@fitlab-ai/agent-infra 0.8.4 → 0.9.0

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

@@ -3,6 +3,7 @@ name: block-task
 description: >
   标记任务为阻塞状态并记录原因。
   当任务因外部阻塞无法推进、需要挂起并记录原因时使用。
+  仅当对话包含可解析的任务引用时才可自动调用本技能。
 ---
 
 # 标记任务阻塞
@@ -21,19 +22,15 @@ description: >
 
 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`。
 
-## 任务入参短号别名
+## 任务上下文解析
 
-> 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。
+> 入口允许省略 task ref，也接受旧位置 task ref 或 `--task <ref>` / `-t <ref>`。先从完整参数中分离 task scope 并原样保留其他业务操作数，再调用 `agent-infra-internal task-context resolve {task-scope}`；`{task-scope}` 为空、位置 ref 或 task flag 之一。只读取结构化结果的 `taskId`，后续把 `{task-id}` 绑定为该完整 `TASK-YYYYMMDD-HHMMSS`。解析失败时透传非零退出码，不自行扫描任务。
 
-## 步骤开始：写入 started 标记
+> 解析任务引用，并确认任务位于本技能支持的状态或目录且存在 `task.md`；无法定位时按未找到任务处理并停止。
 
-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`）：
+## 步骤开始：本地生命周期边界
 
-```
-- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Block 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」。
+确认前置条件后，由步骤 3 的单次 lifecycle intent 原子写入 started/done 日志、基础元数据、目录转移和短号释放；本步骤不得提前手工写入其中任一项。
 
 ## 执行步骤
 ### 1. 验证任务存在
@@ -52,58 +49,40 @@ description: >
 - [ ] 已经尝试了哪些解决方案？
 - [ ] 需要什么帮助或信息才能解除阻塞？
 
-### 3. 更新任务元数据
-
-获取当前时间：
+### 3. 执行本地生命周期意图
 
 ```bash
-date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
+agent-infra-internal task-lifecycle {task-id} block --agent {agent} \
+  --reason "{一行原因}" --unblock-condition "{解除阻塞条件}"
 ```
 
-更新 `.agents/workspace/active/{task-id}/task.md`：
-- `status`：blocked
-- `blocked_at`：{当前时间戳}
-- `updated_at`：{当前时间戳}
-- `agent_infra_version`：按 `.agents/rules/version-stamp.md` 取值
-- **追加**到 `## Activity Log`（不要覆盖之前的记录）：
-  ```
-  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Block Task** by {agent} — {一行原因}
-  ```
+解析 stdout 单 JSON。仅 `status=applied|no-op` 视为本地完成；`status=failed` 时展示 `error` 与 `completedSteps`/`pendingSteps`，不得宣称任务已阻塞。生命周期核心统一维护 `status`/`blocked_at`、阻塞信息、Activity Log、目录与短号。
 
-在 task.md 中添加阻塞信息部分。
+### 4. 验证本地终态
 
-### 4. 移动任务到 blocked 目录
+确认结构化结果的 `targetState=blocked`、目标路径为 `.agents/workspace/blocked/{task-id}`、短号效果已提交，并检查：
 
 ```bash
-mv .agents/workspace/active/{task-id} .agents/workspace/blocked/{task-id}
+ls .agents/workspace/blocked/{task-id}/task.md
 ```
 
-### 5. 验证移动
+### 5. 保留恢复身份
 
-```bash
-ls .agents/workspace/blocked/{task-id}/task.md
-```
+记录 lifecycle 结果中的请求身份与规范 metadata，供失败后以同一 intent 安全重试；不得手工补写局部状态。
 
 ### 6. 同步到 Issue（可选）
 
 检查 `task.md` 中是否存在有效的 `issue_number`。如果没有，跳过。
 
-> Issue 同步的 status label 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`，按 issue-sync.md 设置 `status: blocked`。
+如果存在有效的 `issue_number`，调用 `agent-infra-internal platform-issue sync {task-id} --agent {agent} --status blocked`。
+随后调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}` 更新 task 评论。
 
