@fitlab-ai/agent-infra 0.6.5 → 0.7.0

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

@@ -1,173 +0,0 @@
----
-name: implement-task
-description: "Implement a task from its technical plan and output a report"
----
-
-# Implement Task
-
-Implement the approved task and produce `implementation.md` or `implementation-r{N}.md`.
-
-## Boundary / Critical Rules
-
-- Follow the latest approved plan artifact: `plan.md` or `plan-r{N}.md`
-- Never auto-run `git add` or `git commit`
-- Create a new implementation artifact for each round and never overwrite an older one
-- After executing this skill, you **must** immediately update task.md
-
-Version stamp rule: when creating or updating `task.md` frontmatter, read `.agents/rules/version-stamp.md` first and write or refresh `agent_infra_version`.
-
-## Common Rationalizations and Rebuttals
-
-Before implementing, stop if any of these thoughts appear. They are violations:
-
-| Rationalization | Rebuttal |
-|------|------|
-| "The code is too simple to need tests." | Simple code still regresses; without a failing-to-passing case there is no completion signal, so write a test that verifies business behavior first. |
-| "Writing code first and adding tests later is faster." | Tests added after implementation often mirror the implementation; goal-driven work defines the verifiable case first and then makes it pass. |
-| "This plan is flawed, so I will improve it as I go." | Deviations from `{plan-artifact}` must be recorded in the report; if the direction is questionable, stop and confirm instead of changing it silently. |
-| "The tests passed, so I can commit this too." | This skill never runs `git add` or `git commit`; committing is a separate step explicitly requested by the user. |
-
-## Step 0: State Check (pre-execution hard gate)
-
-After loading workflow / skill / rules instructions, and before any task-state judgment or user-visible conclusion, run the state check first. Reading instruction files does not count as an external-state action or conclusion.
-
-Run these commands and paste the raw output into both the user-facing reply and this round's `## State Check` section:
-
-```bash
-git status -s
-ls -la .agents/workspace/active/{task-id}/
-tail .agents/workspace/active/{task-id}/task.md
-```
-
-Before the state check is complete, do not make external-state assertions such as "the code is unchanged", "tests passed", or "there are no other references", including in reasoning. This gate is only a structural floor; evidence pairing and authenticity still require the report template and review discipline.
-
-## Steps
-
-### 1. Verify Prerequisites
-
-Check these files first:
-- `.agents/workspace/active/{task-id}/task.md`
-- At least one technical plan artifact: `plan.md` or `plan-r{N}.md`
-
-If either file is missing, stop and ask the user to complete the prerequisite step.
-
-### 2. Ensure the Task Branch
-
-Read the branch field in `## Context` from `task.md` and check whether the current Git branch matches it.
-
-- if a task branch is already recorded, switch to it when the current branch does not match
-- if no branch is recorded, check whether the current branch follows the naming convention and belongs to this task
-  - if yes: record the current branch and continue
-  - if no: create and switch to a new task branch that follows the naming rule
-
-After this step, write the final branch name back to `task.md`.
-
-> Branch naming rules, Git commands, and edge-case handling live in `reference/branch-management.md`. Read `reference/branch-management.md` before executing this step.
-
-### 3. Narrow the Milestone
-
-If task.md contains a valid `issue_number`, read `.agents/rules/issue-sync.md` first to complete upstream repository detection plus permission detection; then read `.agents/rules/milestone-inference.md` and follow "Phase 2: `implement-task`" to narrow the Issue milestone before implementation starts; if `has_triage=false`, keep the current milestone unchanged.
-
-### 4. Determine the Input Plan and Implementation Round
-
-Scan `.agents/workspace/active/{task-id}/` and record:
-- the highest-round plan file as `{plan-artifact}`
-- the next implementation artifact as `implementation.md` or `implementation-r{N}.md`
-- `{implementation-round}` and `{implementation-artifact}`
