← Back to Skills Marketplace
openclawchen8-lgtm

Ideas2tasks

by gentoobreaking · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
111
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install ideas2tasks
Description
將 /Users/claw/Ideas 中的臨時想法自動分類、拆解為敏捷專案任務。 觸發條件:用戶提到「idea轉task」「ideas2tasks」「想法拆分」「專案規劃」「task管理」, 或要求掃描 Ideas 目錄、建立專案任務、分配團隊成員。
README (SKILL.md)

ideas2tasks — 想法轉敏捷任務

核心概念

將零散的想法(ideas)系統化轉為可執行的專案任務(tasks),搭配虛擬 Scrum 團隊成員分工執行。

📂 目錄結構

/Users/claw/Ideas/           # 臨時想法存放區
  ├── *.txt                  # 待處理的 idea 檔案
  └── _done/                 # 已處理歸檔區(自動移入)

/Users/claw/Tasks/           # 專案任務區
  └── \x3Cproject-name>/
      ├── README.md          # 專案概覽、成員分工、進度
      └── tasks/
          ├── T001.md        # 個別任務檔案
          ├── T002.md
          └── ...

👥 團隊成員

角色 名稱 OpenClaw Agent ID Workspace
Planner 豪(用戶本人) main /Users/claw/.qclaw/workspace/
Coder 1 碼農 1 號 agent-coder1 ~/.qclaw/workspace-coder1/
Coder 2 碼農 2 號 agent-coder2 ~/.qclaw/workspace-coder2/
DocWriter 安安 agent-ann ~/.qclaw/workspace-ann/
Reviewer 樂樂 agent-lele ~/.qclaw/workspace-lele/

Spawn 方式:sessions_spawn(agentId="agent-ann") 等,詳見各成員的 IDENTITY.md/SOUL.md。

🔄 完整流程

步驟 1:掃描 Ideas

掃描 /Users/claw/Ideas/*.txt,排除 _done/ 子目錄。 空檔案(0 bytes)跳過不處理。

步驟 2:分析與分類

閱讀每個 idea 檔案的內容,判斷:

  • 歸屬哪個專案(新專案或已有專案)
  • 涉及哪些技術領域
  • 優先級(高/中/低)

步驟 3:拆分 Tasks

  • 每個 idea 最多拆成 10 個 tasks
  • 若超過 10 個,先說明原因和拆分方式,等用戶確認後再拆
  • 每個 task 應具備明確的完成條件

步驟 4:專案命名

  • 從 idea 內容提取關鍵字作為專案名稱
  • 發給用戶確認後才執行
  • 命名風格:英文、簡短、見名知義(如 gold-monitorbackup-system

步驟 5:建立專案結構

確認後建立目錄和檔案:

/Users/claw/Tasks/\x3Cproject-name>/README.md
/Users/claw/Tasks/\x3Cproject-name>/tasks/T001.md ~ T0xx.md

步驟 6:分配任務

根據 task 類型分配給對應成員:

  • 開發/腳本 → Coder 1 或 Coder 2
  • 文檔撰寫 → DocWriter
  • 驗收/審核 → Reviewer
  • 規劃/協調 → Planner(豪)

步驟 7:歸檔 Idea 檔案

將已處理的 .txt 移到 /Users/claw/Ideas/_done/

mkdir -p /Users/claw/Ideas/_done
mv /Users/claw/Ideas/\x3Cfilename>.txt /Users/claw/Ideas/_done/

📝 Task 檔案格式

每個 task md 檔案格式:

---
id: T001
project: \x3Cproject-name>
title: \x3C任務標題>
assignee: \x3C成員名稱>
priority: high|medium|low
status: pending|in-progress|review|done
created: YYYY-MM-DD
updated: YYYY-MM-DD
---

## 描述
\x3C任務詳細說明>

## 完成條件
- [ ] \x3C具體可驗證的條件 1>
- [ ] \x3C具體可驗證的條件 2>

## 產出
\x3C預期產出物:腳本、文檔、配置等>

## 備註
\x3C補充說明>

📊 專案 README 格式

# \x3C專案名稱>

## 概覽
\x3C專案簡述>

## 團隊分工
| 角色 | 成員 | 負責 Tasks |
|------|------|-----------|
| Planner | 寶寶 | T001, T005 |
| Coder 1 | 碼農 1 號 | T002, T003 |
| DocWriter | 安安 | T004 |
| Reviewer | 樂樂 | 全部 |