 ### 7. 完成校验
 
-**释放短号**（先 `mv` 目录已成功，再 release；脚本幂等，未在注册表也返回 0）：
-
-```bash
-node .agents/scripts/task-short-id.js release "$task_id" || true
-```
-
 运行完成校验，确认任务产物和同步状态符合规范：
 
 ```bash
-node .agents/scripts/validate-artifact.js gate block-task .agents/workspace/blocked/{task-id} --format text
+agent-infra-internal task-verify {task-id} block-task.completed --format text
 ```
 
 处理结果：
@@ -117,7 +96,7 @@ node .agents/scripts/validate-artifact.js gate block-task .agents/workspace/bloc
 
 > 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。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）。 渲染最终输出前，先读取 `.agents/rules/next-step-output.md` 并落实其两类规则：(1) 「下一步」命令把 `{task-ref}` 渲染为短号 `#NN`（未分配/已释放时回退完整 TASK-id）；(2) 在面向用户输出的绝对最后一行追加 `Completed at` 收尾行（成功、错误、早退等任何面向用户输出都适用，不限于校验通过的成功态）。
+> **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）。 渲染最终输出前，先读取 `.agents/rules/next-step-output.md` 并落实其两类规则：(1) 「下一步」命令把 `{task-ref}` 渲染为短号 `NN`（未分配/已释放时回退完整 TASK-id）；(2) 在面向用户输出的绝对最后一行追加 `Completed at` 收尾行（成功、错误、早退等任何面向用户输出都适用，不限于校验通过的成功态）。
 
 > **可选沙箱清理提示（门控渲染）**：仅当同时满足 (1) `.agents/.airc.json` 存在 `sandbox` 字段、(2) task.md 的 `branch` 字段存在且不是 `main` / `master` 时，才渲染下方输出中「归档路径」之后、「解除阻塞时执行」之前的「可选：清理本任务的沙箱」块；任一不满足则整段省略。`{branch}` 取已读入的 task.md 的 `branch` 值（任务此时已移动到 blocked/，从 `.agents/workspace/blocked/{task-id}/task.md` 读取）。该块独立于「下一步」语义。
 
@@ -135,8 +114,7 @@ node .agents/scripts/validate-artifact.js gate block-task .agents/workspace/bloc
 ai sandbox rm {branch}
 
 解除阻塞时执行：
-  mv .agents/workspace/blocked/{task-id} .agents/workspace/active/{task-id}
-  # 然后更新 task.md：status -> active，移除 blocked_at
+  agent-infra-internal task-lifecycle {task-id} activate --agent {agent} --note "{恢复说明}"
 
 下一步 - 检查任务状态（解除阻塞后）：
   - Claude Code / OpenCode：/check-task {task-ref}
@@ -159,13 +137,11 @@ ai sandbox rm {branch}
 当阻塞问题解决后：
 
 ```bash
-# 1. 移回 active
-mv .agents/workspace/blocked/{task-id} .agents/workspace/active/{task-id}
-
-# 2. 更新 task.md：设置 status 为 active，更新时间戳
-# 3. 从中断处继续（检查 current_step）
+agent-infra-internal task-lifecycle {task-id} activate --agent {agent} --note "{恢复说明}"
 ```
 
+成功后从保留的 `current_step` 继续。失败时按结构化 recovery 字段以同一 intent 重试，不手工移动目录或编辑基础元数据。
+
 ## 注意事项
 
 1. **何时阻塞**：仅在确实无法继续时才阻塞。如果是可以克服的困难，先尝试解决。

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

@@ -18,8 +18,7 @@
       "require_blocked_at": true
     },
     "activity-log": {
-      "expected_action_pattern": "(Block Task|Blocked)",
-      "freshness_minutes": 30
+      "expected_action_pattern": "(Block Task|Blocked)"
     },
     "platform-sync": {
       "when": "issue_number_exists",

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

@@ -3,6 +3,7 @@ name: cancel-task
 description: >
   Cancel an unneeded task and move it.
   Use when a task is no longer needed and should be dropped from active work.
+  Only invoke this skill automatically when the conversation includes a resolvable task reference.
 ---
 
 # Cancel Task
@@ -15,19 +16,15 @@ description: >
 
 Version stamp rule: when creating or updating `task.md` frontmatter, read `.agents/rules/version-stamp.md` first and write or refresh `agent_infra_version`.
 
