task-reviewer-skill

审查者 Skill — 通过 CLI 工具审查子任务、评分、驳回返工

1,061 stars

Best use case

task-reviewer-skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

审查者 Skill — 通过 CLI 工具审查子任务、评分、驳回返工

Teams using task-reviewer-skill should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/task-reviewer-skill/SKILL.md --create-dirs "https://raw.githubusercontent.com/uluckyXH/OpenMOSS/main/skills/task-reviewer-skill/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/task-reviewer-skill/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How task-reviewer-skill Compares

Feature / Agenttask-reviewer-skillStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

审查者 Skill — 通过 CLI 工具审查子任务、评分、驳回返工

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Task Reviewer Skill

你可以使用 `task-cli.py` 工具来审查子任务。该工具位于本 Skill 目录下。

## 认证信息

- API_KEY: `<注册后填入>`

## 工作流程

1. 获取规则 → 2. 检查积分 → 3. 查看待审查子任务 → 4. 逐个审查 → 5. 提交审查记录 → 6. 发送评分详情到群聊 → 7. 记录日志

## 可用命令

> 所有命令前缀:`python task-cli.py --key <API_KEY>`

### 规则

```bash
rules                                     # 获取合并后的规则提示词(执行前必须调用)
```

### 子任务查看

```bash
st list --status review                   # 查看待审查的子任务
st get <sub_task_id>                      # 查看子任务详情(交付物、验收标准)
```

### 审查操作

```bash
# 通过审查
review create <sub_task_id> approved <评分1-5> --comment "评价内容"

# 驳回返工
review create <sub_task_id> rejected <评分1-5> --comment "评价" --issues "问题描述"

# 查看审查历史
review list --sub-task-id <id>
review get <review_id>                    # 查看单条审查详情
```

> 📄 列表命令默认返回全部数据。如数据较多,可加 `--page N --page-size M` 分页查看。返回结果包含 `total`(总数)和 `has_more`(是否还有更多)。

### Agent 查看

```bash
agents                                    # 查看已注册 Agent(ID、角色、状态、积分)
agents --role executor                    # 按角色过滤,查看所有执行者
```

> 💡 审查时可通过 `agents` 获取 Agent ID,用于 `score adjust` 加分/扣分。

### 积分

```bash
score me                                  # 查看自己的积分
score logs --page 1 --page-size 10        # 查看积分明细(建议分页,避免数据过多)
score agent-logs <agent_id> --page 1 --page-size 10  # 查看指定 Agent 的积分明细(审查前了解历史表现)
score leaderboard                         # 积分排行榜
score adjust <agent_id> <分数> "原因"      # 手动加分/扣分(正数加分,负数扣分)
score adjust <agent_id> -5 "未按时交付" --sub-task-id <id>  # 关联子任务扣分
```

> 📄 `score logs` 默认返回全部明细。如数据较多,可加 `--page N --page-size M` 分页查看。

### 通知

```bash
notification                              # 查看通知渠道配置
```

### 日志

```bash
log create "review" "审查了xxx子任务,评分4/5" --sub-task-id <id>
log mine                                  # 回顾工作记录(默认最近7天,最多20条)
log mine --action reflection              # 只看自省笔记
log list --sub-task-id <id>               # 查看某子任务的所有日志
log list --sub-task-id <id> --action delivery  # 查看执行者交付摘要
log list --days 30 --limit 50             # 最近30天,最多50条
```

## 注意事项

- 每次执行前先运行 `rules` 获取最新规则
- 每次唤醒时检查 `score logs`,分析自己的审查表现
- 审查时严格对照验收标准,评分客观一致
- 驳回时 `--issues` 必填,清楚描述问题以便执行者修复
- 每次审查后将评分详情发送到通知渠道:「审查结果:子任务名 | 执行者 | 评分 ⭐x/5 | 评价」
- 无待审查任务时本次唤醒结束

Related Skills

task-planner-skill

1061
from uluckyXH/OpenMOSS

任务规划师 Skill — 通过 CLI 工具创建任务、拆分模块、分配子任务

task-patrol-skill

1061
from uluckyXH/OpenMOSS

巡查 Skill — 通过 CLI 工具巡查任务状态、标记异常、发送告警

task-executor-skill

1061
from uluckyXH/OpenMOSS

任务执行者 Skill — 通过 CLI 工具领取子任务、提交成果、处理返工

wordpress-skill

1061
from uluckyXH/OpenMOSS

WordPress 站点管理 Skill — 通过 CLI 工具管理文章、页面、媒体、分类、标签和搜索

local-web-search

1061
from uluckyXH/OpenMOSS

Use when the user asks for web search that should run via the local-160 Responses API with web_search tool (base URL like https://proxy.example.com, model gpt-5.2-codex(xhigh)). Includes script to query the local endpoint and return summary + citations; use for periodic news monitoring and on-demand searches.

antigravity-gemini-image

1061
from uluckyXH/OpenMOSS

Generate or edit images using the Antigravity-hosted Gemini image model via the local gateway. Use when the user asks to create an image, generate an avatar, or edit/transform an existing image with text instructions. Supports text-to-image and image-to-image editing.

azure-resource-manager-durabletask-dotnet

31392
from sickn33/antigravity-awesome-skills

Azure Resource Manager SDK for Durable Task Scheduler in .NET.

Pitch Deck Reviewer

3891
from openclaw/skills

Reviews pitch decks and provides investor-ready feedback with scoring

Business Strategy & Growth

afrexai-code-reviewer

3891
from openclaw/skills

Enterprise-grade code review agent. Reviews PRs, diffs, or code files for security vulnerabilities, performance issues, error handling gaps, architecture smells, and test coverage. Works with any language, any repo, no dependencies required.

Coding & Development

task-decomposer

3891
from openclaw/skills

Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.

Workflow & Productivity

task-intelligence

31355
from sickn33/antigravity-awesome-skills

Protocolo de Inteligência Pré-Tarefa — ativa TODOS os agentes relevantes do ecossistema ANTES de executar qualquer tarefa solicitada pelo usuário.

web-design-reviewer

28865
from github/awesome-copilot

This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "fix the layout", "find design problems". Detects issues with responsive design, accessibility, visual consistency, and layout breakage, then performs fixes at the source code level.