@fitlab-ai/agent-infra 0.7.1 → 0.7.3

package/templates/.agents/skills/create-pr/reference/comment-publish.en.md

@@ -9,7 +9,8 @@ Read this file before creating or updating the single reviewer-facing PR summary
 - Generate or update the `<!-- sync-pr:{task-id}:summary -->` comment with the canonical template from `.agents/rules/pr-sync.md`
 - When a matching summary comment already exists, PATCH only when the body changed; otherwise skip the write
 - In this skill, summary sync failures follow the existing `create-pr` error handling and must not roll back an already-created PR
+- Populate the "Manual Verification Required" section per the aggregation rules in `.agents/rules/pr-sync.md` (sources: plan assumptions/open questions, review-code "Environment-Blocked Findings"/"Self-Doubt"); write the explicit placeholder when there are none
 
 ## Result Reporting
 
-Reuse the normalized result string from `.agents/rules/pr-sync.md` in this skill's user output or `PR Created` Activity Log.
+Reuse the normalized result string from `.agents/rules/pr-sync.md` in this skill's user output or `Create PR` Activity Log.

package/templates/.agents/skills/create-pr/reference/comment-publish.zh-CN.md

@@ -9,7 +9,8 @@
 - 按 `.agents/rules/pr-sync.md` 中的唯一权威模板生成或更新 `<!-- sync-pr:{task-id}:summary -->` 评论
 - PR 已存在同标记评论时，只在正文变化时 PATCH；否则跳过写入
 - 本 skill 中，摘要同步失败沿用 `create-pr` 的现有错误处理，不回滚已经创建的 PR
+- 按 `.agents/rules/pr-sync.md` 的聚合规则填充「需人工校验」段落（来源：plan 假设/未决问题、review-code 环境性遗留/自我质疑）；无事项时写显式占位
 
 ## 结果回传
 
-将 `.agents/rules/pr-sync.md` 中的结果回传字符串用于当前 skill 的用户输出或 `PR Created` Activity Log 复用。
+将 `.agents/rules/pr-sync.md` 中的结果回传字符串用于当前 skill 的用户输出或 `Create PR` Activity Log 复用。

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

@@ -69,7 +69,7 @@ Final user output should include this follow-up path:
 ```text
 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}
+    - Claude Code / OpenCode: /complete-task {task-ref}
+    - Gemini CLI: /agent-infra:complete-task {task-ref}
+    - Codex CLI: $complete-task {task-ref}
 ```

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

@@ -69,7 +69,7 @@ Milestone 规则：
 ```text
 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}
+    - Claude Code / OpenCode: /complete-task {task-ref}
+    - Gemini CLI: /agent-infra:complete-task {task-ref}
+    - Codex CLI: $complete-task {task-ref}
 ```

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

@@ -24,7 +24,7 @@ Version stamp rule: when creating or updating `task.md` frontmatter, read `.agen
 
 ## Task id short ref
 
-> If `{task-id}` begins with `#`, 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.
+> 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.
 
 ## Steps
 
@@ -109,12 +109,12 @@ Update `.agents/workspace/active/{task-id}/task.md`:
 - `## Context` -> `- **Branch**:`: update it to the generated branch name
 - **Append** to `## Activity Log` (do NOT overwrite previous entries):
   ```
-  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Task Created** by {agent} — Task created from description
+  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Create Task** by {agent} — Task created from description
   ```
 
 ### 4. Cascade Issue Creation via `.agents/rules/create-issue.md`
 
-After task.md is written and `Task Created` is recorded, read `.agents/rules/create-issue.md` first and follow the steps it describes to create an Issue.
+After task.md is written and `Create Task` is recorded, read `.agents/rules/create-issue.md` first and follow the steps it describes to create an Issue.
 
