@fitlab-ai/agent-infra 0.7.5 → 0.7.7

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

@@ -1,6 +1,8 @@
 ---
 name: release
-description: "执行版本发布流程"
+description: >
+  执行版本发布流程。
+  当准备切出并发布新版本时使用。
 ---
 
 # 版本发布

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

@@ -1,6 +1,8 @@
 ---
 name: restore-task
-description: "Restore local task files from platform Issue comments"
+description: >
+  Restore local task files from platform Issue comments.
+  Use when local task files are missing and need rebuilding from platform Issue comments.
 ---
 
 # Restore Task
@@ -20,6 +22,16 @@ Version stamp rule: when creating or updating `task.md` frontmatter, read `.agen
 
 > If `{task-id}` matches `^[#]?[0-9]+$` (bare numeric or `#`-prefixed), follow the "SKILL parameter resolver" section of `.agents/rules/task-short-id.md`; treat `{task-id}` as the resolved full `TASK-YYYYMMDD-HHMMSS` form for every downstream command.
 
+## Step Start: Write the started Marker
+
+After prerequisites pass and before this step's first artifact action, append a started marker to task.md `## Activity Log` (same base action as this step's done entry plus a ` [started]` suffix, note `started`):
+
+```
+- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Restore Task [started]** by {agent} — started
+```
+
+`ai task log` pairs it with the done entry written on completion onto one row (in progress → done). See the "Activity Log started / done dual-marker convention" in `.agents/rules/task-management.md`.
+
 ## Steps
 
 ### 1. Verify Input and Environment

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

@@ -1,6 +1,8 @@
 ---
 name: restore-task
-description: "从平台 Issue 评论还原本地任务文件"
+description: >
+  从平台 Issue 评论还原本地任务文件。
+  当本地任务文件缺失、需要从平台 Issue 评论还原时使用。
 ---
 
 # 还原任务
@@ -20,6 +22,16 @@ description: "从平台 Issue 评论还原本地任务文件"
 
 > 如果 `{task-id}` 入参匹配 `^[#]?[0-9]+$`（裸数字或带 `#` 前缀），先读取 `.agents/rules/task-short-id.md` 的「SKILL 入参解析」段执行解析；后续命令视 `{task-id}` 为解析后的全长 `TASK-YYYYMMDD-HHMMSS` 形式。
 
+## 步骤开始：写入 started 标记
+
+确认前置条件后、本步骤第一个产出动作之前，向 task.md `## 活动日志` 追加一条 started 标记（与本步骤 done 条目同基名 + ` [started]` 后缀，note 用 `started`）：
+
+```
+- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Restore Task [started]** by {agent} — started
+```
+
+`ai task log` 会把它与完成时写入的 done 条目配对成一行（进行中 → 已完成）。约定见 `.agents/rules/task-management.md` 的「Activity Log started / done 双标记约定」。
+
 ## 执行步骤
 ### 1. 验证输入与环境
 

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

@@ -1,6 +1,8 @@
 ---
 name: review-analysis
-description: "Review the requirement analysis artifact"
+description: >
+  Review the requirement analysis artifact.
+  Use when a requirements analysis needs an independent review before planning.
 ---
 
 # Requirement Analysis Review
@@ -30,6 +32,16 @@ tail .agents/workspace/active/{task-id}/task.md
 
 > If `{task-id}` matches `^[#]?[0-9]+$` (bare numeric or `#`-prefixed), follow the "SKILL parameter resolver" section of `.agents/rules/task-short-id.md`; treat `{task-id}` as the resolved full `TASK-YYYYMMDD-HHMMSS` form for every downstream command.
 
+## Step Start: Write the started Marker
+
+After prerequisites pass and before this round's first artifact action, append a started marker to task.md `## Activity Log` (same base action as this round's done entry plus a ` [started]` suffix, note `started`):
+
+```
+- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Analysis (Round {N}) [started]** by {agent} — started
+```
+
+`ai task log` pairs it with the done entry written when the review completes onto one row (in progress → done). Format and pairing rules: see the "Activity Log started / done dual-marker convention" in `.agents/rules/task-management.md`.
+
 ## Steps
 
 ### 1. Verify Prerequisites
@@ -42,7 +54,7 @@ Record `{analysis-artifact}`, `{review-round}`, and `{review-artifact}` (`review
 
 ### 3. Read Analysis Context
 
-Read `{analysis-artifact}`, `task.md`, and Issue context when available.
+Read `{analysis-artifact}`, `task.md`, and Issue context when available. After reading, record the actually reviewed highest-round analysis artifact by filename in the report's `Review Input` field; leave it blank when it cannot be reliably determined—do not fabricate.
 
