取最新的上下文产物：`plan.md` / `plan-r{N}.md`、`review-plan.md` / `review-plan-r{N}.md`、`code.md` / `code-r{N}.md`、`review-code.md` / `review-code-r{N}.md`（存在时）。
 
 基于这些产物聚合 reviewer 摘要，并使用隐藏标记维护唯一且幂等的摘要评论。
 

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

@@ -106,5 +106,5 @@ Next step:
 ## Error Handling
 
 - Alert not found: output "Code Scanning alert #{number} not found"
-- Alert already closed: ask the user whether to continue with analysis
+- Alert already closed: **proceed with task creation/reuse by default** and surface the alert's current state (dismissed/fixed) in the final notice; the user may archive the task manually if desired
 - Network/permission error: output the corresponding error information

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

@@ -106,5 +106,5 @@ Code Scanning 告警 #{alert-number} 已导入。
 ## 错误处理
 
 - 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
+- 告警已关闭：**默认仍继续创建/复用任务**，并在告知用户中明确该告警当前状态（dismissed/fixed）；用户可视情况手动归档任务
 - 网络/权限错误：提示相应信息

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

@@ -29,7 +29,7 @@ Extract key information:
 ### 2. Create the Task Directory and File
 
 Check whether `.agents/workspace/active/` already has a task for this alert.
-- If found, ask the user whether to re-import
+- If found, **reuse the existing task by default**; do not ask the user. State clearly in the final notice: "Reused existing task `{task-id}`; not re-imported." If the user wants to re-import, they must first archive or delete the existing task
 - If not found, create a new task
 
 Create directory: `.agents/workspace/active/TASK-{yyyyMMdd-HHmmss}/`
@@ -110,5 +110,5 @@ Next step:
 ## Error Handling
 
 - Alert not found: output "Security alert #{number} not found"
-- Alert already closed: ask the user whether to continue with analysis
+- Alert already closed: **proceed with task creation/reuse by default** and surface the alert's current state (dismissed/fixed) in the final notice; the user may archive the task manually if desired
 - Network/permission error: output the corresponding error information

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

@@ -29,7 +29,7 @@ description: "导入 Dependabot 安全告警并创建修复任务"
 ### 2. 创建任务目录和文件
 
 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
+- 如果找到，**默认复用现有任务**，不询问用户；在最终告知中明确「已复用现有任务 `{task-id}`，未重新导入」。如需重新导入，需先归档/删除已有任务
 - 如果未找到，创建新任务
 
 创建目录：`.agents/workspace/active/TASK-{yyyyMMdd-HHmmss}/`
@@ -110,5 +110,5 @@ node .agents/scripts/validate-artifact.js gate import-dependabot .agents/workspa
 ## 错误处理
 
 - 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
+- 告警已关闭：**默认仍继续创建/复用任务**，并在告知用户中明确该告警当前状态（dismissed/fixed）；用户可视情况手动归档任务
 - 网络/权限错误：提示相应信息

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

@@ -25,7 +25,7 @@ Use the Issue title as-is for the task title (preserve the Issue's original lang
 ### 2. Check for an Existing Task
 
 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 found, **reuse the existing task by default** (Scenario A); do not ask the user. State clearly in the final notice: "Reused existing task `{task-id}`; not re-imported." If the user wants to re-import, they must first archive or delete the existing task and run this skill again
 - If not found, continue to 2.2
 
 2.2 Use the "historical task comment scan" command in `.agents/rules/issue-pr-commands.md` to scan Issue comments for sync markers and look for a recoverable historical task ID.
@@ -44,7 +44,7 @@ Exit code handling for the whole pipeline:
 
 | 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 A | 2.1 finds a local task | Reuse local ID | Preserve local value | Reuse by default; do not ask; inform the user reuse happened |
 | 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 |
 
@@ -175,7 +175,7 @@ Version stamp rule: when creating or updating `task.md` frontmatter, read `.agen
 ## Notes
 
 1. **Issue validation**: verify that the Issue exists before continuing
-2. **Duplicate task**: if this Issue already has a linked task, ask the user before creating a new one
+2. **Duplicate task**: if this Issue already has a linked task, **reuse it by default** instead of creating a new one (do not ask the user)
 3. **Next step**: after import, run `analyze-task` before `plan-task`
 