 The rule's content is determined by the configured code platform:
 - A platform that supports Issue creation: contains the full flow for auth detection, template detection, label/type/milestone inference, the create-Issue call, and writing back to `task.md`
@@ -130,7 +130,7 @@ Handle the result:
 
 ### 5. Verification Gate
 
-**Allocate short id first** (writes `short_id` back to task.md and the registry entry; the validation gate will read it):
+**Allocate short id first** (ensures the registry entry is allocated; the validation gate will read it):
 
 ```bash
 node .agents/scripts/task-short-id.js alloc "$task_id"
@@ -155,14 +155,14 @@ 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).
+> **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).
 
 Scenario A: when an Issue was created, output:
 ```
 Task created and Issue creation cascaded successfully.
 
 Task information:
-- Task ID: {task-id}
+- Task ID: {task-id} (short id {task-ref})
 - Title: {title}
 - Type: {type}
 - Workflow: {workflow}
@@ -172,9 +172,9 @@ Output file:
 - Task file: .agents/workspace/active/{task-id}/task.md
 
 Next step - run requirements analysis:
-  - Claude Code / OpenCode: /analyze-task {task-id}
-  - Gemini CLI: /{{project}}:analyze-task {task-id}
-  - Codex CLI: $analyze-task {task-id}
+  - Claude Code / OpenCode: /analyze-task {task-ref}
+  - Gemini CLI: /{{project}}:analyze-task {task-ref}
+  - Codex CLI: $analyze-task {task-ref}
 ```
 
 Scenario B: when no Issue was created, output:
@@ -182,7 +182,7 @@ Scenario B: when no Issue was created, output:
 Task created.
 
 Task information:
-- Task ID: {task-id}
+- Task ID: {task-id} (short id {task-ref})
 - Title: {title}
 - Type: {type}
 - Workflow: {workflow}
@@ -191,9 +191,9 @@ Output file:
 - Task file: .agents/workspace/active/{task-id}/task.md
 
 Next step - run requirements analysis:
-  - Claude Code / OpenCode: /analyze-task {task-id}
-  - Gemini CLI: /{{project}}:analyze-task {task-id}
-  - Codex CLI: $analyze-task {task-id}
+  - Claude Code / OpenCode: /analyze-task {task-ref}
+  - Gemini CLI: /{{project}}:analyze-task {task-ref}
+  - Codex CLI: $analyze-task {task-ref}
 ```
 
 Scenario C: when Issue creation failed, output:
@@ -201,7 +201,7 @@ Scenario C: when Issue creation failed, output:
 Task created, but cascade Issue creation failed.
 
 Task information:
-- Task ID: {task-id}
+- Task ID: {task-id} (short id {task-ref})
 - Title: {title}
 - Type: {type}
 - Workflow: {workflow}
@@ -215,9 +215,9 @@ Output file:
 - Task file: .agents/workspace/active/{task-id}/task.md
 
 Next step - run requirements analysis:
-  - Claude Code / OpenCode: /analyze-task {task-id}
-  - Gemini CLI: /{{project}}:analyze-task {task-id}
-  - Codex CLI: $analyze-task {task-id}
+  - Claude Code / OpenCode: /analyze-task {task-ref}
+  - Gemini CLI: /{{project}}:analyze-task {task-ref}
+  - Codex CLI: $analyze-task {task-ref}
 
 For later platform sync: after fixing auth / network / template issues, manually run the Issue creation flow in `.agents/rules/create-issue.md` for this task; or manually create/find an Issue and write `issue_number` into task.md so later skills can take over cascade sync.
 ```

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

@@ -24,7 +24,7 @@ description: "根据自然语言描述创建任务"
 
 ## 任务入参短号别名
 
-> 如果 `{task-id}` 入参以 `#` 开头，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。
+> 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。
 
 ## 执行步骤
 ### 1. 解析用户描述
@@ -108,12 +108,12 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 - `## 上下文` 中的 `- **分支**：`：更新为生成的分支名
 - **追加**到 `## Activity Log`（不要覆盖之前的记录）：
   ```
-  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Task Created** by {agent} — Task created from description
+  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Create Task** by {agent} — Task created from description
   ```
 
 ### 4. 按 `.agents/rules/create-issue.md` 级联创建 Issue
 
-在 task.md 落盘并记录 `Task Created` 后，先读取 `.agents/rules/create-issue.md` 并按其中描述的步骤执行 Issue 创建。
+在 task.md 落盘并记录 `Create Task` 后，先读取 `.agents/rules/create-issue.md` 并按其中描述的步骤执行 Issue 创建。
 
 规则文件由当前配置的代码平台决定其内容：
 - 支持 Issue 创建的平台：包含完整的认证检测、模板检测、label/Issue Type/milestone 推断、Issue 创建调用、`task.md` 回写流程
@@ -129,7 +129,7 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 
 ### 5. 完成校验
 
-**先调用短号分配**（保证 `short_id` 写回 task.md + 注册表 entry 已在；完成校验阶段会读取）：
+**先调用短号分配**（保证注册表 entry 已分配；完成校验阶段会读取）：
 
