菜单
Activate when the user wants the agent team to perform a recurring task automatically on a schedule — e.g. daily news summary, weekly report, nightly diary. Not for one-time reminders — use create-reminder for that.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Activate for ANY request involving specialist delegation — single or multi-step. Contains the complete orchestration SOP: plan-and-confirm format, sequential execution rules, how to write a complete `request` argument, recovery from errors, retry limits, file delivery rules, and output presentation.
Activate when a multi-agent orchestration goes wrong. Contains: recovery from `ValueError: Tool '<name>' not found`, the full forbidden-tool reference for each specialist, retry limits and abandon criteria, recovery if you accidentally invoked two specialists in parallel, and the catalogue of historically-reproduced mistakes. Pair with `multi-agent-chain` (the always- loaded core skill) — that one has the happy-path rules; this one has the escape hatches.
Use when delegating report generation, PDF creation, chart visualization, or data interpretation to the business analysis expert. Load this skill before calling `business_analysis(request='...')` so you know what to send, what it returns, and which tools are internal to that specialist (and must NEVER be called directly).
Use when delegating any task to the coding expert — Python scripting, data analysis, SVM / ML algorithms, file I/O, package installation, git operations, or running tests. Load this skill before calling `coding(request='...')` so you know what to send and how to read the response.
Use when a task involves database operations — SQL queries, schema inspection, data retrieval, record insertion/update/deletion, or database health checks. Load this skill before calling `database(request='...')`. IMPORTANT: This specialist may not be deployed — check the registered tool spec first.
Run before marking any task as done. Parses the task spec for output file paths and verifies each file actually exists on disk. If any required file is missing, requeues the task instead of closing it. Skip for tasks with no file output.
| name | create-regular-work |
| description | Activate when the user wants the agent team to perform a recurring task automatically on a schedule — e.g. daily news summary, weekly report, nightly diary. Not for one-time reminders — use create-reminder for that. |
Do NOT use for one-time notifications → activate create-reminder instead.
get_current_time() to confirm current time and timezone.create_regular_work with these parameters:
user_id: the hashed_id from the current session (a 16-character hex string, e.g. c9e4719ba839d6b6). Never the user's display name.session_id: the current session_id.title: short human-readable name for the work (e.g. "每日科技新聞摘要").spec: Full, self-contained instructions the agent needs to execute autonomously (no user context available at run time).cron: 5-part cron expression (minute hour day month weekday).agent_id (optional): Which agent executes — default costaff_agent; pass a specialist name if the task is domain-specific.channel (optional): "telegram" / "discord" / "line". If omitted, the system auto-resolves from the user's IdentityMap.recipient (optional): same as user_id (the hashed_id) when explicitly delivering to the requesting user. If omitted, auto-resolved.Do NOT execute the work immediately — only confirm the schedule is set.
Important:
recipientis an internal routing key (a hashed_id), not a human-readable name. Either omit it (let the system auto-resolve) or pass the same hashed_id you got fromcheck_identity/ session context.
| Schedule | Cron expression |
|---|---|
| Every day at 09:00 | 0 9 * * * |
| Every Monday at 08:00 | 0 8 * * 1 |
| Every weekday at 18:00 | 0 18 * * 1-5 |
| Every hour | 0 * * * * |
specThe spec must be fully self-contained — no user will be present when it runs:
channel, recipient)