@fitlab-ai/agent-infra 0.6.4 → 0.7.0

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}
-```

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

@@ -1,42 +0,0 @@
-# Review Criteria
-
-Read this file before reviewing code or classifying findings.
-
-## Perform Code Review
-
-Follow the `code-review` step in `.agents/workflows/feature-development.yaml`.
-
-**Required review areas**:
-- [ ] code quality and coding standards
-- [ ] bug and risk detection
-- [ ] test coverage and test quality
-- [ ] error handling and edge cases
-- [ ] performance and security concerns
-- [ ] code comments and documentation
-- [ ] alignment with the technical plan
-
-**Review principles**:
-1. **Strict but fair**: point out problems and also acknowledge good work
-2. **Specific**: cite exact file paths and line numbers
-3. **Actionable**: suggest a concrete fix
-4. **Severity-based**: distinguish blockers, major issues, and minor improvements
-
-## Environment-Blocked Classification
-
-Some findings cannot be closed by the AI agent in the current execution environment, for example:
-
-- missing Docker / sandbox access for end-to-end verification
-- missing a specific OS (macOS-only behavior)
-- missing a third-party account / OAuth access
-- missing privileged operations (root, sudo, special network access)
-
-**Classification decision tree**: "Can the AI agent close this without changing the environment?"
-- yes -> one of blocker / major / minor (based on risk)
-- no -> **env-blocked** (a meta-category, not part of severity ordering)
-
-Where env-blocked findings go:
-- record them in the independent review report section "Environment-Blocked Findings"
-- append them to the end of numeric summaries (for example, `(+ 1 env-blocked)`)
-- do **not** send them into the refine loop; maintainers carry them in the PR description as a "manual verification required" checklist
-
-Also inspect `git diff` so the report reflects the full change context.

package/templates/.claude/commands/implement-task.en.md

@@ -1,8 +0,0 @@
----
-description: "Implement a task from its technical plan and output a report"
-usage: "/implement-task <task-id>"
----
-
-Read and execute the implement-task skill from `.agents/skills/implement-task/SKILL.md`.
-
-Follow all steps defined in the skill exactly.

package/templates/.claude/commands/implement-task.zh-CN.md

@@ -1,8 +0,0 @@
----
-description: "根据技术方案实施任务并输出报告"
-usage: "/implement-task <task-id>"
----
-
-读取并执行 `.agents/skills/implement-task/SKILL.md` 中的 implement-task 技能。
-
-严格按照技能中定义的所有步骤执行。

package/templates/.claude/commands/refine-task.en.md

@@ -1,8 +0,0 @@
----
-description: "Handle code review feedback and fix issues"
-usage: "/refine-task <task-id>"
----
-
-Read and execute the refine-task skill from `.agents/skills/refine-task/SKILL.md`.
-
-Follow all steps defined in the skill exactly.

package/templates/.claude/commands/refine-task.zh-CN.md

@@ -1,8 +0,0 @@
----
-description: "处理代码审查反馈并修复问题"
-usage: "/refine-task <task-id>"
----
-
-读取并执行 `.agents/skills/refine-task/SKILL.md` 中的 refine-task 技能。
-
-严格按照技能中定义的所有步骤执行。

package/templates/.claude/commands/review-task.en.md

@@ -1,8 +0,0 @@
----
-description: "Review a task implementation and output a code review report"
-usage: "/review-task <task-id>"
----
-
-Read and execute the review-task skill from `.agents/skills/review-task/SKILL.md`.
-
-Follow all steps defined in the skill exactly.

package/templates/.claude/commands/review-task.zh-CN.md

@@ -1,8 +0,0 @@
----
-description: "审查任务实现并输出代码审查报告"
-usage: "/review-task <task-id>"
----
-
-读取并执行 `.agents/skills/review-task/SKILL.md` 中的 review-task 技能。
-
-严格按照技能中定义的所有步骤执行。

package/templates/.gemini/commands/_project_/implement-task.en.toml

@@ -1,8 +0,0 @@
-description = "Implement a task from its technical plan and output a report"
-prompt = """
-Implement task {{args}}.
-
-Read and execute the implement-task skill from `.agents/skills/implement-task/SKILL.md`.
-
-Follow all steps defined in the skill exactly.
-"""