 ### 4. Perform Review
 
@@ -67,6 +79,8 @@ 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} — **Review Analysis (Round {N})** by {agent} — Verdict: {Approved/Changes Requested/Rejected}, blockers: {n}, major: {n}, minor: {n}[ (+ {n} env-blocked)] → {review-artifact}`
 
+`env-blocked` is the data source for the `Manual-verify` count folded into review rows in `ai task log`; do not add a parallel manual-verification field.
+
 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

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

@@ -1,6 +1,8 @@
 ---
 name: review-analysis
-description: "审查需求分析报告"
+description: >
+  审查需求分析报告。
+  当需求分析需要在进入方案前接受独立审查时使用。
 ---
 
 # 需求分析审查
@@ -32,6 +34,16 @@ tail .agents/workspace/active/{task-id}/task.md
 
 > 如果 `{task-id}` 入参匹配 `^[#]?[0-9]+$`（裸数字或带 `#` 前缀），先读取 `.agents/rules/task-short-id.md` 的「SKILL 入参解析」段执行解析；后续命令视 `{task-id}` 为解析后的全长 `TASK-YYYYMMDD-HHMMSS` 形式。
 
+## 步骤开始：写入 started 标记
+
+确认前置条件后、本轮第一个产出动作之前，向 task.md `## 活动日志` 追加一条 started 标记（与本轮 done 条目同基名 + ` [started]` 后缀，note 用 `started`）：
+
+```
+- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Analysis (Round {N}) [started]** by {agent} — started
+```
+
+`ai task log` 会把它与审查完成时写入的 done 条目配对成一行（进行中 → 已完成）。格式与配对规则见 `.agents/rules/task-management.md` 的「Activity Log started / done 双标记约定」。
+
 ## 执行步骤
 ### 1. 验证前置条件
 
@@ -48,7 +60,7 @@ tail .agents/workspace/active/{task-id}/task.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）。
+读取最新 `{analysis-artifact}`、`task.md` 和关联 Issue 上下文（如有）。读取后，把本轮实际检视的最高轮 analysis artifact 文件名回填到报告 `审查输入` 段；无法可靠取得时留空，不要伪造。
 
 ### 4. 执行审查
 
@@ -78,6 +90,8 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 - 追加：
   `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Analysis (Round {N})** by {agent} — Verdict: {Approved/Changes Requested/Rejected}, blockers: {n}, major: {n}, minor: {n}[ (+ {n} env-blocked)] → {review-artifact}`
 
+`env-blocked` 是 `ai task log` 中 review 行「人工校验点」（EN `Manual-verify`）计数的数据源；不要新增并行人工验证字段。
+
 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

package/templates/.agents/skills/review-analysis/reference/output-templates.en.md

@@ -16,7 +16,7 @@ Rules:
 - If `Blocker > 0`, never use an approved template
 - Never count env-blocked items as blocker / major / minor or use them to trigger Scenario B/C/D
 - The selected scenario must include all TUI command formats
-- The count line always shows 4 numbers: the first three (Blockers / Major / Minor) must be 0 to proceed; the fourth, `Human-decision` (`{h}`), is the number of rows in task.md `## 审查分歧账本` with `stage=analysis` and `status=needs-human-decision` — a "pending human ruling" item that need not be zero and does not participate in scenario selection
+- The count line always shows 4 numbers: the first three (Blockers / Major / Minor) must be 0 to proceed; the fourth, `Human-decision` (`{h}`), is the number of rows in task.md `## 审查分歧账本` with `stage=analysis` and `status=needs-human-decision` — a "pending human ruling" item that need not be zero and does not participate in scenario selection. When `{h} > 0`, before the selected scenario's "Next steps" commands you must expand each pending ruling per the "Pending human-decision pre-block" in `.agents/rules/next-step-output.md` and prompt to resolve them first
 