-
-If any `plan-r{N}.md` exists, read the highest-round plan file. Otherwise read `plan.md`.
-
-### 5. Read the Technical Plan
-
-Read `{plan-artifact}` carefully and extract:
-- implementation steps
-- files to create or modify
-- test strategy
-- constraints, risks, and any approved tradeoffs
-
-### 6. Implement the Code
-
-Follow `.agents/workflows/feature-development.yaml` and the plan in order.
-
-> Detailed implementation rules, the test execution loop, and deviation handling live in `reference/implementation-rules.md`. Read `reference/implementation-rules.md` before executing this step.
-> Test-writing discipline (RED-GREEN-REFACTOR and anti-patterns) lives in `.agents/rules/testing-discipline.md`; read it before adding or changing tests.
-
-### 7. Run Test Verification
-
-Use the project test command from the `test` skill and keep iterating until all required tests pass.
-
-If tests fail, Attempt to fix the issue and re-run tests first. Only stop when you confirm an external blocker, missing environment, or unclear requirement that is out of scope for the task.
-
-### 8. Write the Implementation Report
-
-Create `.agents/workspace/active/{task-id}/{implementation-artifact}`.
-
-> Report structure, required sections, and the full template live in `reference/report-template.md`. Read `reference/report-template.md` before writing the report.
-
-### 9. Update Task Status
-
-Get the current time:
-
-```bash
-date "+%Y-%m-%d %H:%M:%S%:z"
-```
-
-Update `.agents/workspace/active/{task-id}/task.md`:
-- `current_step`: implementation
-- `assigned_to`: {current agent}
-- `updated_at`: {current time}
-- `agent_infra_version`: value from `.agents/rules/version-stamp.md`
-- review the `## Requirements` section and only change items from `- [ ]` to `- [x]` when they are clearly satisfied by this round's implemented code and passing tests
-- record `{implementation-artifact}` for Round `{implementation-round}`
-- append:
-  `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Implementation (Round {N})** by {agent} — Code implemented, {n} files modified, {n} tests passed → {implementation-artifact}`
-
-If task.md contains a valid `issue_number`, perform these sync actions (skip and continue on any failure; read `.agents/rules/issue-sync.md` first and complete upstream repository detection plus permission detection):
-- Set `status: in-progress` by following issue-sync.md
-- Create or update the task comment marker defined in `.agents/rules/issue-sync.md` (follow the task.md comment sync rule in issue-sync.md)
-- Publish the `{implementation-artifact}` comment
-
-### 10. Verification Gate
-
-Run the verification gate to confirm the task artifact and sync state are valid:
-
-```bash
-node .agents/scripts/validate-artifact.js gate implement-task .agents/workspace/active/{task-id} {implementation-artifact} --format text
-```
-
-Handle the result as follows:
-- exit code 0 (all checks passed) -> continue to the "Inform User" step
-- exit code 1 (validation failed) -> fix the reported issues and run the gate again
-- exit code 2 (network blocked) -> stop and tell the user that human intervention is required
-
-Keep the gate output in your reply as fresh evidence. Do not claim completion without output from this run.
-
-### 11. Inform User
-
-> 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). Use the output template in `reference/output-template.md`.
-
-## Completion Checklist
-
-- [ ] Implemented the approved code changes
-- [ ] Created `{implementation-artifact}`
-- [ ] All required tests passed
-- [ ] Updated task.md and appended the Activity Log entry
-- [ ] Included every TUI command format, including any custom TUIs, in the user-facing next step
-
-## STOP
-
-Stop after the checklist is complete. Do not auto-commit.
-
-## Notes
-
-- Round 1 uses `implementation.md`; later rounds use `implementation-r{N}.md`
-- Record any deviation from `{plan-artifact}` in the report
-- New tests must validate meaningful business behavior, not just passthrough data
-
-## Error Handling
-
-- Task not found: `Task {task-id} not found`
-- Missing plan: `Technical plan not found, please run the plan-task skill first`
-- Test failure after local fixes: explain the external blocker and stop without creating the implementation artifact

