@fitlab-ai/agent-infra 0.5.8 → 0.5.9

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

@@ -1,118 +0,0 @@
----
-name: create-issue
-description: "Create an Issue from a task file"
----
-
-# Create Issue
-
-Create the base Issue from `task.md` and write `issue_number` back to the task.
-
-## Boundary / Critical Rules
-
-- Build the Issue title and body from `task.md` only
-- Issue title format: `type(scope): description` - map `type` from task.md (`feature` -> `feat`, `bugfix` -> `fix`, `refactor` -> `refactor`, `docs` -> `docs`, `chore` -> `chore`), infer scope from the affected module (omit it if unclear), and use the task title from task.md verbatim for the description (do not translate or rewrite)
-- Do not read `analysis.md`, `plan.md`, `implementation.md`, or review artifacts
-- The only durable outputs are the Issue and the `issue_number` update in task.md
-- After executing this skill, you **must** immediately update task.md
-
-## Steps
-
-### 1. Verify Prerequisites
-
-Check:
-- `.agents/workspace/active/{task-id}/task.md`
-- read `.agents/rules/issue-pr-commands.md` first, then follow its prerequisite steps to complete authentication and code-hosting platform detection
-
-If `issue_number` already exists and is not empty or `N/A`, confirm with the user before creating a replacement Issue.
-
-### 2. Extract Task Information
-
-Extract the title, `## Description`, `## Requirements`, `type`, and `milestone` from task.md. Build the Issue title by mapping task.md `type` to a Conventional Commits type, inferring scope, and formatting it as `cc_type(scope): task_title` or `cc_type: task_title` when scope is unclear. If task.md does not provide an explicit `milestone` field, infer it by following "Phase 1: `create-issue`" in `.agents/rules/milestone-inference.md`.
-
-### 3. Build Issue Content
-
-Detect Issue templates through `.agents/rules/issue-pr-commands.md` and decide whether to use a matched template path or the fallback path.
-
-> Template detection, field mapping for `textarea`, `input`, `dropdown`, and `checkboxes`, and the fallback body rules live in `reference/template-matching.md`. Read `reference/template-matching.md` before building the body.
-
-> Label filtering, Issue Type fallback, `issue-types` API handling, `milestone` logic, `--milestone`, and `in:` label rules live in `reference/label-and-type.md`. Read `reference/label-and-type.md` before creating the Issue.
-
-### 4. Create the Issue
-
-Create and enrich the Issue by following the "Create Issue" and "Set the Issue Type" sections in `.agents/rules/issue-pr-commands.md`. Omit label arguments when nothing valid remains.
-
-Handle labels, milestone, Issue Type, and assignee behavior by following the permission-degradation rules in `.agents/rules/issue-pr-commands.md` and `.agents/rules/issue-sync.md`.
-
-### 5. Update Task Status
-
-Get the current time:
-
-```bash
-date "+%Y-%m-%d %H:%M:%S%:z"
-```
-
-Write back `issue_number`, update `updated_at`, and append the Create Issue Activity Log entry.
-
-### 5.1 Backfill Existing Artifacts
-
-If artifact files already exist in the task directory, backfill them in this order:
-
-1. `task.md` -> the task comment marker defined in `.agents/rules/issue-sync.md` (idempotent create or update)
-2. Backfill existing `analysis*.md`, `plan*.md`, `implementation*.md`, `review*.md`, and `refinement*.md` files in filename order
-
-Every backfill action must follow the raw publishing, task.md sync, and chunking rules in `.agents/rules/issue-sync.md`.
-
-### 6. Verification Gate
-
-Run the verification gate to confirm the task artifact and sync state are valid:
-
-```bash
-node .agents/scripts/validate-artifact.js gate create-issue .agents/workspace/active/{task-id} --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.
-
-### 7. 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).
-
-Show the Issue number, URL, labels, Issue Type, milestone result, confirm that `issue_number` was written back, and include the next-step commands in every TUI format:
-
-```
-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}
-```
-
-## Completion Checklist
-
-- [ ] Created the Issue
-- [ ] Used `task.md` as the only content source
-- [ ] Recorded `issue_number` in task.md
-- [ ] Updated `updated_at` and appended the Activity Log entry
-- [ ] Included all TUI formats, including any custom TUIs, for the next-step commands
-
-## STOP
-
-Stop after the checklist. Do not start detailed progress sync here.
-
-## Notes
-
-- `create-issue` creates the base Issue; later status, comments, and checkboxes are maintained by workflow skills and platform automation
-- If no valid labels survive filtering, create the Issue without labels instead of failing
-- If Issue Type or milestone setup fails, continue and record the fallback outcome
-
-## Error Handling
-
-- Task not found: `Task {task-id} not found`
-- the platform CLI unavailable or unauthenticated
-- Empty description in task.md
-- Issue creation failure