-## Task id short ref
+## Task Context Resolution
 
-> 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.
+> The entry point may omit the task ref and also accepts a legacy positional ref or `--task <ref>` / `-t <ref>`. Separate task scope from the full arguments while preserving every business operand, then call `agent-infra-internal task-context resolve {task-scope}` where `{task-scope}` is empty, one positional ref, or one task flag. Read only `taskId` from the structured result and bind `{task-id}` to that full `TASK-YYYYMMDD-HHMMSS` for downstream commands. Pass through resolution failures without scanning tasks locally.
 
-## Step Start: Write the started Marker
+> Resolve the task reference, then confirm that the task is in a state or directory supported by this skill and that `task.md` exists; if it cannot be located, handle it as a missing task and stop.
 
-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`):
+## Step Start: Local Lifecycle Boundary
 
-```
-- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Cancel 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`.
+After prerequisites pass, Step 3 declares one lifecycle intent that atomically commits base metadata, the started/done pair, the directory move, and short-id handling. Do not write partial lifecycle state first.
 
 ## Steps
 
@@ -53,30 +50,17 @@ Infer the Issue closing label from the cancellation reason:
 
 When syncing to the Issue, replace any existing `status:` labels with the inferred label.
 
-### 3. Update Task Metadata
-
-Get the current time:
+### 3. Apply the Local Lifecycle Intent
 
 ```bash
-date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
+agent-infra-internal task-lifecycle {task-id} cancel --agent {agent} --reason "{one-line cancellation reason}"
 ```
 
-Update `task.md` in the task directory:
-- `status`: completed
-- `cancelled_at`: {current timestamp}
-- `cancel_reason`: {cancellation reason}
-- `updated_at`: {current timestamp}
-- `agent_infra_version`: value from `.agents/rules/version-stamp.md`
-- **Append** to `## Activity Log` (do NOT overwrite previous entries):
-  ```
-  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Cancel Task** by {agent} — {one-line cancellation reason}
-  ```
-
-### 4. Move the Task
+Only `status=applied|no-op` means local cancellation completed. On `status=failed`, show the structured error and recovery steps and retry the same intent; do not manually edit task.md, move the directory, or release the short id.
 
-Move the task directory into `.agents/workspace/completed/{task-id}`.
+### 4. Verify the Local Final State
 
-If the source directory is `blocked/`, move it from `blocked/`; if it is `active/`, move it from `active/`.
+Confirm `targetState=completed`, terminal fields, and the short-id effect from the structured result.
 
 ### 5. Verify the Move
 
@@ -90,17 +74,10 @@ Confirm the task directory was moved successfully.
 
 Check whether `task.md` contains 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.
-> Read `.agents/rules/issue-pr-commands.md` before closing the Issue.
-
 If a valid `issue_number` exists:
-- Replace all `status:` labels with the label inferred in Step 2 by following issue-sync.md
-- Remove all `in:` labels by following issue-sync.md
-- Remove the milestone by following issue-sync.md
-- Remove all assignees (skip directly when permission is insufficient; no fallback)
-- Publish a cancellation comment using the cancel marker defined in `.agents/rules/issue-sync.md`
-- Create or update the task comment marker defined in `.agents/rules/issue-sync.md` using the task-comment sync rules from `.agents/rules/issue-sync.md`
-- Close the Issue by following the "Close an Issue" command in `.agents/rules/issue-pr-commands.md`, using the fixed reason `not planned`
+- Run `agent-infra-internal platform-issue sync {task-id} --agent {agent} --status {reason} --in-labels none --assignees none --milestone none --state closed --close-reason not_planned`
+- Write the cancellation body to a temporary file and run `agent-infra-internal platform-comment sync {task-id} --kind cancel --body-file {path} --agent {agent}`
+- Run `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`
 
 The cancellation comment must include at least:
 - the cancellation reason
@@ -108,16 +85,10 @@ The cancellation comment must include at least:
 