## 進度
- 總 tasks: N
- 已完成: X
- 進行中: Y
- 待處理: Z

## Task 列表
| ID | 標題 | 負責人 | 狀態 | 優先級 |
|----|------|--------|------|--------|
| T001 | ... | ... | pending | high |

⏰ Lifecycle(每日定時)

cron 每天 09:00 Asia/Taipei 執行:

  1. 執行 scripts/lifecycle.py(掃描 → 分類 → 彙整摘要)
  2. 結果寫入 scripts/lifecycle_status.json(供 AI 讀取)
  3. 有待處理 tasks → 發送摘要到 Telegram,請豪確認
  4. 無新 idea → 安靜(不通知)

⚠️ 重要規則

  1. 專案命名必須先確認 — 不可未確認就直接建立目錄
  2. Task 拆分上限 10 個 — 超過需說明原因並等確認
  3. 已標記 done 的 idea task — 檔案內含 "done" 的行視為已完成,整體仍需分析是否還有未完成項
  4. 歸檔不刪除 — 移到 _done/ 而非刪除
  5. 空檔案跳過 — 0 bytes 的 .txt 不處理

🔧 狀態同步系統(v2.1.0)

核心問題修復

問題: 兩套狀態系統不同步

  • Ideas/*.txttask.N done 標記
  • Tasks/*/tasks/T*.mdStatus: done
  • Agent 完成後只改 T*.md → idea 檔未同步 → 重複建立

解決方案:

1. 統一狀態讀取(task_status.py

  • 正規化讀取(忽略大小寫、emoji、空白)
  • 統一寫入格式:Status: pending / in-progress / done

2. 狀態同步器(sync_status.py

  • Task 完成 → 自動更新 idea 檔的 task.N done 標記
  • 提供手動同步工具:python3 sync_status.py --fix-history

3. Task 完成掛鉤(task_completion_hook.py

  • Agent 完成時呼叫
  • 同步更新 Tasks/ 和 Ideas/ 的狀態
  • 用法:python3 task_completion_hook.py /path/to/T001.md

