taskboard-cli
by ckouder
Lightweight task management CLI for multi-agent workflows. SQLite backend, no external dependencies or credentials. Status-change hooks emit agent instructions (message, session) but do not auto-execute. Use when managing tasks across agents, tracking work status, assigning tasks, generating board summaries, or orchestrating cross-agent handoffs. Triggers on \"create task\", \"task board\", \"taskboard\", \"list tasks\", \"assign task\", \"board summary\", \"project tasks\".
安装
claude skill add --url github.com/openclaw/skills/tree/main/skills/ckouder/taskboard-cli文档
Taskboard CLI
SQLite-backed task management for multi-agent projects. No network calls, no credentials, no environment variables.
Quick Start
# Create tasks
python3 scripts/taskboard.py create "Build auth" --assign code-engineer --priority high
python3 scripts/taskboard.py create "Design UI" --assign designer --criteria "Responsive, mobile-first"
# Manage tasks
python3 scripts/taskboard.py update 1 --status in_progress --author code-engineer
python3 scripts/taskboard.py comment 1 "PR #42 ready" --author code-engineer
python3 scripts/taskboard.py update 1 --status done --author code-engineer --note "Merged to main"
# View board
python3 scripts/taskboard.py list --status in_progress
python3 scripts/taskboard.py show 1
python3 scripts/taskboard.py show 1 --json
python3 scripts/taskboard.py summary
# Subtasks
python3 scripts/taskboard.py create "Write tests" --parent 1 --assign code-engineer
# Thread linking
python3 scripts/taskboard.py set-thread 1 1484268803994026085
python3 scripts/taskboard.py get-thread 1
# Change history
python3 scripts/taskboard.py history 1
Custom Database Path
By default the database lives at scripts/taskboard.db. Override with --db:
python3 scripts/taskboard.py --db /path/to/my.db list
Task Statuses
todo → in_progress → done
Also: blocked, rejected
No "review" status — use hooks to create follow-up tasks or notify agents.
Hooks (Cross-Agent Orchestration)
Hooks fire when task status changes. They print instructions to stdout for the calling agent to execute — no auto-execution, no network calls.
# When task is started (ack'd), print a notification instruction
python3 scripts/taskboard.py create "Build auth" \
--on-ack "message:CHANNEL_ID:🔨 {task.title} started by {task.assigned_to}"
# When done, instruct the agent to create a review task
python3 scripts/taskboard.py create "Design UI" \
--on-done "session:tech-lead:Review {task.title} and create QA task"
# Add/update hooks on existing task
python3 scripts/taskboard.py update 1 --on-done "message:CHANNEL_ID:Done!"
Hook output format:
🔔 ON_ACK: message:CHANNEL_ID:🔨 Build auth started
🔔 ON_DONE: session:tech-lead:Review Build auth and create QA task
The agent reads these lines and decides how to act (send a message, spawn a session, create a task, etc.).
Data Model
- tasks — id, title, description, acceptance_criteria, status, priority, assigned_to, created_by, parent_id, thread_id, on_ack, on_done, timestamps
- task_comments — per-task comment history
- task_updates — audit log of all field changes
Schema auto-initializes on first run. Upgrades from v1 (missing on_ack/on_done columns) are handled automatically.
Reference
references/webhook-integration.md— How to add Discord/webhook notifications on top of taskboardreferences/github-backend.md— Syncing tasks with GitHub Issuesreferences/taskboard-setup.md— Task lifecycle, cross-agent handoff protocol, cron integration
相关 Skills
表格处理
by anthropics
围绕 .xlsx、.xlsm、.csv、.tsv 做读写、修复、清洗、格式整理、公式计算与格式转换,适合修改现有表格、生成新报表或把杂乱数据整理成交付级电子表格。
✎ 做 Excel/CSV 相关任务很省心,能直接读写、修复、清洗和格式转换,尤其擅长把乱七八糟的表格整理成交付级文件。
PDF处理
by anthropics
遇到 PDF 读写、文本表格提取、合并拆分、旋转加水印、表单填写或加解密时直接用它,也能提取图片、生成新 PDF,并把扫描件通过 OCR 变成可搜索文档。
✎ PDF杂活别再来回切工具了,文本表格提取、合并拆分到OCR识别一次搞定,连扫描件也能变可搜索。
Word文档
by anthropics
覆盖Word/.docx文档的创建、读取、编辑与重排,适合生成报告、备忘录、信函和模板,也能处理目录、页眉页脚、页码、图片替换、查找替换、修订批注及内容提取整理。
✎ 搞定 .docx 的创建、改写与精排版,目录、批量替换、批注修订和图片更新都能自动化,做正式文档尤其省心。
相关 MCP 服务
文件系统
编辑精选by Anthropic
Filesystem 是 MCP 官方参考服务器,让 LLM 安全读写本地文件系统。
✎ 这个服务器解决了让 Claude 直接操作本地文件的痛点,比如自动整理文档或生成代码文件。适合需要自动化文件处理的开发者,但注意它只是参考实现,生产环境需自行加固安全。
by wonderwhy-er
Desktop Commander 是让 AI 直接执行终端命令、管理文件和进程的 MCP 服务器。
✎ 这工具解决了 AI 无法直接操作本地环境的痛点,适合需要自动化脚本调试或文件批量处理的开发者。它能让你用自然语言指挥终端,但权限控制需谨慎,毕竟让 AI 执行 rm -rf 可不是闹着玩的。
EdgarTools
编辑精选by dgunning
EdgarTools 是无需 API 密钥即可解析 SEC EDGAR 财报的开源 Python 库。
✎ 这个工具解决了金融数据获取的痛点——直接让 AI 读取结构化财报,比如让 Claude 分析苹果的 10-K 文件。适合量化分析师或金融开发者快速构建数据管道。但注意,它依赖 SEC 网站稳定性,高峰期可能延迟。