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

@@ -1,118 +0,0 @@
----
-name: create-issue
-description: "从任务文件创建 Issue"
----
-
-# 创建 Issue
-
-仅从 `task.md` 创建基础 Issue，并把 `issue_number` 回写到任务文件。
-
-## 行为边界 / 关键规则
-
-- Issue 标题和正文只能来自 `task.md`
-- Issue 标题格式为 `type(scope): 描述`——type 从 task.md 的 `type` 字段映射（feature→feat, bugfix→fix, refactor→refactor, docs→docs, chore→chore），scope 从受影响模块推断（无法确定时省略），描述使用 task.md 中的任务标题原文（不要翻译或改写）
-- 不要读取 `analysis.md`、`plan.md`、`implementation.md` 或审查产物
-- 持久产物只有 Issue 本身，以及 task.md 中的 `issue_number` 更新
-- 执行本技能后，你**必须**立即更新 task.md
-
-## 执行步骤
-
-### 1. 验证前置条件
-
-检查：
-- `.agents/workspace/active/{task-id}/task.md`
-- 执行前先读取 `.agents/rules/issue-pr-commands.md`，并按其中的前置步骤完成认证和代码托管平台检测
-
-如果 `issue_number` 已存在且既不为空也不为 `N/A`，创建前必须先与用户确认。
-
-### 2. 提取任务信息
-
-从 task.md 提取标题、`## Description`、`## Requirements`、`type` 和 `milestone`。构造 Issue 标题：将 task.md 的 `type` 映射为 Conventional Commits type，推断 scope，拼接为 `cc_type(scope): task_title` 或 `cc_type: task_title`（scope 不确定时省略）。如果 task.md 没有显式 `milestone` 字段，按 `.agents/rules/milestone-inference.md` 的「阶段 1：`create-issue`」推断。
-
-### 3. 构建 Issue 内容
-
-通过 `.agents/rules/issue-pr-commands.md` 检测 Issue 模板，决定使用模板路径还是 fallback 路径。
-
-> 模板识别、`textarea`、`input`、`dropdown`、`checkboxes` 字段映射，以及 fallback 正文规则见 `reference/template-matching.md`。构建正文前先读取 `reference/template-matching.md`。
-
-> `labels:` 过滤、Issue Type fallback、`issue-types` API、`milestone` 逻辑、`--milestone` 和 `in:` label 规则见 `reference/label-and-type.md`。创建 Issue 前先读取 `reference/label-and-type.md`。
-
-### 4. 创建 Issue
-
-按 `.agents/rules/issue-pr-commands.md` 中的 “创建 Issue” 与 “Issue Type 设置” 规则创建并补充 Issue；如果没有有效 label，就省略 label 参数。
-
-Label、milestone、Issue Type 和 assignee 的具体处理方式，都按 `.agents/rules/issue-pr-commands.md` 与 `.agents/rules/issue-sync.md` 中的权限降级规则执行。
-
-### 5. 更新任务状态
-
-获取当前时间：
-
-```bash
-date "+%Y-%m-%d %H:%M:%S%:z"
-```
-
-回写 `issue_number`，更新 `updated_at`，并追加 Create Issue 的 Activity Log。
-
-### 5.1 补发已有产物
-
-如果任务目录中已存在产物文件，按以下顺序补发：
-
-1. `task.md` → `.agents/rules/issue-sync.md` 中定义的 task 评论标记（幂等创建或更新）
-2. 按文件名排序补发已存在的 `analysis*.md`、`plan*.md`、`implementation*.md`、`review*.md`、`refinement*.md`
-
-所有补发动作都必须遵循 `.agents/rules/issue-sync.md` 的原文发布、task.md 同步和分片规则。
-
-### 6. 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 create-issue .agents/workspace/active/{task-id} --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。
-
-### 7. 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）。
-
-展示 Issue 编号、URL、labels、Issue Type、milestone 结果，确认 `issue_number` 已回写，并完整输出所有 TUI 里的下一步命令：
-
-```
-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}
-```
-
-## 完成检查清单
-
-- [ ] 已创建 Issue
-- [ ] 已仅使用 `task.md` 作为内容来源
-- [ ] 已在 task.md 中记录 `issue_number`
-- [ ] 已更新 `updated_at` 并追加 Activity Log
-- [ ] 已输出所有 TUI 格式的下一步命令（含自定义 TUI）
-
-## 停止
-
-完成检查清单后立即停止。不要在本技能里继续做详细进度同步。
-
-## 注意事项
-
-- `create-issue` 只负责创建基础 Issue；后续状态、评论和复选框由工作流技能与 platform automation 维护
-- 如果过滤后没有有效 label，允许不带 label 创建 Issue
-- 如果 Issue Type 或 milestone 设置失败，继续执行并记录结果
-
-## 错误处理
-
-- 任务未找到：`Task {task-id} not found`
-- the platform CLI 不可用或未认证
-- task.md 的描述为空
-- 创建 Issue 失败