 ### 7. Verification Gate
 
-**Release short id** (after the directory has already been moved; the script is idempotent and returns 0 even if the task isn't registered):
-
-```bash
-node .agents/scripts/task-short-id.js release "$task_id" || true
-```
-
 Run the verification gate to confirm the moved task and sync state are valid:
 
 ```bash
-node .agents/scripts/validate-artifact.js gate cancel-task .agents/workspace/completed/{task-id} --format text
+agent-infra-internal task-verify {task-id} cancel-task.completed --format text
 ```
 
 Handle the result as follows:
@@ -131,7 +102,7 @@ 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. 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). Before rendering the final output, read `.agents/rules/next-step-output.md` and apply both of its rules: (1) render `{task-ref}` in the "Next steps" commands as the short id `#NN` (falling back to the full TASK-id when unallocated or released); (2) append the `Completed at` line as the very last line of the user-facing output (this applies to every user-facing output — success, error, and early-return paths alike, not only the success path).
+> **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). Before rendering the final output, read `.agents/rules/next-step-output.md` and apply both of its rules: (1) render `{task-ref}` in the "Next steps" commands as the short id `NN` (falling back to the full TASK-id when unallocated or released); (2) append the `Completed at` line as the very last line of the user-facing output (this applies to every user-facing output — success, error, and early-return paths alike, not only the success path).
 
 > **Optional sandbox-cleanup hint (gated)**: Render the "Optional: clean up this task's sandbox" block — placed after "Target path" and before "Next step" in the output below — only when BOTH (1) `.agents/.airc.json` has a `sandbox` field and (2) task.md's `branch` field exists and is not `main` / `master`; otherwise omit the whole block. `{branch}` is the `branch` value from the task.md you already loaded (the task has moved to completed/, so read it from `.agents/workspace/completed/{task-id}/task.md`). This block is independent of "Next steps" semantics.
 

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

@@ -3,6 +3,7 @@ name: cancel-task
 description: >
   取消不再需要的任务并转移。
   当某个任务不再需要、应从 active 工作中撤下时使用。
+  仅当对话包含可解析的任务引用时才可自动调用本技能。
 ---
 
 # 取消任务
@@ -15,19 +16,15 @@ description: >
 
 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`。
 
-## 任务入参短号别名
+## 任务上下文解析
 
-> 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。
+> 入口允许省略 task ref，也接受旧位置 task ref 或 `--task <ref>` / `-t <ref>`。先从完整参数中分离 task scope 并原样保留其他业务操作数，再调用 `agent-infra-internal task-context resolve {task-scope}`；`{task-scope}` 为空、位置 ref 或 task flag 之一。只读取结构化结果的 `taskId`，后续把 `{task-id}` 绑定为该完整 `TASK-YYYYMMDD-HHMMSS`。解析失败时透传非零退出码，不自行扫描任务。
 
-## 步骤开始：写入 started 标记
+> 解析任务引用，并确认任务位于本技能支持的状态或目录且存在 `task.md`；无法定位时按未找到任务处理并停止。
 
-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`）：
+## 步骤开始：本地生命周期边界
 
-```
-- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Cancel 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」。
+确认前置条件后，由步骤 3 的单次 lifecycle intent 原子完成基础元数据、started/done 日志、目录转移和短号处理；不得提前手工写入局部状态。
 
 ## 执行步骤
 ### 1. 验证任务存在
@@ -52,30 +49,17 @@ description: >
 
 后续同步到 Issue 时，使用最终推断结果替换现有 `status:` labels。
 
-### 3. 更新任务元数据
-
-获取当前时间：
+### 3. 执行本地生命周期意图
 
 ```bash
-date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
+agent-infra-internal task-lifecycle {task-id} cancel --agent {agent} --reason "{一行取消原因}"
 ```
 
-更新任务目录中的 `task.md`：
-- `status`：completed
-- `cancelled_at`：{当前时间戳}
-- `cancel_reason`：{取消原因}
-- `updated_at`：{当前时间戳}
-- `agent_infra_version`：按 `.agents/rules/version-stamp.md` 取值
-- **追加**到 `## Activity Log`（不要覆盖之前记录）：
-  ```
-  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Cancel Task** by {agent} — {一行取消原因}
-  ```
-
-### 4. 转移任务
+仅 `status=applied|no-op` 视为本地取消完成。`status=failed` 时展示结构化 `error` 与 recovery steps，并以同一 intent 重试；不得手工编辑 task.md、移动目录或释放短号。
 