 ## Error Handling

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

@@ -25,7 +25,7 @@ description: "从 Issue 导入并创建任务"
 ### 2. 检查已有任务
 
 2.1 搜索 `.agents/workspace/active/` 中是否已有链接到此 Issue 的任务。
-- 如果找到，询问用户是重新导入还是继续使用现有任务
+- 如果找到，**默认复用现有任务**（场景 A），不询问用户；在最终告知中明确「已复用现有任务 `{task-id}`，未重新导入」。若用户希望重新导入，需要先手动归档/删除已有任务再次执行本技能
 - 如果未找到，继续执行 2.2
 
 2.2 按 `.agents/rules/issue-pr-commands.md` 的“历史任务评论扫描”命令扫描 Issue 评论中的同步标记，查找可恢复的历史任务 ID。
@@ -44,7 +44,7 @@ description: "从 Issue 导入并创建任务"
 
 | 场景 | 触发条件 | task ID 来源 | created_at 来源 | 用户确认 |
 |---|---|---|---|---|
-| 场景 A | 2.1 命中本地任务 | 复用本地 ID | 本地保留 | 必须询问"重新导入还是继续使用现有任务" |
+| 场景 A | 2.1 命中本地任务 | 复用本地 ID | 本地保留 | 默认复用，不询问；告知用户已复用 |
 | 场景 B | 2.1 无命中 + 2.2 无候选 | `date +%Y%m%d-%H%M%S` 新建 | 当前时间 | 不需要 |
 | 场景 C | 2.1 无命中 + 2.2 有候选 | 自动复用最早候选 ID | 优先用远端 frontmatter 的 `created_at`，缺失时用当前时间 | 告知即可 |
 
@@ -175,7 +175,7 @@ Issue #{number} 已导入。
 ## 注意事项
 
 1. **Issue 验证**：在继续之前检查 Issue 是否存在
-2. **重复任务**：如果此 Issue 已有关联任务，在创建新任务前询问用户
+2. **重复任务**：如果此 Issue 已有关联任务，**默认复用**而非创建新任务（不询问用户）
 3. **下一步**：导入完成后，先执行 `analyze-task`，再进入 `plan-task`
 
 ## 错误处理

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

@@ -167,10 +167,10 @@ Output file:
 Important: human review checkpoint.
 Please review the technical plan before continuing to implementation.
 
-Next step - implement the task:
-  - Claude Code / OpenCode: /implement-task {task-id}
-  - Gemini CLI: /{{project}}:implement-task {task-id}
-  - Codex CLI: $implement-task {task-id}
+Next step - review the technical plan:
+  - Claude Code / OpenCode: /review-plan {task-id}
+  - Gemini CLI: /{{project}}:review-plan {task-id}
+  - Codex CLI: $review-plan {task-id}
 ```
 
 ## Completion Checklist

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

@@ -167,10 +167,10 @@ node .agents/scripts/validate-artifact.js gate plan-task .agents/workspace/activ
 重要：人工审查检查点。
 请在继续实现之前审查技术方案。
 
-下一步 - 实施任务：
-  - Claude Code / OpenCode：/implement-task {task-id}
-  - Gemini CLI：/agent-infra:implement-task {task-id}
-  - Codex CLI：$implement-task {task-id}
+下一步 - 审查技术方案：
+  - Claude Code / OpenCode：/review-plan {task-id}
+  - Gemini CLI：/{{project}}:review-plan {task-id}
+  - Codex CLI：$review-plan {task-id}
 ```
 
 ## 完成检查清单

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

@@ -43,10 +43,11 @@ Rules:
 - map `{file-stem}` back to filenames:
   - `task` -> `task.md`
   - `analysis` / `analysis-r{N}` -> matching `.md`
+  - `review-analysis` / `review-analysis-r{N}` -> matching `.md`
   - `plan` / `plan-r{N}` -> matching `.md`
-  - `implementation` / `implementation-r{N}` -> matching `.md`
-  - `review` / `review-r{N}` -> matching `.md`
-  - `refinement` / `refinement-r{N}` -> matching `.md`
+  - `review-plan` / `review-plan-r{N}` -> matching `.md`
+  - `code` / `code-r{N}` -> matching `.md`
+  - `review-code` / `review-code-r{N}` -> matching `.md`
 
 ### 4. Process Chunks and Check the Local Directory
 

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

@@ -43,10 +43,11 @@ description: "从平台 Issue 评论还原本地任务文件"
 - 将 `{file-stem}` 映射回文件名：
   - `task` -> `task.md`
   - `analysis` / `analysis-r{N}` -> 对应 `.md`
+  - `review-analysis` / `review-analysis-r{N}` -> 对应 `.md`
   - `plan` / `plan-r{N}` -> 对应 `.md`
-  - `implementation` / `implementation-r{N}` -> 对应 `.md`
-  - `review` / `review-r{N}` -> 对应 `.md`
-  - `refinement` / `refinement-r{N}` -> 对应 `.md`
+  - `review-plan` / `review-plan-r{N}` -> 对应 `.md`
+  - `code` / `code-r{N}` -> 对应 `.md`
+  - `review-code` / `review-code-r{N}` -> 对应 `.md`
 