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

@@ -1,30 +0,0 @@
-{
-  "skill": "create-issue",
-  "checks": {
-    "task-meta": {
-      "required_fields": [
-        "id",
-        "type",
-        "workflow",
-        "status",
-        "created_at",
-        "updated_at",
-        "current_step",
-        "assigned_to"
-      ],
-      "require_issue_number": true
-    },
-    "activity-log": {
-      "expected_action_pattern": "Create Issue",
-      "freshness_minutes": 30
-    },
-    "platform-sync": {
-      "when": "issue_number_exists",
-      "issue_must_exist": true,
-      "verify_task_comment_content": true,
-      "verify_issue_type": true,
-      "verify_milestone": true,
-      "expected_status_label_key": "waitingForTriage"
-    }
-  }
-}

package/templates/.agents/skills/create-issue/reference/label-and-type.en.md

@@ -1,71 +0,0 @@
-# Labels, Issue Type, and Milestone Rules
-
-Read this file before applying labels, Issue Type, milestone, or `in:` labels.
-
-## Default Body Format (Fallback)
-
-Recommended fallback:
-
-```markdown
-## Description
-
-{task-description}
-
-## Requirements
-
-- [ ] {requirement-1}
-- [ ] {requirement-2}
-```
-
-Map task types to labels and Issue Types, but keep only labels that actually exist.
-
-Fallback label mapping:
-
-| task.md type | label |
-|---|---|
-| `bug`, `bugfix` | `type: bug` |
-| `feature` | `type: feature` |
-| `enhancement` | `type: enhancement` |
-| `docs`, `documentation` | `type: documentation` |
-| `dependency-upgrade` | `type: dependency-upgrade` |
-| `task`, `chore` | `type: task` |
-| `refactor`, `refactoring` | `type: enhancement` |
-| other values | skip |
-
-Issue Type fallback mapping:
-
-| task.md type | Issue Type |
-|---|---|
-| `bug`, `bugfix` | `Bug` |
-| `feature`, `enhancement` | `Feature` |
-| `task`, `documentation`, `dependency-upgrade`, `chore`, `docs`, `refactor`, `refactoring`, and all other values | `Task` |
-
-## Create the Issue
-
-Before creating the Issue, read `.agents/rules/issue-pr-commands.md` and use its "Create an Issue" command template.
-
-Before calling the creation command, follow `.agents/rules/issue-sync.md` / `.agents/rules/issue-pr-commands.md` to complete the prerequisite authentication and code-hosting platform detection steps.
-
-If no valid labels remain, omit label arguments.
-
-For milestone inference, read `.agents/rules/milestone-inference.md` and follow "Phase 1: `create-issue`" before creating the Issue.
-
-Issue Type setup follows the matching commands in `.agents/rules/issue-pr-commands.md`.
-
-- handle direct writes for labels, milestones, `in:` labels, and Issue Type by following the permission-degradation rules in `.agents/rules/issue-pr-commands.md` and `.agents/rules/issue-sync.md`
-- when those rules say to skip a direct write, continue without failing Issue creation
-
-`in:` labels (coarse selection):
-
-Prepare label edit arguments by following the Issue update command in `.agents/rules/issue-pr-commands.md`.
-
-Use the returned labels to do semantic matching against the task.md title and description:
-- add a label when the task **explicitly mentions** a module (for example, "fix CLI argument parsing" -> `in: cli`)
-- add a label when the task **strongly implies** a module
-- skip the label when the mapping is ambiguous or uncertain
-
-Principle: prefer missing labels over wrong labels. Coarse selection does not need to be perfect because implement-task / create-pr will refine `in:` labels from actual changed files later.
-
-Handle relevant `in:` labels by following the permission-degradation rules in `.agents/rules/issue-sync.md`. Do not fail Issue creation when `in:` labels are unavailable, irrelevant, or skipped by those rules.
-
-Skip unavailable labels, Issue Types, or milestones without failing the Issue creation flow.