 ### Scenario A: Approved with no findings
 

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

@@ -16,7 +16,7 @@
 - 只要 `Blocker > 0`，就绝对不能输出通过模板
 - env-blocked 项绝对不能被计入 blocker / major / minor 计数，也不能用作触发场景 B/C/D 的依据
 - 所选场景中必须包含所有 TUI 命令格式
-- 计数行固定显示 4 个数字：前三项（阻塞 / 主要 / 次要）必须为 0 才进下一步；第四项 `人工裁决`（`{h}`）= task.md `## 审查分歧账本` 中 `stage=analysis` 且 `status=needs-human-decision` 的行数，是「待人裁」项、不要求归零，也不参与场景判断
+- 计数行固定显示 4 个数字：前三项（阻塞 / 主要 / 次要）必须为 0 才进下一步；第四项 `人工裁决`（`{h}`）= task.md `## 审查分歧账本` 中 `stage=analysis` 且 `status=needs-human-decision` 的行数，是「待人裁」项、不要求归零，也不参与场景判断。当 `{h} > 0` 时，必须在选定场景的「下一步」命令之前，按 `.agents/rules/next-step-output.md`「人工裁决待办前置块」逐项展开裁决项并提示先完成裁决
 
 ### 场景 A：通过且无问题
 

package/templates/.agents/skills/review-analysis/reference/report-template.en.md

@@ -10,7 +10,7 @@ Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`
 - **Review Round**: Round {review-round}
 - **Artifact File**: `{review-artifact}`
 - **Review Input**:
-  - `{analysis-artifact}`
+  - `{analysis-artifact}` (the highest-round requirement-analysis artifact actually reviewed, e.g. `analysis-r2.md`; leave blank if it cannot be reliably determined)
 
 ## State Check
 

package/templates/.agents/skills/review-analysis/reference/report-template.zh-CN.md

@@ -10,8 +10,7 @@
 - **审查轮次**：第 {review-round} 轮
 - **产物文件**：`{review-artifact}`
 - **审查输入**：
-  - `{code-artifact}`
-  - `{code-artifact}`（如存在）
+  - `{analysis-artifact}`（本轮实际检视的最高轮需求分析产物，如 `analysis-r2.md`；无法可靠取得则留空）
 
 ## 状态核对
 

package/templates/.agents/skills/review-analysis/reference/review-criteria.en.md

@@ -13,6 +13,7 @@ Follow the `analysis-review` step in `.agents/workflows/feature-development.yaml
 - [ ] Risks, edge cases, and open questions are recorded
 - [ ] The design stage has enough input to proceed
 - [ ] The analysis matches the original Issue or user request
+- [ ] The reviewer checked whether the executor missed any key design decision that should be upgraded to `[needs-human-decision]`
 - [ ] Every blocker is backed by reproducible grep/sed/nl evidence; conclusions not directly verified are declared under Self-Doubt
 
 **Common anti-examples**:

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

@@ -13,6 +13,7 @@
 - [ ] 风险、边界情况和开放问题是否记录
 - [ ] 后续设计阶段是否有足够输入
 - [ ] 与原始 Issue / 用户需求是否一致
+- [ ] 已复核执行方是否漏标应升级为 `[needs-human-decision]` 的关键设计决策
 - [ ] 每条 blocker 都配可复现的 grep/sed/nl 证据，未直接验证的结论已在「自我质疑」声明
 
 **常见反例**：

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

@@ -1,6 +1,8 @@
 ---
 name: review-code
-description: "Review code implementation and output a code review report"
+description: >
+  Review code implementation and output a code review report.
+  Use when a code implementation needs review before merging.
 ---
 
 # Code Review
@@ -41,6 +43,16 @@ Before the state check is complete, do not make external-state assertions such a
 
 > If `{task-id}` matches `^[#]?[0-9]+$` (bare numeric or `#`-prefixed), follow the "SKILL parameter resolver" section of `.agents/rules/task-short-id.md`; treat `{task-id}` as the resolved full `TASK-YYYYMMDD-HHMMSS` form for every downstream command.
 
+## Step Start: Write the started Marker
+
+After prerequisites pass and before this round's first artifact action, append a started marker to task.md `## Activity Log` (same base action as this round's done entry plus a ` [started]` suffix, note `started`):
+
+```
+- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Code (Round {N}) [started]** by {agent} — started
+```
+
+`ai task log` pairs it with the done entry written when the review completes onto one row (in progress → done). Format and pairing rules: see the "Activity Log started / done dual-marker convention" in `.agents/rules/task-management.md`.
+
 ## Steps
 
 ### 1. Verify Prerequisites
@@ -57,7 +69,7 @@ Scan the task directory and record:
 
 ### 3. Read Implementation and Refinement Context
 
-Read the highest-round code artifact and, if present, the highest-round fix artifact.
+Read the highest-round code artifact and, if present, the highest-round fix artifact. After reading, record the actually reviewed highest-round code artifact (and the highest-round fix artifact, if present) by filename in the report's `Review Input` field; leave it blank when it cannot be reliably determined—do not fabricate.
 