package/templates/.agents/skills/implement-task/reference/output-template.en.md

@@ -1,20 +0,0 @@
-# Output Template
-
-When reporting that implementation is complete, use the following standard format:
-
-```text
-Task {task-id} implementation complete.
-
-Summary:
-- Implementation round: Round {implementation-round}
-- Files modified: {count}
-- All tests passed: {yes/no}
-
-Output files:
-- Implementation report: .agents/workspace/active/{task-id}/{implementation-artifact}
-
-Next step - code review:
-  - Claude Code / OpenCode: /review-task {task-id}
-  - Gemini CLI: /{{project}}:review-task {task-id}
-  - Codex CLI: $review-task {task-id}
-```

package/templates/.agents/skills/implement-task/reference/output-template.zh-CN.md

@@ -1,20 +0,0 @@
-# 输出模板
-
-向用户汇报实现完成时，使用以下标准格式：
-
-```text
-任务 {task-id} 实现完成。
-
-摘要：
-- 实现轮次：Round {implementation-round}
-- 修改文件：{数量}
-- 所有测试通过：{是/否}
-
-产出文件：
-- 实现报告：.agents/workspace/active/{task-id}/{implementation-artifact}
-
-下一步 - 代码审查：
-  - Claude Code / OpenCode：/review-task {task-id}
-  - Gemini CLI：/{{project}}:review-task {task-id}
-  - Codex CLI：$review-task {task-id}
-```

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

@@ -1,153 +0,0 @@
----
-name: refine-task
-description: "Handle code review feedback and fix issues"
----
-
-# Refine Task
-
-Fix review findings and produce `refinement.md` or `refinement-r{N}.md`.
-
-## Boundary / Critical Rules
-
-- Fix only the issues documented in review artifacts
-- env-blocked findings are outside the repair scope: the refinement report must preserve them and record "outside AI repair scope (environment-blocked)" instead of making no-op edits to clear the report
-- Never auto-run `git add` or `git commit`
-- After executing this skill, you **must** immediately update task.md
-
-Version stamp rule: when creating or updating `task.md` frontmatter, read `.agents/rules/version-stamp.md` first and write or refresh `agent_infra_version`.
-
-## Common Rationalizations and Rebuttals
-
-| Rationalization | Rebuttal |
-|------|------|
-| "This review comment is wrong, so I will ignore it." | If you disagree, record the reason under unresolved issues in the report; do not silently skip blocker or major findings. |
-| "I can clean up nearby code while I am here." | Scope is limited to review findings; changes outside that scope are out of bounds. |
-| "Clearing env-blocked items makes the report look better." | env-blocked findings are outside the repair scope; preserve and label them truthfully, and never use no-op edits to pad the fix count. |
-
-## Step 0: State Check (pre-execution hard gate)
-
-After loading workflow / skill / rules instructions, and before any task-state judgment or user-visible conclusion, run the state check first. Reading instruction files does not count as an external-state action or conclusion.
-
-Run these commands and paste the raw output into both the user-facing reply and this round's `## State Check` section:
-
-```bash
-git status -s
-ls -la .agents/workspace/active/{task-id}/
-tail .agents/workspace/active/{task-id}/task.md
-```
-
-Before the state check is complete, do not make external-state assertions such as "the code is unchanged", "tests passed", or "there are no other references", including in reasoning. This gate is only a structural floor; evidence pairing and authenticity still require the report template and review discipline.
-
-## Steps
-
-### 1. Verify Prerequisites
-
-Require:
-- `.agents/workspace/active/{task-id}/task.md`
-- at least one review artifact: `review.md` or `review-r{N}.md`
-
-During prerequisite discovery, record `{review-artifact}`, `{refinement-round}`, `{refinement-artifact}`, and Record `{implementation-artifact}` from the latest implementation report.
-
-Also validate the latest Code Review entry in Activity Log. If it points to a missing file, stop with:
-`Review artifact mismatch: Activity Log references {expected} but file not found. Please verify the review artifact exists.`