-将任务目录移动到 `.agents/workspace/completed/{task-id}`。
+### 4. 验证本地终态
 
-如果源目录在 `blocked/`，从 `blocked/` 移动；如果源目录在 `active/`，从 `active/` 移动。
+确认 `targetState=completed`、终态字段与短号效果符合结构化结果。
 
 ### 5. 验证转移
 
@@ -89,17 +73,10 @@ ls .agents/workspace/completed/{task-id}/task.md
 
 检查 `task.md` 中是否存在有效的 `issue_number`。如果没有，跳过此步骤。
 
-> 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。
-> 关闭 Issue 前先读取 `.agents/rules/issue-pr-commands.md`。
-
 如果存在有效的 `issue_number`：
-- 按 issue-sync.md 替换所有 `status:` labels，并设置步骤 2 推断出的标签
-- 按 issue-sync.md 移除所有 `in:` labels
-- 按 issue-sync.md 移除 milestone
-- 移除全部 assignees（无权限时直接跳过，不做替代）
-- 发布取消评论，隐藏标记使用 `.agents/rules/issue-sync.md` 中定义的 cancel 评论标记
-- 使用 `.agents/rules/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
-- 关闭 Issue：按 `.agents/rules/issue-pr-commands.md` 中的“关闭 Issue”命令执行，关闭原因固定为 `not planned`
+- 调用 `agent-infra-internal platform-issue sync {task-id} --agent {agent} --status {reason} --in-labels none --assignees none --milestone none --state closed --close-reason not_planned`
+- 将取消正文写入临时文件，调用 `agent-infra-internal platform-comment sync {task-id} --kind cancel --body-file {path} --agent {agent}`
+- 调用 `agent-infra-internal platform-comment sync {task-id} --kind task --agent {agent}`
 
 取消评论至少包含：
 - 取消原因
@@ -107,16 +84,10 @@ ls .agents/workspace/completed/{task-id}/task.md
 
 ### 7. 完成校验
 
-**释放短号**（先 `mv` 目录已成功，再 release；脚本幂等，未在注册表也返回 0）：
-
-```bash
-node .agents/scripts/task-short-id.js release "$task_id" || true
-```
-
 运行完成校验，确认任务转移和同步状态符合规范：
 
 ```bash
-node .agents/scripts/validate-artifact.js gate cancel-task .agents/workspace/completed/{task-id} --format text
+agent-infra-internal task-verify {task-id} cancel-task.completed --format text
 ```
 
 处理结果：
@@ -130,7 +101,7 @@ node .agents/scripts/validate-artifact.js gate cancel-task .agents/workspace/com
 
 > 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。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）。 渲染最终输出前，先读取 `.agents/rules/next-step-output.md` 并落实其两类规则：(1) 「下一步」命令把 `{task-ref}` 渲染为短号 `#NN`（未分配/已释放时回退完整 TASK-id）；(2) 在面向用户输出的绝对最后一行追加 `Completed at` 收尾行（成功、错误、早退等任何面向用户输出都适用，不限于校验通过的成功态）。
+> **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）。 渲染最终输出前，先读取 `.agents/rules/next-step-output.md` 并落实其两类规则：(1) 「下一步」命令把 `{task-ref}` 渲染为短号 `NN`（未分配/已释放时回退完整 TASK-id）；(2) 在面向用户输出的绝对最后一行追加 `Completed at` 收尾行（成功、错误、早退等任何面向用户输出都适用，不限于校验通过的成功态）。
 
 > **可选沙箱清理提示（门控渲染）**：仅当同时满足 (1) `.agents/.airc.json` 存在 `sandbox` 字段、(2) task.md 的 `branch` 字段存在且不是 `main` / `master` 时，才渲染下方输出中「目标路径」之后、「下一步」之前的「可选：清理本任务的沙箱」块；任一不满足则整段省略。`{branch}` 取已读入的 task.md 的 `branch` 值（任务此时已移动到 completed/，从 `.agents/workspace/completed/{task-id}/task.md` 读取）。该块独立于「下一步」语义。
 