 ### 4. 处理分片并检查本地目录
 

package/templates/.agents/skills/review-analysis/SKILL.en.md

@@ -0,0 +1,76 @@
+---
+name: review-analysis
+description: "Review the requirement analysis artifact"
+---
+
+# Requirement Analysis Review
+
+Review the latest analysis artifact and produce `review-analysis.md` or `review-analysis-r{N}.md`.
+
+## Boundary / Critical Rules
+
+- This skill only reviews analysis artifacts and writes a report; it does not modify product code.
+- After executing this skill, you **must** immediately update task.md.
+
+Version stamp rule: when creating or updating `task.md` frontmatter, read `.agents/rules/version-stamp.md` first and write or refresh `agent_infra_version`.
+
+## Step 0: State Check (pre-execution hard gate)
+
+After loading workflow / skill / rules instructions, and before any task-state judgment or user-visible conclusion, run the state check first.
+
+Run these commands and paste the raw output into both the user-facing reply and this round's `## State Check` section:
+
+```bash
+git status -s
+ls -la .agents/workspace/active/{task-id}/
+tail .agents/workspace/active/{task-id}/task.md
+```
+
+## Steps
+
+### 1. Verify Prerequisites
+
+Require `task.md` and at least one analysis artifact: `analysis.md` or `analysis-r{N}.md`.
+
+### 2. Determine Review Round
+
+Record `{analysis-artifact}`, `{review-round}`, and `{review-artifact}` (`review-analysis.md` or `review-analysis-r{N}.md`).
+
+### 3. Read Analysis Context
+
+Read `{analysis-artifact}`, `task.md`, and Issue context when available.
+
+### 4. Perform Review
+
+Check requirement completeness, risks, affected scope, open questions, and effort estimates.
+
+> Read `reference/review-criteria.md` before this step.
+
+### 5. Write Review Report
+
+Create `.agents/workspace/active/{task-id}/{review-artifact}`.
+
+> Read `reference/report-template.md` before writing the report.
+
+### 6. Update Task Status
+
+Get the current time:
+
+```bash
+date "+%Y-%m-%d %H:%M:%S%:z"
+```
+
+Set `current_step` to `requirement-analysis-review`, refresh task metadata, and append:
+`- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Analysis Review (Round {N})** by {agent} — Verdict: {Approved/Changes Requested/Rejected}, blockers: {n}, major: {n}, minor: {n}[ (+ {n} env-blocked)] → {review-artifact}`
+
+If task.md has a valid `issue_number`, read `.agents/rules/issue-sync.md`, sync the task comment, and publish the `{review-artifact}` comment.
+
+### 7. Run Completion Gate
+
+```bash
+node .agents/scripts/validate-artifact.js gate review-analysis .agents/workspace/active/{task-id} {review-artifact} --format text
+```
+
+### 8. Tell the User
+
+Use the conclusion branch in `reference/output-templates.md` and show all TUI command formats.