package/templates/.agents/skills/create-issue/reference/label-and-type.zh-CN.md

@@ -1,71 +0,0 @@
-# Label、Issue Type 和 Milestone 规则
-
-在应用 label、Issue Type、milestone 或 `in:` label 之前先读取本文件。
-
-## 默认正文格式（Fallback）
-
-推荐 fallback：
-
-```markdown
-## Description
-
-{task-description}
-
-## Requirements
-
-- [ ] {requirement-1}
-- [ ] {requirement-2}
-```
-
-将任务类型映射到 label 和 Issue Type，但只保留仓库里实际存在的 label。
-
-Fallback label 映射：
-
-| task.md type | label |
-|---|---|
-| `bug`, `bugfix` | `type: bug` |
-| `feature` | `type: feature` |
-| `enhancement` | `type: enhancement` |
-| `docs`, `documentation` | `type: documentation` |
-| `dependency-upgrade` | `type: dependency-upgrade` |
-| `task`, `chore` | `type: task` |
-| `refactor`, `refactoring` | `type: enhancement` |
-| 其他值 | 跳过 |
-
-Issue Type fallback 映射：
-
-| task.md type | Issue Type |
-|---|---|
-| `bug`, `bugfix` | `Bug` |
-| `feature`, `enhancement` | `Feature` |
-| `task`, `documentation`, `dependency-upgrade`, `chore`, `docs`, `refactor`, `refactoring` 以及其他所有值 | `Task` |
-
-## 创建 Issue
-
-创建 Issue 时，执行前先读取 `.agents/rules/issue-pr-commands.md`，并使用其中的 “创建 Issue” 命令模板。
-
-调用创建命令前，先按 `.agents/rules/issue-sync.md` / `.agents/rules/issue-pr-commands.md` 完成前置步骤中的认证和代码托管平台检测。
-
-如果最终没有有效 label，就省略 label 参数。
-
-Milestone 推断规则见 `.agents/rules/milestone-inference.md` 的「阶段 1：`create-issue`」。推断前先读取该文件。
-
-Issue Type 设置同样遵循 `.agents/rules/issue-pr-commands.md` 中的对应命令。
-
-- Label、milestone、`in:` label 和 Issue Type 的直接设置，都按 `.agents/rules/issue-pr-commands.md` 与 `.agents/rules/issue-sync.md` 的权限降级规则处理
-- 当规则判定应跳过直接写入时，继续创建 Issue，不要让流程失败
-
-`in:` label（粗选）：
-
-执行前先按 `.agents/rules/issue-pr-commands.md` 的 Issue 更新命令准备 label 编辑参数。
-
-从查询结果中，根据 task.md 的标题和描述进行语义匹配：
-- 任务描述**明确提及**某个模块（如"修复 CLI 参数解析"→ `in: cli`）→ 添加
-- 任务描述**强烈暗示**某个模块 → 添加
-- 无法确定或模糊 → **不添加**
-
-原则：宁缺毋滥。粗选阶段不求精确，后续 implement-task / create-pr 阶段会基于实际改动文件精修。
-
-相关 `in:` label 的添加按 `.agents/rules/issue-sync.md` 的权限降级规则处理。当 `in:` label 不可用、不相关或规则判定应跳过时，不要让创建 Issue 流程失败。
-
-当 label、Issue Type 或 milestone 不可用时，应跳过并继续，不要让 Issue 创建失败。