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

@@ -19,8 +19,7 @@
       "require_cancelled_at": true
     },
     "activity-log": {
-      "expected_action_pattern": "(Cancel Task|Cancelled)",
-      "freshness_minutes": 30
+      "expected_action_pattern": "(Cancel Task|Cancelled)"
     },
     "platform-sync": {
       "when": "issue_number_exists",

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

@@ -3,6 +3,7 @@ name: check-task
 description: >
   Check a task's current status and progress.
   Use when you want a quick view of a task's current status and progress.
+  Only invoke this skill automatically when the conversation includes a resolvable task reference.
 ---
 
 # Check Task Status
@@ -12,9 +13,11 @@ description: >
 - This skill is **read-only** -- do not modify any files
 - Mechanical facts (frontmatter metadata, artifact grouping, git/platform state, and locating the task across the active, blocked, and completed directories) are delegated to the deterministic `ai task status` command. This skill only adds the semantic layer the CLI cannot produce: workflow-stage interpretation, review-verdict parsing, and the next-step recommendation.
 
-## Task id short ref
+## Task Context Resolution
 
-> 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.
+> The entry point may omit the task ref and also accepts a legacy positional ref or `--task <ref>` / `-t <ref>`. Separate task scope from the full arguments while preserving every business operand, then call `agent-infra-internal task-context resolve {task-scope}` where `{task-scope}` is empty, one positional ref, or one task flag. Read only `taskId` from the structured result and bind `{task-id}` to that full `TASK-YYYYMMDD-HHMMSS` for downstream commands. Pass through resolution failures without scanning tasks locally.
+
+> Resolve the task reference, then confirm that the task is in a state or directory supported by this skill and that `task.md` exists; if it cannot be located, handle it as a missing task and stop.
 
 ## Steps
 
@@ -74,7 +77,7 @@ Recommend the appropriate next skill based on the current workflow state. You mu
 >
 > **Important: if the latest review report contains any issue at all, do not use the corresponding review-passed row. Use the corresponding has-issues row instead.**
 >
-> Before rendering the final output, read `.agents/rules/next-step-output.md` and apply both of its rules: (1) render `{task-ref}` in the table commands below as the short id `#NN` (falling back to the full TASK-id when unallocated or released); (2) append the `Completed at` line as the very last line of the user-facing output (this applies to every user-facing output — success, error, and early-return paths alike, not only the success path).
+> Before rendering the final output, read `.agents/rules/next-step-output.md` and apply both of its rules: (1) render `{task-ref}` in the table commands below as the short id `NN` (falling back to the full TASK-id when unallocated or released); (2) append the `Completed at` line as the very last line of the user-facing output (this applies to every user-facing output — success, error, and early-return paths alike, not only the success path).
 
 | Current State              | Claude Code / OpenCode                              | Gemini CLI                               | Codex CLI                                           |
 |----------------------------|-----------------------------------------------------|------------------------------------------|-----------------------------------------------------|

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

@@ -3,6 +3,7 @@ name: check-task
 description: >
   查看任务的当前状态和进度。
   当想快速查看某个任务当前状态与进度时使用。
+  仅当对话包含可解析的任务引用时才可自动调用本技能。
 ---
 
 # 查看任务状态
@@ -12,9 +13,11 @@ description: >
 - 本技能是**只读**操作 —— 不修改任何文件
 - 机械数据（frontmatter 元数据、产物分组、Git/Platform 状态，以及跨 active、blocked、completed 三目录定位任务）一律委托给确定性的 `ai task status` 命令。本技能只负责 CLI 无法产出的语义层：工作流阶段解读、审查结论解析、下一步建议。
 