 ```bash
 node .agents/scripts/task-short-id.js alloc "$task_id"
@@ -154,14 +154,14 @@ 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。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）。
+> **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）。
 
 场景 A：已创建 Issue 时输出：
 ```
 任务已创建，并已级联创建 Issue。
 
 任务信息：
-- 任务 ID：{task-id}
+- 任务 ID：{task-id}（短号 {task-ref}）
 - 标题：{title}
 - 类型：{type}
 - 工作流：{workflow}
@@ -171,9 +171,9 @@ node .agents/scripts/validate-artifact.js gate create-task .agents/workspace/act
 - 任务文件：.agents/workspace/active/{task-id}/task.md
 
 下一步 - 执行需求分析：
-  - Claude Code / OpenCode：/analyze-task {task-id}
-  - Gemini CLI：/{{project}}:analyze-task {task-id}
-  - Codex CLI：$analyze-task {task-id}
+  - Claude Code / OpenCode：/analyze-task {task-ref}
+  - Gemini CLI：/{{project}}:analyze-task {task-ref}
+  - Codex CLI：$analyze-task {task-ref}
 ```
 
 场景 B：未创建 Issue 时输出：
@@ -181,7 +181,7 @@ node .agents/scripts/validate-artifact.js gate create-task .agents/workspace/act
 任务已创建。
 
 任务信息：
-- 任务 ID：{task-id}
+- 任务 ID：{task-id}（短号 {task-ref}）
 - 标题：{title}
 - 类型：{type}
 - 工作流：{workflow}
@@ -190,9 +190,9 @@ node .agents/scripts/validate-artifact.js gate create-task .agents/workspace/act
 - 任务文件：.agents/workspace/active/{task-id}/task.md
 
 下一步 - 执行需求分析：
-  - Claude Code / OpenCode：/analyze-task {task-id}
-  - Gemini CLI：/{{project}}:analyze-task {task-id}
-  - Codex CLI：$analyze-task {task-id}
+  - Claude Code / OpenCode：/analyze-task {task-ref}
+  - Gemini CLI：/{{project}}:analyze-task {task-ref}
+  - Codex CLI：$analyze-task {task-ref}
 ```
 
 场景 C：Issue 创建失败时输出：
@@ -200,7 +200,7 @@ node .agents/scripts/validate-artifact.js gate create-task .agents/workspace/act
 任务已创建，但 Issue 级联创建失败。
 
 任务信息：
-- 任务 ID：{task-id}
+- 任务 ID：{task-id}（短号 {task-ref}）
 - 标题：{title}
 - 类型：{type}
 - 工作流：{workflow}
@@ -214,9 +214,9 @@ Issue 创建失败：
 - 任务文件：.agents/workspace/active/{task-id}/task.md
 
 下一步 - 执行需求分析：
-  - Claude Code / OpenCode：/analyze-task {task-id}
-  - Gemini CLI：/{{project}}:analyze-task {task-id}
-  - Codex CLI：$analyze-task {task-id}
+  - Claude Code / OpenCode：/analyze-task {task-ref}
+  - Gemini CLI：/{{project}}:analyze-task {task-ref}
+  - Codex CLI：$analyze-task {task-ref}
 
 后续如需平台同步：修复认证/网络/模板问题后，可按 `.agents/rules/create-issue.md` 对当前任务手动执行一次 Issue 创建；或手动创建/查找 Issue，并把 `issue_number` 写入 task.md，后续技能会接管级联同步。
 ```