 ### 4. Perform the Review
 
@@ -87,6 +99,7 @@ Update task.md and append:
 `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Code (Round {N})** by {agent} — Verdict: {Approved/Changes Requested/Rejected}, blockers: {n}, major: {n}, minor: {n}[ (+ {n} env-blocked)] → {artifact-filename}`
 
 Omit the bracketed segment when env-blocked = 0; append ` (+ {n} env-blocked)` when env-blocked > 0.
+`env-blocked` is the data source for the `Manual-verify` count folded into review rows in `ai task log`; do not add a parallel manual-verification field.
 
 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

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

@@ -1,6 +1,8 @@
 ---
 name: review-code
-description: "审查代码实现并输出代码审查报告"
+description: >
+  审查代码实现并输出代码审查报告。
+  当代码实现需要在合入前接受审查时使用。
 ---
 
 # 代码审查
@@ -41,6 +43,16 @@ tail .agents/workspace/active/{task-id}/task.md
 
 > 如果 `{task-id}` 入参匹配 `^[#]?[0-9]+$`（裸数字或带 `#` 前缀），先读取 `.agents/rules/task-short-id.md` 的「SKILL 入参解析」段执行解析；后续命令视 `{task-id}` 为解析后的全长 `TASK-YYYYMMDD-HHMMSS` 形式。
 
+## 步骤开始：写入 started 标记
+
+确认前置条件后、本轮第一个产出动作之前，向 task.md `## 活动日志` 追加一条 started 标记（与本轮 done 条目同基名 + ` [started]` 后缀，note 用 `started`）：
+
+```
+- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Code (Round {N}) [started]** by {agent} — started
+```
+
+`ai task log` 会把它与审查完成时写入的 done 条目配对成一行（进行中 → 已完成）。格式与配对规则见 `.agents/rules/task-management.md` 的「Activity Log started / done 双标记约定」。
+
 ## 执行步骤
 ### 1. 验证前置条件
 
@@ -56,7 +68,7 @@ tail .agents/workspace/active/{task-id}/task.md
 
 ### 3. 阅读实现与修复上下文
 
-读取最高轮次的实现产物；如存在修复产物，也读取最高轮次的修复产物。
+读取最高轮次的实现产物；如存在修复产物，也读取最高轮次的修复产物。读取后，把本轮实际检视的最高轮 code artifact（及如存在的最高轮修复产物）按文件名回填到报告 `审查输入` 段；无法可靠取得时留空，不要伪造。
 
 ### 4. 执行审查
 
@@ -90,6 +102,7 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Code (Round {N})** by {agent} — Verdict: {Approved/Changes Requested/Rejected}, blockers: {n}, major: {n}, minor: {n}[ (+ {n} env-blocked)] → {artifact-filename}`
 
 env-blocked = 0 时省略括号部分；env-blocked > 0 时附加 ` (+ {n} env-blocked)`。
+`env-blocked` 是 `ai task log` 中 review 行「人工校验点」（EN `Manual-verify`）计数的数据源；不要新增并行人工验证字段。
 
 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

package/templates/.agents/skills/review-code/reference/output-templates.en.md

@@ -18,7 +18,7 @@ Prohibitions:
 - if `Blocker > 0`, never output an approval template
 - never count env-blocked findings as blockers / major issues / minor issues, and never use them to trigger Branch B/C/D
 - always include every TUI command format in the selected branch
-- the count line always shows 5 numbers: the first three (Blockers / Major / Minor) must be 0 to proceed; the last two are "pending human" items and need not be zero — `Manual-verify` (`{e}`) = this round's env-blocked count, `Human-decision` (`{h}`) = the number of rows in task.md `## 审查分歧账本` with `stage=code` and `status=needs-human-decision`; neither participates in branch selection
+- the count line always shows 5 numbers: the first three (Blockers / Major / Minor) must be 0 to proceed; the last two are "pending human" items and need not be zero — `Manual-verify` (`{e}`) = this round's env-blocked count, `Human-decision` (`{h}`) = the number of rows in task.md `## 审查分歧账本` with `stage=code` and `status=needs-human-decision`; neither participates in branch selection. When `{h} > 0`, before the selected scenario's "Next steps" commands you must expand each pending ruling per the "Pending human-decision pre-block" in `.agents/rules/next-step-output.md` and prompt to resolve them first
 