package/templates/.agents/skills/review-analysis/SKILL.zh-CN.md

@@ -0,0 +1,102 @@
+---
+name: review-analysis
+description: "审查需求分析报告"
+---
+
+# 需求分析审查
+
+审查最新需求分析产物，并产出 `review-analysis.md` 或 `review-analysis-r{N}.md`。
+
+## 行为边界 / 关键规则
+
+- 本技能只审查分析产物并写报告，不修改业务代码
+- 执行本技能后，你**必须**立即更新 task.md
+
+版本戳规则：创建或更新 `task.md` frontmatter 时，先读取 `.agents/rules/version-stamp.md`，并写入或刷新 `agent_infra_version`。
+
+## 第 0 步：状态核对（执行前硬约束）
+
+在加载 workflow / skill / rules 指令之后、做任何任务状态判断或用户可见结论之前，必须先执行状态核对。指令类文件读取不算对外动作或结论。
+
+运行以下命令，并把原文粘贴到回复正文和本轮产物的 `## 状态核对` 段：
+
+```bash
+git status -s
+ls -la .agents/workspace/active/{task-id}/
+tail .agents/workspace/active/{task-id}/task.md
+```
+
+状态核对完成前，禁止任何关于外部状态的断言。
+
+## 执行步骤
+
+### 1. 验证前置条件
+
+要求存在：
+- `.agents/workspace/active/{task-id}/task.md`
+- 至少一个分析产物：`analysis.md` 或 `analysis-r{N}.md`
+
+### 2. 确定审查轮次
+
+扫描任务目录并记录：
+- `{analysis-artifact}`：最高轮次的分析产物
+- `{review-round}`
+- `{review-artifact}`：`review-analysis.md` 或 `review-analysis-r{N}.md`
+
+### 3. 阅读分析上下文
+
+读取最新 `{analysis-artifact}`、`task.md` 和关联 Issue 上下文（如有）。
+
+### 4. 执行审查
+
+重点检查需求完整性、风险识别、影响范围、开放问题和工作量评估。
+
+> 详细审查标准见 `reference/review-criteria.md`。执行此步骤前先读取 `reference/review-criteria.md`。
+
+### 5. 编写审查报告
+
+创建 `.agents/workspace/active/{task-id}/{review-artifact}`。
+
+> 报告格式见 `reference/report-template.md`。写报告前先读取 `reference/report-template.md`。
+
+### 6. 更新任务状态
+
+获取当前时间：
+
+```bash
+date "+%Y-%m-%d %H:%M:%S%:z"
+```
+
+更新 task.md：
+- `current_step`：requirement-analysis-review
+- `assigned_to`：{当前代理}
+- `updated_at`：{当前时间}
+- `agent_infra_version`：按 `.agents/rules/version-stamp.md` 取值
+- 追加：
+  `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Analysis Review (Round {N})** by {agent} — Verdict: {Approved/Changes Requested/Rejected}, blockers: {n}, major: {n}, minor: {n}[ (+ {n} env-blocked)] → {review-artifact}`
+
+如果 task.md 中存在有效的 `issue_number`，执行前先读取 `.agents/rules/issue-sync.md`，完成 upstream 仓库检测和权限检测，然后同步 task 评论并发布 `{review-artifact}` 评论。
+
+### 7. 完成校验
+
+```bash
+node .agents/scripts/validate-artifact.js gate review-analysis .agents/workspace/active/{task-id} {review-artifact} --format text
+```
+
+校验通过后继续告知用户；校验失败则修复报告或 task 状态后重跑。
+
+### 8. 告知用户
+
+按 `reference/output-templates.md` 的结论分支输出，并展示所有 TUI 的下一步命令。
+
+## 完成检查清单
+
+- [ ] 已审查最新分析上下文
+- [ ] 已创建 `{review-artifact}`
+- [ ] 已更新 task.md 并追加 Activity Log
+- [ ] 已展示所有 TUI 的下一步命令
+
+## 注意事项
+
+- 首轮审查使用 `review-analysis.md`，后续轮次使用 `review-analysis-r{N}.md`
+- 所有问题都要引用具体文件路径和行号；分析产物问题可引用 `{analysis-artifact}` 的行号

package/templates/.agents/skills/review-analysis/config/verify.en.json

@@ -0,0 +1,51 @@
+{
+  "skill": "review-analysis",
+  "checks": {
+    "task-meta": {
+      "required_fields": [
+        "id",
+        "type",
+        "workflow",
+        "status",
+        "created_at",
+        "updated_at",
+        "agent_infra_version",
+        "current_step",
+        "assigned_to"
+      ],
+      "expected_step": "requirement-analysis-review"
+    },
+    "artifact": {
+      "file_pattern": "review-analysis.md|review-analysis-r{N}.md",
+      "required_sections": [
+        "Review Summary",
+        "Findings",
+        "Environment-Blocked Findings",
+        "Conclusion and Recommendations",
+        "State Check",
+        "Evidence"
+      ],
+      "required_patterns": [
+        "^### Approval Decision$",
+        "^\\$ "
+      ],
+      "freshness_minutes": 30
+    },
+    "activity-log": {
+      "expected_action_pattern": "Analysis Review \\(Round \\d+\\)",
+      "freshness_minutes": 30
+    },
+    "platform-sync": {
+      "when": "issue_number_exists",
+      "expected_status_label": "status: pending-design-work",
+      "expected_comment_marker": "<!-- sync-issue:{task-id}:{artifact-stem} -->",
+      "verify_comment_content": true,
+      "verify_task_comment_content": true,
+      "verify_issue_type": true,
+      "verify_issue_fields": false,
+      "verify_milestone": true,
+      "expected_status_label_key": "pendingDesignWork",
+      "expected_comment_marker_key": "artifact"
+    }
+  }
+}