Install
$ agentstack add skill-gaojiongwenv587-beep-threads-skills-threads-batch-reply ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ● Filesystem access Used
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
threads-batch-reply — 批量回覆助手
透過 GUI 弹窗逐條填寫評論,自動執行 reply-thread,結果匯總回報。
🚫 內容禁區(最高優先級)
絕對禁止生成、分析或互動任何政治相關內容。遇到政治相關帖子直接跳過。
語言規則(強制)
所有 AI 生成的回覆內容一律使用繁體中文,不得使用简体中文。
工作流程
第一步:拉取目標帖子
# 從首頁 Feed 取帖
python scripts/cli.py list-feeds --limit 30
# 或按關鍵詞搜尋
python scripts/cli.py search --query "設計系統" --type recent --limit 20
第二步:篩選帖子,寫入臨時文件
從 CLI 輸出中取出目標帖子(按互動量、話題等篩選),寫成 JSON 文件:
import json, tempfile, pathlib
posts = [...] # 篩選後的帖子子集,格式同 CLI 輸出的 posts 陣列
tmp = pathlib.Path(tempfile.mktemp(suffix=".json", prefix="threads_batch_"))
tmp.write_text(json.dumps(posts, ensure_ascii=False), encoding="utf-8")
print(tmp) # 輸出臨時文件路徑供下一步使用
每條帖子需包含以下欄位(直接使用 CLI 輸出即可):
{
"postId": "DVxppvZCAAl",
"url": "https://www.threads.net/@user/post/DVxppvZCAAl",
"author": { "username": "someuser", "displayName": "顯示名稱" },
"content": "帖子正文",
"likeCount": "1,234",
"replyCount": "56"
}
第三步:啟動批量回覆助手
啟動前先確保 tkinter 可用(不可用則自動安裝):
python3 -c "import tkinter" 2>/dev/null || brew install python-tk@3.13
GUI 可用時(有彈窗界面):
uv run python scripts/reply_assistant.py --posts-file /tmp/threads_batch_xxx.json
# 多帳號:
uv run python scripts/reply_assistant.py --posts-file /tmp/threads_batch_xxx.json --account myaccount
tkinter 不可用時(終端交互):
uv run python scripts/reply_assistant_cli.py --posts-file /tmp/threads_batch_xxx.json
# 多帳號:
uv run python scripts/reply_assistant_cli.py --posts-file /tmp/threads_batch_xxx.json --account myaccount
> ⚠️ 腳本路徑固定為 scripts/reply_assistant.py 和 scripts/reply_assistant_cli.py,不要去其他目錄找。
兩個版本的 --posts-file、--account、--port 參數完全相同,輸出的摘要 JSON 格式也一致。
第四步:讀取結果 JSON,匯報給用戶
腳本完成後向 stdout 輸出摘要:
{
"total": 10,
"replied": 3,
"skipped": 5,
"already_replied": 2,
"replied_ids": ["DVxppvZCAAl", "DVxHauYk1YQ", "DVxWF-hiayK"]
}
向用戶報告:成功回覆 N 條、跳過 M 條、已回覆過 K 條。
GUI 弹窗操作說明
┌──────────────────────────────────────────┐
│ 批量回覆 3 / 10 @bigbigburger1 │
├──────────────────────────────────────────┤
│ 帖子正文(可滾動) │
│ ❤️ 1,234 💬 56 │
├──────────────────────────────────────────┤
│ ┌────────────────────────────────────┐ │
│ │ 在此輸入評論... │ │
│ └────────────────────────────────────┘ │
│ 字符: 0 / 500 │
├──────────────────────────────────────────┤
│ [ 發布 ] [ 跳過 ] [ 結束 ] │
└──────────────────────────────────────────┘
| 按鈕 | 快捷鍵 | 行為 | |------|--------|------| | 發布 | Ctrl+Enter | 提交評論,執行 reply-thread | | 跳過 | Esc / 關閉視窗 | 跳過當前帖子,繼續下一條 | | 結束 | — | 立即退出,剩餘帖子標記為 skipped |
- 輸入為空或超 500 字符時「發布」按鈕自動置灰
- 已回覆過的帖子自動跳過(不彈窗)
前置條件
- Chrome 已啟動並登入 Threads:
python scripts/chrome_launcher.py
python scripts/cli.py check-login
- 檢查 tkinter,不可用時自動安裝:
python3 -c "import tkinter" 2>/dev/null || (echo "正在安裝 tkinter..." && brew install python-tk@3.13 && echo "安裝完成")
安裝後再次驗證:
python3 -c "import tkinter" 2>/dev/null && echo "GUI可用,用 reply_assistant.py" || echo "安裝失敗,改用 reply_assistant_cli.py"
失敗處理
| 錯誤 | 原因 | 處理 | |------|------|------| | 無法連接 Chrome | Chrome 未啟動或端口不符 | 執行 chrome_launcher.py,確認 --port 參數 | | 未登錄 | Cookie 失效 | 執行 python scripts/cli.py login | | tkinter 無法導入 | 缺少 tk 依賴 | brew install python-tk | | 回覆未成功 | 頁面未渲染 / 選擇器失效 | 稍後重試;若持續失敗執行 inspector.py 驗證選擇器 |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: gaojiongwenv587-beep
- Source: gaojiongwenv587-beep/threads-skills
- License: MIT
- Homepage: https://openclaw.dev
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.