-
-### 2. Read Review and Implementation Context
-
-Read the latest `{review-artifact}` and `{implementation-artifact}` before editing any code.
-
-### 3. Plan and Apply the Fixes
-
-Prioritize Blocker -> Major -> Minor and keep changes tightly scoped.
-
-> The detailed fix workflow, repair order, and verification loop live in `reference/fix-workflow.md`. Read `reference/fix-workflow.md` before making changes.
-
-### 4. Run Test Verification
-
-Run the project test command after the fixes and keep the repair cycle focused on the documented findings.
-
-### 5. Write the Refinement Report
-
-Create `.agents/workspace/active/{task-id}/{refinement-artifact}`.
-
-> The report structure and example sections live in `reference/report-template.md`. Read `reference/report-template.md` before writing the report.
-
-### 6. Update Task Status
-
-Get the current time:
-
-```bash
-date "+%Y-%m-%d %H:%M:%S%:z"
-```
-
-Update task.md:
-- review the `## Requirements` section and only change items from `- [ ]` to `- [x]` when they are newly satisfied by this round's fixes and passing tests
-- preserve explicit optional Issue field metadata (`priority`, `effort`, `start_date`, `target_date`); only infer `priority` or `effort` from clear review context, and do not invent dates
-- append:
-  `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Refinement (Round {N}, for {review-artifact})** by {agent} — Fixed {n} blockers, {n} major, {n} minor issues[, skipped {n} env-blocked] → {refinement-artifact}`
-
-Append `, skipped {n} env-blocked` when env-blocked > 0; omit it when env-blocked = 0.
-
-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
-- Set `status: in-progress` by following issue-sync.md
-- Create or update the task comment marker defined in `.agents/rules/issue-sync.md` (follow the task.md comment sync rule in issue-sync.md)
-- Publish the `{refinement-artifact}` comment
-
-### 7. Verification Gate
-
-Run the verification gate to confirm the task artifact and sync state are valid:
-
-```bash
-node .agents/scripts/validate-artifact.js gate refine-task .agents/workspace/active/{task-id} {refinement-artifact} --format text
-```
-
-Handle the result as follows:
-- exit code 0 (all checks passed) -> continue to the "Inform User" step
-- exit code 1 (validation failed) -> fix the reported issues and run the gate again
-- exit code 2 (network blocked) -> stop and tell the user that human intervention is required
-
-Keep the gate output in your reply as fresh evidence. Do not claim completion without output from this run.
-
-### 8. Inform User
-
-> 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).
-
-After summarizing the fixes, present the next step:
-
-```
-Next step - re-review or commit:
-- Re-review (always recommended):
-  - Claude Code / OpenCode: /review-task {task-id}
-  - Gemini CLI: /{{project}}:review-task {task-id}
-  - Codex CLI: $review-task {task-id}
-- Commit directly (optional; only when all issues are resolved and changes are low risk):
-  - Claude Code / OpenCode: /commit
-  - Gemini CLI: /{{project}}:commit
-  - Codex CLI: $commit
-```
-
-## Completion Checklist
-
-- [ ] Read the latest review and implementation context
-- [ ] Fixed all required Blocker and Major findings
-- [ ] Wrote `{refinement-artifact}`
-- [ ] Updated task.md and appended the Activity Log entry
-- [ ] Recommended the correct next step based on residual risk
-
-## Notes
-
-- Round 1 uses `refinement.md`; later rounds use `refinement-r{N}.md`
-- Record any disagreement with a review comment under unresolved issues in the report
-- Do not expand scope beyond the review findings
-
-## STOP
-
-Stop after the checklist is complete.
-
-## Error Handling
-
-- Task not found: `Task {task-id} not found`
-- Missing review report: `Review report not found, please run the review-task skill first`
-- Review artifact mismatch: `Review artifact mismatch: Activity Log references {expected} but file not found. Please verify the review artifact exists.`