-## 任务入参短号别名
+## 任务上下文解析
 
-> 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。
+> 入口允许省略 task ref，也接受旧位置 task ref 或 `--task <ref>` / `-t <ref>`。先从完整参数中分离 task scope 并原样保留其他业务操作数，再调用 `agent-infra-internal task-context resolve {task-scope}`；`{task-scope}` 为空、位置 ref 或 task flag 之一。只读取结构化结果的 `taskId`，后续把 `{task-id}` 绑定为该完整 `TASK-YYYYMMDD-HHMMSS`。解析失败时透传非零退出码，不自行扫描任务。
+
+> 解析任务引用，并确认任务位于本技能支持的状态或目录且存在 `task.md`；无法定位时按未找到任务处理并停止。
 
 ## 执行步骤
 
@@ -74,7 +77,7 @@ ai task status {task-id}
 >
 > **特别注意：只要最新审查报告中存在任何问题，就不能使用对应「审查通过」行。必须改用对应「审查有问题」行。**
 >
-> 渲染最终输出前先读取 `.agents/rules/next-step-output.md` 并落实其两类规则：(1) 下方表格中命令的 `{task-ref}` 渲染为短号 `#NN`（未分配/已释放时回退完整 TASK-id）；(2) 在面向用户输出的绝对最后一行追加 `Completed at` 收尾行（成功、错误、早退等任何面向用户输出都适用，不限于校验通过的成功态）。
+> 渲染最终输出前先读取 `.agents/rules/next-step-output.md` 并落实其两类规则：(1) 下方表格中命令的 `{task-ref}` 渲染为短号 `NN`（未分配/已释放时回退完整 TASK-id）；(2) 在面向用户输出的绝对最后一行追加 `Completed at` 收尾行（成功、错误、早退等任何面向用户输出都适用，不限于校验通过的成功态）。
 
 | 当前状态           | Claude Code / OpenCode       | Gemini CLI                               | Codex CLI                    |
 |--------------------|------------------------------|------------------------------------------|------------------------------|

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

@@ -13,15 +13,9 @@ Dismiss the specified Code Scanning (CodeQL) alert and record a justified reason
 
 > 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
+## Step Start: Local Lifecycle Boundary
 
-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} — **Close Codescan [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`.
+The skill still owns the security-alert API. When a related task exists, Step 7 declares exactly one local lifecycle intent that commits base metadata, the log pair, archival placement, and short-id handling.
 
 ## Execution Flow
 
@@ -85,27 +79,17 @@ Dismiss the alert by following the Code Scanning dismiss command in `.agents/rul
 ### 7. Record in the Task (If Any)
 
 If a related task exists (search for `codescan_alert_number: <alert-number>`):
-Get the current time:
 
 ```bash
-date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
+agent-infra-internal task-lifecycle {task-id} close-codescan --agent {agent} \
+  --alert-number {alert-number} --reason "{reason}"
 ```
 
-- Add the dismissal record to task.md
-- **Append** to `## Activity Log` (do NOT overwrite previous entries):
-  ```
-  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Close Codescan** by {agent} — Code Scanning alert #{alert-number} dismissed: {reason}
-  ```
-- Archive the task
-- **Release short id** (after the archive `mv` succeeded; the script is idempotent):
-
-  ```bash
-  node .agents/scripts/task-short-id.js release "$task_id" || true
-  ```
+Only `status=applied|no-op` means local archival completed. If the API dismissal succeeded but lifecycle returns `failed`, explicitly report that remote is dismissed while local recovery remains, show recovery steps, and retry the same intent. Do not hand-edit task.md, move directories, or release the short id.
 
 ### 8. Inform User
 
-> **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). Before rendering the final output, read `.agents/rules/next-step-output.md` and apply both of its rules: (1) render `{task-ref}` in the "Next steps" commands as the short id `#NN` (falling back to the full TASK-id when unallocated or released); (2) append the `Completed at` line as the very last line of the user-facing output (this applies to every user-facing output — success, error, and early-return paths alike, not only the success path).
+> **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). Before rendering the final output, read `.agents/rules/next-step-output.md` and apply both of its rules: (1) render `{task-ref}` in the "Next steps" commands as the short id `NN` (falling back to the full TASK-id when unallocated or released); (2) append the `Completed at` line as the very last line of the user-facing output (this applies to every user-facing output — success, error, and early-return paths alike, not only the success path).
 