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

@@ -18,7 +18,7 @@
       "expected_status": "active"
     },
     "activity-log": {
-      "expected_action_pattern": "Task Created",
+      "expected_action_pattern": "(Create Task|Task Created)",
       "freshness_minutes": 30
     },
     "platform-sync": {

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

@@ -15,7 +15,7 @@ Import the specified Code Scanning (CodeQL) alert and create a remediation task.
 
 ## Task id short ref
 
-> If `{task-id}` begins with `#`, 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.
+> 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.
 
 ## Execution Flow
 
@@ -57,12 +57,12 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 Update task.md: `current_step` -> `requirement-analysis`.
 - **Append** to `## Activity Log` (do NOT overwrite previous entries):
   ```
-  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Import Code Scanning Alert** by {agent} — Code Scanning alert #{alert-number} imported
+  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Import Codescan** by {agent} — Code Scanning alert #{alert-number} imported
   ```
 
 ### 4. Verification Gate
 
-**Allocate short id first** (writes `short_id` back to task.md and the registry entry; the validation gate will read it):
+**Allocate short id first** (ensures the registry entry is allocated; the validation gate will read it):
 
 ```bash
 node .agents/scripts/task-short-id.js alloc "$task_id"
@@ -87,7 +87,7 @@ 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).
+> **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).
 
 ```
 Code Scanning alert #{alert-number} imported.
@@ -98,12 +98,12 @@ Alert information:
 - Location: {file-path}:{line-number}
 
 Task information:
-- Task ID: {task-id}
+- Task ID: {task-id} (short id {task-ref})
 
 Next step:
-  - Claude Code / OpenCode: /analyze-task {task-id}
-  - Gemini CLI: /{{project}}:analyze-task {task-id}
-  - Codex CLI: $analyze-task {task-id}
+  - Claude Code / OpenCode: /analyze-task {task-ref}
+  - Gemini CLI: /{{project}}:analyze-task {task-ref}
+  - Codex CLI: $analyze-task {task-ref}
 ```
 
 

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

@@ -15,7 +15,7 @@ description: "导入 Code Scanning 告警并创建修复任务"
 
 ## 任务入参短号别名
 
-> 如果 `{task-id}` 入参以 `#` 开头，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。
+> 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。
 
 ## 执行流程
 
@@ -57,12 +57,12 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 更新 task.md：`current_step` -> `requirement-analysis`。
 - **追加**到 `## Activity Log`（不要覆盖之前的记录）：
   ```
-  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Import Code Scanning Alert** by {agent} — Code Scanning alert #{alert-number} imported
+  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Import Codescan** by {agent} — Code Scanning alert #{alert-number} imported
   ```
 
 ### 4. 完成校验
 
-**先调用短号分配**（保证 `short_id` 写回 task.md + 注册表 entry 已在；完成校验阶段会读取）：
+**先调用短号分配**（保证注册表 entry 已分配；完成校验阶段会读取）：
 
 ```bash
 node .agents/scripts/task-short-id.js alloc "$task_id"
@@ -87,7 +87,7 @@ 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。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）。
+> **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）。
 
 ```
 Code Scanning 告警 #{alert-number} 已导入。
@@ -98,12 +98,12 @@ Code Scanning 告警 #{alert-number} 已导入。
 - 位置：{file-path}:{line-number}
 
 任务信息：
-- 任务 ID：{task-id}
+- 任务 ID：{task-id}（短号 {task-ref}）
 
 下一步：
-  - Claude Code / OpenCode：/analyze-task {task-id}
-  - Gemini CLI：/agent-infra:analyze-task {task-id}
-  - Codex CLI：$analyze-task {task-id}
+  - Claude Code / OpenCode：/analyze-task {task-ref}
+  - Gemini CLI：/agent-infra:analyze-task {task-ref}
+  - Codex CLI：$analyze-task {task-ref}
 ```
 