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

@@ -1,153 +0,0 @@
----
-name: refine-task
-description: "处理代码审查反馈并修复问题"
----
-
-# 修复审查问题
-
-修复审查发现的问题，并产出 `refinement.md` 或 `refinement-r{N}.md`。
-
-## 行为边界 / 关键规则
-
-- 只修复审查产物中记录的问题
-- env-blocked 项不在修复范围内：refinement 报告必须如实保留这些项并记录“不在 AI 修复范围（环境性遗留）”，不能为了清空报告做 no-op 改动
-- 绝不自动执行 `git add` 或 `git commit`
-- 执行本技能后，你**必须**立即更新 task.md
-
-版本戳规则：创建或更新 `task.md` frontmatter 时，先读取 `.agents/rules/version-stamp.md`，并写入或刷新 `agent_infra_version`。
-
-## 常见违规借口与反驳
-
-| 借口 | 反驳 |
-|------|------|
-| 「这条审查意见不合理，直接忽略」 | 不同意要在报告的未解决问题中写明理由，不能静默跳过 blocker/major。 |
-| 「顺手把旁边也优化了」 | 范围严格限定在审查项内，范围外改动属于越界。 |
-| 「env-blocked 项清掉报告好看」 | env-blocked 不在修复范围，必须如实保留并标注，禁止 no-op 改动充数。 |
-
-## 第 0 步：状态核对（执行前硬约束）
-
-在加载 workflow / skill / rules 指令之后、做任何任务状态判断或用户可见结论之前，必须先执行状态核对。指令类文件读取不算对外动作或结论。
-
-运行以下命令，并把原文粘贴到回复正文和本轮产物的 `## 状态核对` 段：
-
-```bash
-git status -s
-ls -la .agents/workspace/active/{task-id}/
-tail .agents/workspace/active/{task-id}/task.md
-```
-
-状态核对完成前，禁止任何关于外部状态的断言（例如“代码没变”“测试已通过”“没有其他引用”），包括思考阶段。本门禁只提供结构下限；逐条证据配对和真实性仍需按报告模板与审查要求核对。
-
-## 执行步骤
-
-### 1. 验证前置条件
-
-要求存在：
-- `.agents/workspace/active/{task-id}/task.md`
-- 至少一个审查产物：`review.md` 或 `review-r{N}.md`
-
-在前置检查阶段必须记录 `{review-artifact}`、`{refinement-round}`、`{refinement-artifact}`，并从最新实现报告中记录 `{implementation-artifact}`。
-
-同时校验 Activity Log 中最近一条 Code Review 记录；如果引用了不存在的文件，立即停止并输出：
-`Review artifact mismatch: Activity Log references {expected} but file not found. Please verify the review artifact exists.`
-
-### 2. 阅读审查与实现上下文
-
-在修改代码前先读取最新的 `{review-artifact}` 和 `{implementation-artifact}`。
-
-### 3. 规划并执行修复
-
-按 Blocker -> Major -> Minor 的顺序处理，始终保持改动聚焦。
-
-> 详细修复流程、优先级和验证循环见 `reference/fix-workflow.md`。执行此步骤前先读取 `reference/fix-workflow.md`。
-
-### 4. 运行测试验证
-
-修复后运行项目测试命令，并把修复范围限制在审查结论内。
-
-### 5. 编写修复报告
-
-创建 `.agents/workspace/active/{task-id}/{refinement-artifact}`。
-
-> 报告结构和示例章节见 `reference/report-template.md`。写报告前先读取 `reference/report-template.md`。
-
-### 6. 更新任务状态
-
-获取当前时间：
-
-```bash
-date "+%Y-%m-%d %H:%M:%S%:z"
-```
-
-更新 task.md：
-- 审查 `## 需求` 段落，仅把因本轮修复而新满足且有测试通过支撑的条目从 `- [ ]` 勾为 `- [x]`
-- 保留明确填写的可选 Issue 字段元数据（`priority`、`effort`、`start_date`、`target_date`）；仅在审查上下文非常明确时推断 `priority` 或 `effort`，不要臆测日期
-- 追加：
-  `- {YYYY-MM-DD HH:mm:ss±HH:MM} — **Refinement (Round {N}, for {review-artifact})** by {agent} — Fixed {n} blockers, {n} major, {n} minor issues[, skipped {n} env-blocked] → {refinement-artifact}`
-
-env-blocked > 0 时附加 `, skipped {n} env-blocked`；env-blocked = 0 时省略。
-
-如果 task.md 中存在有效的 `issue_number`，执行以下同步操作（任一失败则跳过并继续）：
-- 执行前先读取 `.agents/rules/issue-sync.md`，完成 upstream 仓库检测和权限检测
-- 按 issue-sync.md 设置 `status: in-progress`
-- 创建或更新 `.agents/rules/issue-sync.md` 中定义的 task 评论标记（按 issue-sync.md 的 task.md 评论同步规则）
-- 发布 `{refinement-artifact}` 评论
-
-### 7. 完成校验
-
-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 refine-task .agents/workspace/active/{task-id} {refinement-artifact} --format text
-```
-
-处理结果：
-- 退出码 0（全部通过）-> 继续到「告知用户」步骤
-- 退出码 1（校验失败）-> 根据输出修复问题后重新运行校验
-- 退出码 2（网络中断）-> 停止执行并告知用户需要人工介入
-
-将校验输出保留在回复中作为当次验证输出。没有当次校验输出，不得声明完成。
-
-### 8. 告知用户
-
-> 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）。
-
-输出修复摘要后，展示下一步：
-
-```
-下一步 - 重新审查或提交：
-- 重新审查（始终推荐）：
-  - Claude Code / OpenCode：/review-task {task-id}
-  - Gemini CLI：/agent-infra:review-task {task-id}
-  - Codex CLI：$review-task {task-id}
-- 直接提交（可选；仅在所有问题已解决且风险可控时）：
-  - Claude Code / OpenCode：/commit
-  - Gemini CLI：/agent-infra:commit
-  - Codex CLI：$commit
-```
-
-## 完成检查清单
-
-- [ ] 已读取最新审查与实现上下文
-- [ ] 已修复所有必需的 Blocker 和 Major 问题
-- [ ] 已写出 `{refinement-artifact}`
-- [ ] 已更新 task.md 并追加 Activity Log
-- [ ] 已根据剩余风险推荐正确的下一步
-
-## 注意事项
-
-- 首轮修复使用 `refinement.md`，后续轮次使用 `refinement-r{N}.md`
-- 若不同意审查意见，要在报告的未解决问题中记录理由
-- 不要把范围扩展到审查项之外
-
-## 停止
-
-完成检查清单后立即停止。
-
-## 错误处理
-
-- 任务未找到：`Task {task-id} not found`
-- 缺少审查报告：`Review report not found, please run the review-task skill first`
-- 审查产物不一致：`Review artifact mismatch: Activity Log references {expected} but file not found. Please verify the review artifact exists.`