4. Lifecycle 增強

  • 優先看 Tasks/ 目錄的實際狀態
  • 合併判斷:Tasks/ 已 done → 覆蓋 idea 檔狀態

維護命令

# 檢查同步狀態(預覽)
python3 sync_status.py --dry-run

# 修復歷史不一致
python3 sync_status.py --fix-history

# 掃描專案狀態
python3 task_status.py /Users/claw/Tasks/\x3Cproject-name>

# 手動標記 task 完成(同時同步 idea 檔)
python3 task_completion_hook.py /Users/claw/Tasks/\x3Cproject>/tasks/T001.md

詳見:docs/STATUS_SYNC_FIX.md

Usage Guidance
Before installing or running this skill, review and test locally rather than running it on your main account: 1) Inspect scripts (lifecycle.py, executor.py, sync_status.py, task_completion_hook.py) yourself to confirm the actions are acceptable (they will move files into _done/ and modify task/README files). 2) Run in dry-run modes first (many scripts support --dry-run) and back up /Users/claw/Ideas and /Users/claw/Tasks. 3) Be aware the code will attempt to send Telegram messages and call the gh CLI to create GitHub issues — ensure TELEGRAM_BOT_TOKEN / TELEGRAM_CHAT_ID and gh credentials are intentionally provided; if you don't want remote actions, unset those envs and remove/disable GitHub sync code. 4) Note the executor uses subprocess with shell=True; ensure task titles or idea contents cannot be manipulated to inject shell commands in your environment. 5) If you will allow cron or automated runs, prefer running inside an isolated environment/container or a dedicated user with limited access. 6) If anything is unclear or you need the skill to avoid external sync, ask the author to (a) declare required env vars, (b) avoid shell=True usage or use subprocess with argument lists, and (c) document exactly when files will be moved or network calls made.
Capability Analysis
Type: OpenClaw Skill Name: ideas2tasks Version: 1.0.1 The ideas2tasks skill bundle automates project management by scanning local directories (/Users/claw/Ideas) and syncing tasks with GitHub and Telegram. A significant security vulnerability exists in scripts/executor.py, which uses subprocess.run with shell=True to execute GitHub CLI commands; because task titles and project names are incorporated into these commands without rigorous sanitization, it presents a high risk of Shell Injection. While the external communications (Telegram API and GitHub) and broad filesystem access are consistent with the tool's stated purpose, the insecure execution pattern and the potential for an AI agent to be manipulated into processing malicious 'ideas' make this bundle suspicious.
Capability Assessment
Purpose & Capability
The core purpose (scan /Users/claw/Ideas, create /Users/claw/Tasks, split ideas into tasks and archive processed files) aligns with the code and SKILL.md. However the code also implements optional integrations (Telegram notifications, GitHub Issue/Board sync via the gh CLI, creation of GitHub blob URLs) that are not declared in the skill metadata or requires.env. These integrations are plausibly related (reporting / issue sync) but should have been declared up-front.
Instruction Scope
Runtime instructions and shipped scripts will read and write user files under /Users/claw (Ideas, Tasks), move files into _done/, create and update README and task files, spawn agents (mapped agent IDs) and send external network requests (Telegram API) and call the GitHub CLI. SKILL.md mentions scanning, creating tasks, archiving, sending Telegram, and spawning agents, but it does not mention GitHub CLI usage, nor does it declare that it will read ~/.qclaw/gold_monitor_config.json. The code also contains logic to update files permanently — e.g., shutil.move — so data will be modified/moved on disk. The skill's instructions are not fully explicit about required credentials and side effects.
Install Mechanism
No install spec — this is instruction+script bundle. No network-based installer or archive download. That reduces supply-chain concerns; risk comes from running included scripts, not from an installer.
Credentials
The code reads environment variables TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID and falls back to a config file at ~/.qclaw/gold_monitor_config.json; it also expects the gh CLI to run (implying GitHub credentials available to gh). None of these credentials/config paths are declared in the skill metadata. Requesting access to Telegram/GitHub auth is plausible for notifications and issue sync, but the absence of declared required env vars and the presence of a fallback config path are inconsistent and increase surprise/risk.
Persistence & Privilege
always:false and model invocation allowed (default). The skill writes to the user's filesystem (creates/moves files) and recommends daily cron execution; it does not request forced permanent inclusion. These file writes are coherent with the purpose, but the ability to spawn agents and invoke external network operations combined with file modifications increases the operational impact if misused. No evidence it modifies other skills' configs.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ideas2tasks
  3. After installation, invoke the skill by name or use /ideas2tasks
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Big update: Adds status sync system to fix state inconsistency between ideas and tasks. - Status sync tools introduced: `task_status.py`, `sync_status.py`, and `task_completion_hook.py` to keep Ideas/*.txt and Tasks/*/tasks/T*.md statuses consistent. - When task files mark as done, idea files are now automatically updated. - Manual and automatic sync/repair commands now available (see `docs/STATUS_SYNC_FIX.md`). - Several maintenance scripts and documentation files added. - Team agent IDs updated for consistency. - Lifecycle and project status logic enhanced to prioritize actual Tasks/ status and prevent duplicate creation.
v1.0.0
ideas2tasks v1.0.0 — 初始發佈 - 將 `/Users/claw/Ideas` 目錄下的臨時想法自動分類、拆解為敏捷專案任務,並支援團隊成員分工。 - 定義專案與任務目錄結構,支持自動建立、分配與進度追蹤。 - 每日定時掃描、分類並產生摘要,任務狀態寫回 json,並發送通知給用戶。 - 任務拆分上限 10 項,專案命名及拆分需用戶確認,已處理想法自動歸檔。 - 支持多角色分工(Planner, Coder, DocWriter, Reviewer),並制定嚴謹處理規則。
Metadata
Slug ideas2tasks
Version 1.0.1
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is Ideas2tasks?

將 /Users/claw/Ideas 中的臨時想法自動分類、拆解為敏捷專案任務。 觸發條件:用戶提到「idea轉task」「ideas2tasks」「想法拆分」「專案規劃」「task管理」, 或要求掃描 Ideas 目錄、建立專案任務、分配團隊成員。 It is an AI Agent Skill for Claude Code / OpenClaw, with 111 downloads so far.

How do I install Ideas2tasks?

Run "/install ideas2tasks" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Ideas2tasks free?

Yes, Ideas2tasks is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Ideas2tasks support?

Ideas2tasks is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Ideas2tasks?

It is built and maintained by gentoobreaking (@openclawchen8-lgtm); the current version is v1.0.1.

💬 Comments