 ### Branch A: Approved with No Findings
 

package/templates/.agents/skills/review-code/reference/output-templates.zh-CN.md

@@ -18,7 +18,7 @@
 - 只要 `Blocker > 0`，就绝对不能输出通过模板
 - env-blocked 项绝对不能被计入 blocker / major / minor 计数，也不能用作触发场景 B/C/D 的依据
 - 所选场景中必须包含所有 TUI 命令格式
-- 计数行固定显示 5 个数字：前三项（阻塞 / 主要 / 次要）必须为 0 才进下一步；后两项是「待人处理」项、不要求归零——`人工校验点`（`{e}`）= 本轮 env-blocked 计数，`人工裁决`（`{h}`）= task.md `## 审查分歧账本` 中 `stage=code` 且 `status=needs-human-decision` 的行数；二者均不参与场景判断
+- 计数行固定显示 5 个数字：前三项（阻塞 / 主要 / 次要）必须为 0 才进下一步；后两项是「待人处理」项、不要求归零——`人工校验点`（`{e}`）= 本轮 env-blocked 计数，`人工裁决`（`{h}`）= task.md `## 审查分歧账本` 中 `stage=code` 且 `status=needs-human-decision` 的行数；二者均不参与场景判断。当 `{h} > 0` 时，必须在选定场景的「下一步」命令之前，按 `.agents/rules/next-step-output.md`「人工裁决待办前置块」逐项展开裁决项并提示先完成裁决
 
 ### 场景 A：通过且无问题
 

package/templates/.agents/skills/review-code/reference/report-template.en.md

@@ -10,7 +10,7 @@ Use this template when writing `review-code.md` or `review-code-r{N}.md`.
 - **Review Round**: Round {review-round}
 - **Artifact File**: `{review-artifact}`
 - **Review Input**:
-  - `{code-artifact}`
+  - `{code-artifact}` (the highest-round implementation artifact actually reviewed—plus the highest-round fix artifact if present, e.g. `code-r2.md`; leave blank if it cannot be reliably determined)
 
 ## State Check
 

package/templates/.agents/skills/review-code/reference/report-template.zh-CN.md

@@ -10,8 +10,7 @@
 - **审查轮次**：第 {review-round} 轮
 - **产物文件**：`{review-artifact}`
 - **审查输入**：
-  - `{code-artifact}`
-  - `{code-artifact}`（如存在）
+  - `{code-artifact}`（本轮实际检视的最高轮实现产物——含如存在的最高轮修复产物，如 `code-r2.md`；无法可靠取得则留空）
 
 ## 状态核对
 

package/templates/.agents/skills/review-code/reference/review-criteria.en.md

@@ -14,6 +14,7 @@ Follow the `code-review` step in `.agents/workflows/feature-development.yaml`.
 - [ ] Performance and security risks
 - [ ] Comments and documentation
 - [ ] Consistency with the approved technical plan
+- [ ] The reviewer checked whether the executor missed any key design decision that should be upgraded to `[needs-human-decision]`
 - [ ] Every blocker is backed by reproducible grep/sed/nl evidence; conclusions not directly verified are declared under Self-Doubt
 
 **Common anti-examples**:

package/templates/.agents/skills/review-code/reference/review-criteria.zh-CN.md

@@ -14,6 +14,7 @@
 - [ ] 性能与安全风险
 - [ ] 代码注释和文档
 - [ ] 与已批准技术方案的一致性
+- [ ] 已复核执行方是否漏标应升级为 `[needs-human-decision]` 的关键设计决策
 - [ ] 每条 blocker 都配可复现的 grep/sed/nl 证据，未直接验证的结论已在「自我质疑」声明
 
 **常见反例**：

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

@@ -1,6 +1,8 @@
 ---
 name: review-plan
-description: "Review the technical plan"
+description: >
+  Review the technical plan.
+  Use when a technical plan needs review before implementation.
 ---
 
 # Technical Plan Review
@@ -30,6 +32,16 @@ tail .agents/workspace/active/{task-id}/task.md
 
 > If `{task-id}` matches `^[#]?[0-9]+$` (bare numeric or `#`-prefixed), follow the "SKILL parameter resolver" section of `.agents/rules/task-short-id.md`; treat `{task-id}` as the resolved full `TASK-YYYYMMDD-HHMMSS` form for every downstream command.
 