package/templates/.gemini/commands/_project_/implement-task.zh-CN.toml

@@ -1,8 +0,0 @@
-description = "根据技术方案实施任务并输出报告"
-prompt = """
-实施任务 {{args}}。
-
-读取并执行 `.agents/skills/implement-task/SKILL.md` 中的 implement-task 技能。
-
-严格按照技能中定义的所有步骤执行。
-"""

package/templates/.gemini/commands/_project_/refine-task.en.toml

@@ -1,8 +0,0 @@
-description = "Handle code review feedback and fix issues"
-prompt = """
-Refine task {{args}}.
-
-Read and execute the refine-task skill from `.agents/skills/refine-task/SKILL.md`.
-
-Follow all steps defined in the skill exactly.
-"""

package/templates/.gemini/commands/_project_/refine-task.zh-CN.toml

@@ -1,8 +0,0 @@
-description = "处理代码审查反馈并修复问题"
-prompt = """
-修复任务 {{args}} 的审查问题。
-
-读取并执行 `.agents/skills/refine-task/SKILL.md` 中的 refine-task 技能。
-
-严格按照技能中定义的所有步骤执行。
-"""

package/templates/.gemini/commands/_project_/review-task.en.toml

@@ -1,8 +0,0 @@
-description = "Review a task implementation and output a code review report"
-prompt = """
-Review task {{args}}.
-
-Read and execute the review-task skill from `.agents/skills/review-task/SKILL.md`.
-
-Follow all steps defined in the skill exactly.
-"""

package/templates/.gemini/commands/_project_/review-task.zh-CN.toml

@@ -1,8 +0,0 @@
-description = "审查任务实现并输出代码审查报告"
-prompt = """
-审查任务 {{args}}。
-
-读取并执行 `.agents/skills/review-task/SKILL.md` 中的 review-task 技能。
-
-严格按照技能中定义的所有步骤执行。
-"""

package/templates/.opencode/commands/implement-task.en.md

@@ -1,11 +0,0 @@
----
-description: "Implement a task from its technical plan and output a report"
-agent: general
-subtask: false
----
-
-Implement task $1.
-
-Read and execute the implement-task skill from `.agents/skills/implement-task/SKILL.md`.
-
-Follow all steps defined in the skill exactly.

package/templates/.opencode/commands/implement-task.zh-CN.md

@@ -1,11 +0,0 @@
----
-description: "根据技术方案实施任务并输出报告"
-agent: general
-subtask: false
----
-
-实施任务 $1。
-
-读取并执行 `.agents/skills/implement-task/SKILL.md` 中的 implement-task 技能。
-
-严格按照技能中定义的所有步骤执行。

package/templates/.opencode/commands/refine-task.en.md

@@ -1,11 +0,0 @@
----
-description: "Handle code review feedback and fix issues"
-agent: general
-subtask: false
----
-
-Refine task $1.
-
-Read and execute the refine-task skill from `.agents/skills/refine-task/SKILL.md`.
-
-Follow all steps defined in the skill exactly.

package/templates/.opencode/commands/refine-task.zh-CN.md

@@ -1,11 +0,0 @@
----
-description: "处理代码审查反馈并修复问题"
-agent: general
-subtask: false
----
-
-修复任务 $1 的审查问题。
-
-读取并执行 `.agents/skills/refine-task/SKILL.md` 中的 refine-task 技能。
-
-严格按照技能中定义的所有步骤执行。

package/templates/.opencode/commands/review-task.en.md

@@ -1,11 +0,0 @@
----
-description: "Review a task implementation and output a code review report"
-agent: general
-subtask: false
----
-
-Review task $1.
-
-Read and execute the review-task skill from `.agents/skills/review-task/SKILL.md`.
-
-Follow all steps defined in the skill exactly.

package/templates/.opencode/commands/review-task.zh-CN.md

@@ -1,11 +0,0 @@
----
-description: "审查任务实现并输出代码审查报告"
-agent: general
-subtask: false
----
-
-审查任务 $1。
-
-读取并执行 `.agents/skills/review-task/SKILL.md` 中的 review-task 技能。
-
-严格按照技能中定义的所有步骤执行。