 

package/templates/.agents/skills/import-codescan/config/verify.json

@@ -17,7 +17,7 @@
       "expected_status": "active"
     },
     "activity-log": {
-      "expected_action_pattern": "Import Code Scanning Alert",
+      "expected_action_pattern": "(Import Codescan|Import Code Scanning Alert)",
       "freshness_minutes": 30
     },
     "platform-sync": null

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

@@ -15,7 +15,7 @@ Import the specified Dependabot security alert and create a remediation task.
 
 ## Task id short ref
 
-> If `{task-id}` begins with `#`, 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.
+> 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.
 
 ## Execution Flow
 
@@ -58,12 +58,12 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 Update task.md: `current_step` -> `requirement-analysis`.
 - **Append** to `## Activity Log` (do NOT overwrite previous entries):
   ```
-  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Import Dependabot Alert** by {agent} — Dependabot alert #{alert-number} imported
+  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Import Dependabot** by {agent} — Dependabot alert #{alert-number} imported
   ```
 
 ### 4. Verification Gate
 
-**Allocate short id first** (writes `short_id` back to task.md and the registry entry; the validation gate will read it):
+**Allocate short id first** (ensures the registry entry is allocated; the validation gate will read it):
 
 ```bash
 node .agents/scripts/task-short-id.js alloc "$task_id"
@@ -88,7 +88,7 @@ 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).
+> **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).
 
 ```
 Security alert #{alert-number} imported.
@@ -99,15 +99,15 @@ Vulnerability information:
 - Affected package: {package-name}
 
 Task information:
-- Task ID: {task-id}
+- Task ID: {task-id} (short id {task-ref})
 
 Output file:
 - Task file: .agents/workspace/active/{task-id}/task.md
 
 Next step:
-  - Claude Code / OpenCode: /analyze-task {task-id}
-  - Gemini CLI: /{{project}}:analyze-task {task-id}
-  - Codex CLI: $analyze-task {task-id}
+  - Claude Code / OpenCode: /analyze-task {task-ref}
+  - Gemini CLI: /{{project}}:analyze-task {task-ref}
+  - Codex CLI: $analyze-task {task-ref}
 ```
 
 

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

@@ -15,7 +15,7 @@ description: "导入 Dependabot 安全告警并创建修复任务"
 
 ## 任务入参短号别名
 
-> 如果 `{task-id}` 入参以 `#` 开头，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。
+> 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。
 
 ## 执行流程
 
@@ -58,12 +58,12 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 更新 task.md：`current_step` -> `requirement-analysis`。
 - **追加**到 `## Activity Log`（不要覆盖之前的记录）：
   ```
-  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Import Dependabot Alert** by {agent} — Dependabot alert #{alert-number} imported
+  - {YYYY-MM-DD HH:mm:ss±HH:MM} — **Import Dependabot** by {agent} — Dependabot alert #{alert-number} imported
   ```
 
 ### 4. 完成校验
 
-**先调用短号分配**（保证 `short_id` 写回 task.md + 注册表 entry 已在；完成校验阶段会读取）：
+**先调用短号分配**（保证注册表 entry 已分配；完成校验阶段会读取）：
 
 ```bash
 node .agents/scripts/task-short-id.js alloc "$task_id"
@@ -88,7 +88,7 @@ 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。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）。
+> **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）。
 
 ```
 安全告警 #{alert-number} 已导入。
@@ -99,15 +99,15 @@ node .agents/scripts/validate-artifact.js gate import-dependabot .agents/workspa
 - 受影响包：{package-name}
 
 任务信息：
-- 任务 ID：{task-id}
+- 任务 ID：{task-id}（短号 {task-ref}）
 
 产出文件：
 - 任务文件：.agents/workspace/active/{task-id}/task.md
 
 下一步：
-  - Claude Code / OpenCode：/analyze-task {task-id}
-  - Gemini CLI：/agent-infra:analyze-task {task-id}
-  - Codex CLI：$analyze-task {task-id}
+  - Claude Code / OpenCode：/analyze-task {task-ref}
+  - Gemini CLI：/agent-infra:analyze-task {task-ref}
+  - Codex CLI：$analyze-task {task-ref}
 ```
 