+## Step Start: Write the started Marker
+
+After prerequisites pass and before this round's first artifact action, append a started marker to task.md `## Activity Log` (same base action as this round's done entry plus a ` [started]` suffix, note `started`):
+
+```
+- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Plan (Round {N}) [started]** by {agent} — started
+```
+
+`ai task log` pairs it with the done entry written when the review completes onto one row (in progress → done). Format and pairing rules: see the "Activity Log started / done dual-marker convention" in `.agents/rules/task-management.md`.
+
 ## Steps
 
 ### 1. Verify Prerequisites
@@ -42,7 +54,7 @@ Record `{plan-artifact}`, `{review-round}`, and `{review-artifact}` (`review-pla
 
 ### 3. Read Plan Context
 
-Read `{plan-artifact}`, the latest analysis artifact, `task.md`, and Issue context when available.
+Read `{plan-artifact}`, the latest analysis artifact, `task.md`, and Issue context when available. After reading, record the actually reviewed highest-round plan artifact by filename in the report's `Review Input` field; leave it blank when it cannot be reliably determined—do not fabricate.
 
 ### 4. Perform Review
 
@@ -67,6 +79,8 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 Set `current_step` to `technical-design-review`, refresh task metadata, and append:
 `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Plan (Round {N})** by {agent} — Verdict: {Approved/Changes Requested/Rejected}, blockers: {n}, major: {n}, minor: {n}[ (+ {n} env-blocked)] → {review-artifact}`
 
+`env-blocked` is the data source for the `Manual-verify` count folded into review rows in `ai task log`; do not add a parallel manual-verification field.
+
 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

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

@@ -1,6 +1,8 @@
 ---
 name: review-plan
-description: "审查技术方案"
+description: >
+  审查技术方案。
+  当技术方案需要在进入实现前接受审查时使用。
 ---
 
 # 技术方案审查
@@ -32,6 +34,16 @@ tail .agents/workspace/active/{task-id}/task.md
 
 > 如果 `{task-id}` 入参匹配 `^[#]?[0-9]+$`（裸数字或带 `#` 前缀），先读取 `.agents/rules/task-short-id.md` 的「SKILL 入参解析」段执行解析；后续命令视 `{task-id}` 为解析后的全长 `TASK-YYYYMMDD-HHMMSS` 形式。
 
+## 步骤开始：写入 started 标记
+
+确认前置条件后、本轮第一个产出动作之前，向 task.md `## 活动日志` 追加一条 started 标记（与本轮 done 条目同基名 + ` [started]` 后缀，note 用 `started`）：
+
+```
+- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Plan (Round {N}) [started]** by {agent} — started
+```
+
+`ai task log` 会把它与审查完成时写入的 done 条目配对成一行（进行中 → 已完成）。格式与配对规则见 `.agents/rules/task-management.md` 的「Activity Log started / done 双标记约定」。
+
 ## 执行步骤
 ### 1. 验证前置条件
 
@@ -48,7 +60,7 @@ tail .agents/workspace/active/{task-id}/task.md
 
 ### 3. 阅读方案上下文
 
-读取最新 `{plan-artifact}`、最新分析产物、`task.md` 和关联 Issue 上下文（如有）。
+读取最新 `{plan-artifact}`、最新分析产物、`task.md` 和关联 Issue 上下文（如有）。读取后，把本轮实际检视的最高轮 plan artifact 文件名回填到报告 `审查输入` 段；无法可靠取得时留空，不要伪造。
 
 ### 4. 执行审查
 
@@ -78,6 +90,8 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 - 追加：
   `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Review Plan (Round {N})** by {agent} — Verdict: {Approved/Changes Requested/Rejected}, blockers: {n}, major: {n}, minor: {n}[ (+ {n} env-blocked)] → {review-artifact}`
 