package/templates/.agents/skills/create-issue/reference/template-matching.en.md

@@ -1,17 +0,0 @@
-# Issue Template Matching
-
-Read this file before deciding how to build the Issue body.
-
-## Detect Issue Templates
-
-Issue template detection is platform-specific. Read `.agents/rules/issue-pr-commands.md` and follow the template detection section provided by the configured platform.
-
-If templates exist, inspect their top-level names and choose the best match for the task title and description. Use the candidate template guidance provided by the configured platform rule when available.
-
-If no template matches clearly, choose the nearest candidate. If templates are missing, unreadable, or parsing fails, fall back to the default body path.
-
-## Build the Body from the Matched Template
-
-Build the body by following the field handling and field mapping guidance provided by the configured platform section in `.agents/rules/issue-pr-commands.md`.
-
-When platform guidance is unavailable, use the default body path.

package/templates/.agents/skills/create-issue/reference/template-matching.zh-CN.md

@@ -1,17 +0,0 @@
-# Issue 模板匹配
-
-在决定如何构建 Issue 正文前先读取本文件。
-
-## 检测 Issue 模板
-
-Issue 模板检测属于平台相关逻辑。先读取 `.agents/rules/issue-pr-commands.md`，并按当前配置平台提供的模板检测章节执行。
-
-如果存在模板，检查其顶层名称，并根据任务标题和描述选择最匹配的模板。可用时，使用当前配置平台规则提供的候选模板指引。
-
-如果没有清晰匹配，选择最接近的候选模板。模板不存在、无法读取或解析失败时，回退到默认正文路径。
-
-## 从匹配模板构建正文
-
-按 `.agents/rules/issue-pr-commands.md` 中当前配置平台章节提供的字段处理和字段映射指引构建正文。
-
-如果平台指引不可用，使用默认正文路径。

package/templates/.claude/commands/create-issue.en.md

@@ -1,8 +0,0 @@
----
-description: "Create an Issue from a task file"
-usage: "/create-issue <task-id>"
----
-
-Read and execute the create-issue skill from `.agents/skills/create-issue/SKILL.md`.
-
-Follow all steps defined in the skill exactly.

package/templates/.claude/commands/create-issue.zh-CN.md

@@ -1,8 +0,0 @@
----
-description: "从任务文件创建 Issue"
-usage: "/create-issue <task-id>"
----
-
-读取并执行 `.agents/skills/create-issue/SKILL.md` 中的 create-issue 技能。
-
-严格按照技能中定义的所有步骤执行。

package/templates/.gemini/commands/_project_/create-issue.en.toml

@@ -1,8 +0,0 @@
-description = "Create an Issue from a task file"
-prompt = """
-Create Issue for task {{args}}.
-
-Read and execute the create-issue skill from `.agents/skills/create-issue/SKILL.md`.
-
-Follow all steps defined in the skill exactly.
-"""

package/templates/.gemini/commands/_project_/create-issue.zh-CN.toml

@@ -1,8 +0,0 @@
-description = "从任务文件创建 Issue"
-prompt = """
-为任务 {{args}} 创建 Issue。
-
-读取并执行 `.agents/skills/create-issue/SKILL.md` 中的 create-issue 技能。
-
-严格按照技能中定义的所有步骤执行。
-"""

package/templates/.opencode/commands/create-issue.en.md

@@ -1,11 +0,0 @@
----
-description: "Create an Issue from a task file"
-agent: general
-subtask: false
----
-
-Create Issue for task $1.
-
-Read and execute the create-issue skill from `.agents/skills/create-issue/SKILL.md`.
-
-Follow all steps defined in the skill exactly.

package/templates/.opencode/commands/create-issue.zh-CN.md

@@ -1,11 +0,0 @@
----
-description: "从任务文件创建 Issue"
-agent: general
-subtask: false
----
-
-为任务 $1 创建 Issue。
-
-读取并执行 `.agents/skills/create-issue/SKILL.md` 中的 create-issue 技能。
-
-严格按照技能中定义的所有步骤执行。