 

package/templates/.agents/skills/import-dependabot/config/verify.json

@@ -17,7 +17,7 @@
       "expected_status": "active"
     },
     "activity-log": {
-      "expected_action_pattern": "Import Dependabot Alert",
+      "expected_action_pattern": "(Import Dependabot|Import Dependabot Alert)",
       "freshness_minutes": 30
     },
     "platform-sync": null

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

@@ -15,7 +15,7 @@ Import the specified Issue and create a task. Argument: issue number.
 
 ## Task id short ref
 
-> If `{task-id}` begins with `#`, 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.
+> 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.
 
 ## Execution Flow
 
@@ -123,7 +123,7 @@ If task.md contains a valid `issue_number`, perform these sync actions (skip and
 
 ### 7. Verification Gate
 
-**Allocate short id first** (writes `short_id` back to task.md and the registry entry; the validation gate will read it):
+**Allocate short id first** (ensures the registry entry is allocated; the validation gate will read it):
 
 ```bash
 node .agents/scripts/task-short-id.js alloc "$task_id"
@@ -148,13 +148,13 @@ 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).
+> **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).
 
 ```
 Issue #{number} imported.
 
 Task information:
-- Task ID: {task-id}
+- Task ID: {task-id} (short id {task-ref})
 - Title: {title}
 - Workflow: {workflow}
 
@@ -162,9 +162,9 @@ Output file:
 - Task file: .agents/workspace/active/{task-id}/task.md
 
 Next step - run requirements analysis:
-  - Claude Code / OpenCode: /analyze-task {task-id}
-  - Gemini CLI: /{{project}}:analyze-task {task-id}
-  - Codex CLI: $analyze-task {task-id}
+  - Claude Code / OpenCode: /analyze-task {task-ref}
+  - Gemini CLI: /{{project}}:analyze-task {task-ref}
+  - Codex CLI: $analyze-task {task-ref}
 ```
 
 

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

@@ -15,7 +15,7 @@ description: "从 Issue 导入并创建任务"
 
 ## 任务入参短号别名
 
-> 如果 `{task-id}` 入参以 `#` 开头，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。
+> 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。
 
 ## 执行流程
 
@@ -123,7 +123,7 @@ date "+%Y-%m-%d %H:%M:%S%:z"
 
 ### 7. 完成校验
 
-**先调用短号分配**（保证 `short_id` 写回 task.md + 注册表 entry 已在；完成校验阶段会读取）：
+**先调用短号分配**（保证注册表 entry 已分配；完成校验阶段会读取）：
 
 ```bash
 node .agents/scripts/task-short-id.js alloc "$task_id"
@@ -148,13 +148,13 @@ node .agents/scripts/validate-artifact.js gate import-issue .agents/workspace/ac
 
 > 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）。
+> **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）。
 
 ```
 Issue #{number} 已导入。
 
 任务信息：
-- 任务 ID：{task-id}
+- 任务 ID：{task-id}（短号 {task-ref}）
 - 标题：{title}
 - 工作流：{workflow}
 
@@ -162,9 +162,9 @@ Issue #{number} 已导入。
 - 任务文件：.agents/workspace/active/{task-id}/task.md
 
 下一步 - 执行需求分析：
-  - Claude Code / OpenCode：/analyze-task {task-id}
-  - Gemini CLI：/agent-infra:analyze-task {task-id}
-  - Codex CLI：$analyze-task {task-id}
+  - Claude Code / OpenCode：/analyze-task {task-ref}
+  - Gemini CLI：/agent-infra:analyze-task {task-ref}
+  - Codex CLI：$analyze-task {task-ref}
 ```