+`env-blocked` 是 `ai task log` 中 review 行「人工校验点」（EN `Manual-verify`）计数的数据源；不要新增并行人工验证字段。
+
 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

package/templates/.agents/skills/review-plan/reference/output-templates.en.md

@@ -16,7 +16,7 @@ Rules:
 - If `Blocker > 0`, never use an approved template
 - Never count env-blocked items as blocker / major / minor or use them to trigger Scenario B/C/D
 - The selected scenario must include all TUI command formats
-- The count line always shows 4 numbers: the first three (Blockers / Major / Minor) must be 0 to proceed; the fourth, `Human-decision` (`{h}`), is the number of rows in task.md `## 审查分歧账本` with `stage=plan` and `status=needs-human-decision` — a "pending human ruling" item that need not be zero and does not participate in scenario selection
+- The count line always shows 4 numbers: the first three (Blockers / Major / Minor) must be 0 to proceed; the fourth, `Human-decision` (`{h}`), is the number of rows in task.md `## 审查分歧账本` with `stage=plan` and `status=needs-human-decision` — a "pending human ruling" item that need not be zero and does not participate in scenario selection. When `{h} > 0`, before the selected scenario's "Next steps" commands you must expand each pending ruling per the "Pending human-decision pre-block" in `.agents/rules/next-step-output.md` and prompt to resolve them first
 
 ### Scenario A: Approved with no findings
 

package/templates/.agents/skills/review-plan/reference/output-templates.zh-CN.md

@@ -16,7 +16,7 @@
 - 只要 `Blocker > 0`，就绝对不能输出通过模板
 - env-blocked 项绝对不能被计入 blocker / major / minor 计数，也不能用作触发场景 B/C/D 的依据
 - 所选场景中必须包含所有 TUI 命令格式
-- 计数行固定显示 4 个数字：前三项（阻塞 / 主要 / 次要）必须为 0 才进下一步；第四项 `人工裁决`（`{h}`）= task.md `## 审查分歧账本` 中 `stage=plan` 且 `status=needs-human-decision` 的行数，是「待人裁」项、不要求归零，也不参与场景判断
+- 计数行固定显示 4 个数字：前三项（阻塞 / 主要 / 次要）必须为 0 才进下一步；第四项 `人工裁决`（`{h}`）= task.md `## 审查分歧账本` 中 `stage=plan` 且 `status=needs-human-decision` 的行数，是「待人裁」项、不要求归零，也不参与场景判断。当 `{h} > 0` 时，必须在选定场景的「下一步」命令之前，按 `.agents/rules/next-step-output.md`「人工裁决待办前置块」逐项展开裁决项并提示先完成裁决
 
 ### 场景 A：通过且无问题
 

package/templates/.agents/skills/review-plan/reference/report-template.en.md

@@ -10,7 +10,7 @@ Use this template when writing `review-plan.md` or `review-plan-r{N}.md`.
 - **Review Round**: Round {review-round}
 - **Artifact File**: `{review-artifact}`
 - **Review Input**:
-  - `{plan-artifact}`
+  - `{plan-artifact}` (the highest-round technical-plan artifact actually reviewed, e.g. `plan-r2.md`; leave blank if it cannot be reliably determined)
 
 ## State Check
 

package/templates/.agents/skills/review-plan/reference/report-template.zh-CN.md

@@ -10,8 +10,7 @@
 - **审查轮次**：第 {review-round} 轮
 - **产物文件**：`{review-artifact}`
 - **审查输入**：
-  - `{code-artifact}`
-  - `{code-artifact}`（如存在）
+  - `{plan-artifact}`（本轮实际检视的最高轮技术方案产物，如 `plan-r2.md`；无法可靠取得则留空）
 
 ## 状态核对
 

package/templates/.agents/skills/review-plan/reference/review-criteria.en.md

@@ -13,6 +13,7 @@ Follow the `design-review` step in `.agents/workflows/feature-development.yaml`.
 - [ ] Test strategy covers critical paths, regression risks, and edge cases
 - [ ] Risks, migration, rollback, or compatibility handling are sufficient
 - [ ] The plan avoids over-design and unrelated scope expansion
+- [ ] The reviewer checked whether the executor missed any key design decision that should be upgraded to `[needs-human-decision]`
 - [ ] Every blocker is backed by reproducible grep/sed/nl evidence; conclusions not directly verified are declared under Self-Doubt
 