package/templates/.agents/skills/refine-task/reference/report-template.en.md

@@ -1,64 +0,0 @@
-# Refinement Report Template
-
-Use this structure when writing `refinement.md` or `refinement-r{N}.md`.
-
-## Output Template
-
-```markdown
-# Refinement Report
-
-- **Refinement Round**: Round {refinement-round}
-- **Artifact File**: `{refinement-artifact}`
-- **Review Input**: `{review-artifact}`
-- **Implementation Context**: `{implementation-artifact}`
-
-## State Check
-
-> Paste the raw state-check command output; each command starts with `$ `.
-
-### Review Feedback Handling
-
-#### Blocker Fixes
-1. **{issue-title}**
-   - **Fix**: {what changed}
-   - **File**: `{file-path}:{line-number}`
-   - **Validation**: {validation}
-
-#### Major Issue Fixes
-1. **{issue-title}**
-   - **Fix**: {what changed}
-   - **File**: `{file-path}:{line-number}`
-
-#### Minor Issue Handling
-1. **{issue-title}**
-   - **Fix**: {what changed}
-
-#### Environment-Blocked Handling
-
-> These findings are outside AI repair scope and do not count toward repair totals. Preserve them unchanged and identify the maintainer verification path.
-
-1. **{issue-title}**
-   - **Status**: skipped (outside AI repair scope)
-   - **Required Environment**: {e.g. Docker sandbox / macOS host / third-party account}
-   - **Maintainer Verification Steps**: {steps}
-
-> If this round has no env-blocked findings, keep the subsection heading and write "None".
-
-#### Unresolved Issues
-- {issue}: {reason}
-
-
-## Evidence
-
-> Pair each "I verified X" claim with the corresponding raw tool output; the gate only checks that this section exists and at least one `$ ` line is present.
-
-- Claim: {verified claim}
-```text
-$ {command}
-{raw output}
-```
-
-### Test Results After Refinement
-- All tests passing: {yes/no}
-- Test output: {summary}
-```

package/templates/.agents/skills/refine-task/reference/report-template.zh-CN.md

@@ -1,64 +0,0 @@
-# 修复报告模板
-
-编写 `refinement.md` 或 `refinement-r{N}.md` 时，使用以下结构。
-
-## 输出模板
-
-```markdown
-# 修复报告
-
-- **修复轮次**: Round {refinement-round}
-- **产物文件**: `{refinement-artifact}`
-- **审查输入**: `{review-artifact}`
-- **实现上下文**: `{implementation-artifact}`
-
-## 状态核对
-
-> 粘贴状态核对命令原文；每条命令以 `$ ` 开头。
-
-### 审查反馈处理
-
-#### 阻塞项修复
-1. **{issue-title}**
-   - **修复**: {what changed}
-   - **文件**: `{file-path}:{line-number}`
-   - **验证**: {validation}
-
-#### 主要问题修复
-1. **{issue-title}**
-   - **修复**: {what changed}
-   - **文件**: `{file-path}:{line-number}`
-
-#### 次要问题处理
-1. **{issue-title}**
-   - **修复**: {what changed}
-
-#### 环境性遗留处理
-
-> 这些项不在 AI 修复范围；不计入修复总数。仅原样保留并指明维护者后续验证路径。
-
-1. **{issue-title}**
-   - **状态**：跳过（不在 AI 修复范围）
-   - **所需环境**：{e.g. Docker 沙箱 / macOS host / 第三方账号}
-   - **维护者验证步骤**：{steps}
-
-> 如本轮无 env-blocked 项，保留小节标题并写「（无）」。
-
-#### 未解决问题
-- {issue}: {reason}
-
-
-## 证据原文
-
-> 每条“我验证了 X”断言都要配对对应 tool output 原文；gate 仅校验本段存在和至少一行 `$ `。
-
-- 断言：{verified claim}
-```text
-$ {command}
-{raw output}
-```
-
-### 修复后的测试结果
-- 所有测试通过: {yes/no}
-- 测试输出: {summary}
-```