 > **Optional sandbox-cleanup hint (gated)**: Render the "Optional: clean up this task's sandbox" block — placed after the "Note:" line and before "Next step" in the output below — only when ALL of (1) `.agents/.airc.json` has a `sandbox` field, (2) step 7 located a related task by the alert number, and (3) that related task's task.md `branch` field exists and is not `main` / `master`; otherwise omit the whole block. `{branch}` is the `branch` value from the related task.md located in step 7. This block is independent of "Next step" semantics.
 
@@ -145,5 +129,3 @@ Next step - complete and archive the task if a related task exists:
 - Already closed: output "Alert #{number} is already {state}"
 - Permission error: output "No permission to modify alerts"
 - User canceled: output "Cancellation acknowledged"
-
-

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

@@ -13,15 +13,9 @@ description: >
 
 > 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
+## 步骤开始：本地生命周期边界
 
-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} — **Close Codescan [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」。
+安全告警 API 仍由本技能处理；若存在关联任务，步骤 7 只声明一个本地 lifecycle intent，由核心统一提交基础元数据、日志、归档目录和短号。
 
 ## 执行流程
 
@@ -85,27 +79,17 @@ Code Scanning 告警 #{alert-number}
 ### 7. 记录到任务（如存在）
 
 如果有关联任务（搜索 `codescan_alert_number: <alert-number>`）：
-获取当前时间：
 
 ```bash
-date "+%Y-%m-%d %H:%M:%S%z" | sed 's/\([+-][0-9][0-9]\)\([0-9][0-9]\)$/\1:\2/'
+agent-infra-internal task-lifecycle {task-id} close-codescan --agent {agent} \
+  --alert-number {alert-number} --reason "{reason}"
 ```
 
-- 添加关闭记录到 task.md
-- **追加**到 `## Activity Log`（不要覆盖之前的记录）：
-  ```
-  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Close Codescan** by {agent} — Code Scanning alert #{alert-number} dismissed: {reason}
-  ```
-- 归档任务
-- **释放短号**（归档目录已 mv 成功，再 release；脚本幂等）：
-
-  ```bash
-  node .agents/scripts/task-short-id.js release "$task_id" || true
-  ```
+仅 `status=applied|no-op` 视为本地归档完成。若 API 已关闭但 lifecycle 返回 `failed`，必须明确报告“远端已关闭、本地待恢复”，展示 recovery steps，并以同一 intent 重试；不得手工更新 task.md、移动目录或释放短号。
 
 ### 8. 告知用户
 
-> **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）。 渲染最终输出前，先读取 `.agents/rules/next-step-output.md` 并落实其两类规则：(1) 「下一步」命令把 `{task-ref}` 渲染为短号 `#NN`（未分配/已释放时回退完整 TASK-id）；(2) 在面向用户输出的绝对最后一行追加 `Completed at` 收尾行（成功、错误、早退等任何面向用户输出都适用，不限于校验通过的成功态）。
+> **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）。 渲染最终输出前，先读取 `.agents/rules/next-step-output.md` 并落实其两类规则：(1) 「下一步」命令把 `{task-ref}` 渲染为短号 `NN`（未分配/已释放时回退完整 TASK-id）；(2) 在面向用户输出的绝对最后一行追加 `Completed at` 收尾行（成功、错误、早退等任何面向用户输出都适用，不限于校验通过的成功态）。
 
 > **可选沙箱清理提示（门控渲染）**：仅当同时满足 (1) `.agents/.airc.json` 存在 `sandbox` 字段、(2) 第 7 步按告警号定位到了关联任务、(3) 该关联任务 task.md 的 `branch` 字段存在且不是 `main` / `master` 时，才渲染下方输出中「注意：…」之后、「下一步」之前的「可选：清理本任务的沙箱」块；任一不满足则整段省略。`{branch}` 取第 7 步定位到的关联任务 task.md 的 `branch` 值。该块独立于「下一步」语义。
 
@@ -145,5 +129,3 @@ ai sandbox rm {branch}
 - 已关闭：提示 "Alert #{number} is already {state}"
 - 权限错误：提示 "No permission to modify alerts"
 - 用户取消：提示 "Cancellation acknowledged"
-
-