 **Common anti-examples**:

package/templates/.agents/skills/review-plan/reference/review-criteria.zh-CN.md

@@ -13,6 +13,7 @@
 - [ ] 测试策略是否覆盖关键路径、回归风险和边界情况
 - [ ] 风险、迁移、回滚或兼容性处理是否充分
 - [ ] 方案是否避免过度设计和无关扩张
+- [ ] 已复核执行方是否漏标应升级为 `[needs-human-decision]` 的关键设计决策
 - [ ] 每条 blocker 都配可复现的 grep/sed/nl 证据，未直接验证的结论已在「自我质疑」声明
 
 **常见反例**：

package/templates/.agents/skills/test/SKILL.en.md

@@ -1,6 +1,8 @@
 ---
 name: test
-description: "Run the full project test workflow"
+description: >
+  Run the full project test workflow.
+  Use when you need to run the project's full test suite.
 ---
 
 # Run Tests

package/templates/.agents/skills/test/SKILL.zh-CN.md

@@ -2,7 +2,7 @@
 name: test
 description: >
   执行项目完整测试流程（编译检查 + 单元测试）。
-  当用户要求运行测试或验证代码质量时触发。
+  当需要运行测试或验证代码质量时使用。
 ---
 
 # 执行测试

package/templates/.agents/skills/test-integration/SKILL.en.md

@@ -1,6 +1,8 @@
 ---
 name: test-integration
-description: "Run the integration test workflow"
+description: >
+  Run the integration test workflow.
+  Use when you need to run the project's integration tests.
 ---
 
 # Run Integration Tests

package/templates/.agents/skills/test-integration/SKILL.zh-CN.md

@@ -1,6 +1,8 @@
 ---
 name: test-integration
-description: "执行项目集成测试流程"
+description: >
+  执行项目集成测试流程。
+  当需要运行项目集成测试流程时使用。
 ---
 
 # 运行集成测试

package/templates/.agents/skills/update-agent-infra/SKILL.en.md

@@ -1,6 +1,8 @@
 ---
 name: update-agent-infra
-description: "Update the project AI collaboration configuration"
+description: >
+  Update the project AI collaboration configuration.
+  Use when the project's AI collaboration configuration needs updating to the latest templates.
 ---
 
 # Update Project

package/templates/.agents/skills/update-agent-infra/SKILL.zh-CN.md

@@ -1,6 +1,8 @@
 ---
 name: update-agent-infra
-description: "更新项目 AI 协作配置"
+description: >
+  更新项目 AI 协作配置。
+  当需要把项目 AI 协作配置更新到最新模板时使用。
 ---
 
 # 更新项目

package/templates/.agents/skills/upgrade-dependency/SKILL.en.md

@@ -1,6 +1,8 @@
 ---
 name: upgrade-dependency
-description: "Upgrade a dependency and validate the change"
+description: >
+  Upgrade a dependency and validate the change.
+  Use when a dependency needs upgrading and the change validated.
 ---
 
 # Upgrade Dependency

package/templates/.agents/skills/upgrade-dependency/SKILL.zh-CN.md

@@ -1,6 +1,8 @@
 ---
 name: upgrade-dependency
-description: "升级项目依赖到新版本并验证"
+description: >
+  升级项目依赖到新版本并验证。
+  当需要升级某个依赖并验证改动时使用。
 ---
 
 # 升级依赖

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

@@ -1,6 +1,8 @@
 ---
 name: watch-pr
-description: "Watch a PR's required checks and self-heal on failure"
+description: >
+  Watch a PR's required checks and self-heal on failure.
+  Use when you need to monitor a PR's required checks and auto-recover on failure.
 ---
 
 # Watch Pull Request
@@ -21,6 +23,16 @@ Version stamp rule: before creating or updating `task.md` frontmatter, read `.ag
 
 > If the `{task-id}` argument matches `^[#]?[0-9]+$` (a bare number or `#`-prefixed), first read the "SKILL argument parsing" section of `.agents/rules/task-short-id.md` to resolve it; subsequent commands treat `{task-id}` as the resolved full `TASK-YYYYMMDD-HHMMSS` form.
 
+## Step Start: Write the started Marker
+
+After prerequisites pass and before this round's first artifact action, append a started marker to task.md `## Activity Log` (same base action as this round's done entry plus a ` [started]` suffix, note `started`):
+
+```
+- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Watch PR (Round {N}) [started]** by {agent} — started
+```
+
+`ai task log` pairs it with the done entry written on completion onto one row (in progress → done). See the "Activity Log started / done dual-marker convention" in `.agents/rules/task-management.md`.
+
 ## Steps
 
 ### 1. Resolve Arguments