메뉴
Allows the agent to create cron job to execute actions later or regularly
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Deterministic communication metrics for the mirrored Teams channels. Computes reply-latency distributions, after-hours share, burst/fragmentation index, unanswered blockers, and interruption-cascade depth from data/teams/*/messages.jsonl, and refreshes the hyperscreen dashboard data. Use before making ANY quantitative claim about team communication.
Generate an interactive "application simulator" — a tiny, agent-built React mock of an external app (SAP MD04, a CRM, an ERP form) that the trainee can click through. The trainee's clicks stream back to you via viewerState so you can coach in real time. Each simulator is a single self-contained HTML file under `out/simulators/<app>.simulator.html`. Use this skill when the expert asks for a simulator (often in the context of curriculum topic 4 "Werkzeuge") or when a guest asks "can I practice this somewhere?".
Co-author a new roleplay scenario with an expert. Interview the expert about the persona, topic, hints with point values, and evaluation criteria, draft the JSON, and on confirmation write it to roleplay/<slug>.roleplay.json. Use when the expert invokes "Author a roleplay scenario" from the menu, asks "let me add a customer call to practice", "I want to script a difficult buyer", or equivalent. The scenarios authored here are consumed at runtime by the roleplay-engine skill.
Maintains a project knowledge wiki at wiki/ as the agent's long-term memory, dynamically structured around the mission in wiki/_meta/mission.md. Use whenever the user shares a fact, decision, preference, requirement, or finding worth remembering; whenever the user says "remember this", "add to wiki", "we decided", "save", "note that", or "for the record"; whenever the user asks "what do we know about X", "have we considered Y", "what did we decide", "summarize what we have"; whenever a file in the project codebase contains information relevant to the mission and should be ingested; at the end of a session to consolidate findings; and at session start to load relevant context. Reads index first, deduplicates before writing, tracks provenance, appends history rather than overwriting, and creates stubs for mentioned-but-unresearched topics. Pure markdown, no embeddings, no external network.
Engineering Design Support System. Use this skill whenever the user is doing long-horizon product/engineering design and wants to capture intent, decisions, risks, assumptions, evidence, open questions, or hypotheses; whenever they say 'add a decision', 'propose a hypothesis', 'what did we rule out', 'what changed', 'generate a status report', 'show whitespots', 'sharpen this', 'mission', 'realign', or ask what the project knows; at session start to load mission + state; and as the curator/researcher/synthesizer/critic loops. The mission is the versioned north star; the RDF knowledge graph is the system of record for a typed dependency graph (Concept/Decision/Risk/Assumption/Evidence/OpenQuestion/Gap/Whitespot/Hypothesis/Test); the scrapbook is a projected view; the wiki is synthesized prose; hypotheses run as stateful workflows. Pull-only: never push to the engineer except a critic mission-contradiction.
Use this skill whenever the user wants to take structured notes, collect ideas, organize project requirements, or manage a project notebook — trigger on phrases like 'scrapbook', 'add a note', 'what have we captured', 'notebook', 'show my notes', 'what should I focus on', 'jot this down', or any request to review, prioritize, or organize project items. Reads and writes to the project scrapbook via MCP tools, presenting content as a structured hierarchy with priorities and focus levels.
| name | schedule-task |
| description | Allows the agent to create cron job to execute actions later or regularly |
This skill enables you to schedule tasks to run at specific times. When a user requests something to happen at a future time, this skill parses the time expression, creates a scheduled task, and optionally saves the prompt for reuse.
Use this skill when the user asks you to do something at a specific time, such as:
Extract two components from the user's request:
Convert natural language time expressions to cron format (minute hour day month weekday):
| Expression | Cron Expression | Notes |
|---|---|---|
| Today at 16:00 | 0 16 7 2 * | Single run: specific date |
| Tomorrow at 9am | 0 9 8 2 * | Single run: specific date |
| At 14:30 | 30 14 7 2 * | Single run: today at that time |
| Every day at 8am | 0 8 * * * | Recurring daily |
| Every Monday at 10:00 | 0 10 * * 1 | Recurring weekly |
| Every hour | 0 * * * * | Recurring hourly |
| In 2 hours | Calculate current time + 2 hours | Single run |
Current date reference: Use the system date to calculate "today", "tomorrow", etc.
Cron format: minute hour day-of-month month day-of-week
Use the scheduler API to create the task:
POST /api/scheduler/{project}/task
Content-Type: application/json; charset=utf-8
{
"id": "unique-task-id",
"name": "Task name (short description)",
"prompt": "The full prompt to execute",
"cronExpression": "0 16 7 2 *",
"timeZone": "Europe/Berlin",
"type": "one-time"
}
Important fields:
id: Generate a unique ID (e.g., task-{timestamp} or UUID)name: A short, descriptive name for the taskprompt: The exact prompt that Claude should execute when the task runscronExpression: The cron expression from Step 2timeZone: Use the user's timezone (default: "Europe/Berlin" or ask if unclear)type: Either "recurring" or "one-time". Use "one-time" for tasks that should run once (today, tomorrow, specific date). Use "recurring" for repeating schedules (every day, every Monday, etc.)After creating the task, confirm with the user:
POST /api/scheduler/{project}/task
Body: { id, name, prompt, cronExpression, timeZone, type }
Response: { task: TaskDefinition }
GET /api/scheduler/{project}/tasks
Response: { tasks: TaskDefinition[] }
DELETE /api/scheduler/{project}/task/{taskId}
Response: { success: true }
GET /api/scheduler/{project}/history
Response: { history: TaskHistoryEntry[] }
User: "Today at 16:00 look up the stock prices for nvidia and write me an email"
Analysis:
0 16 {today's day} {today's month} *API Call:
POST /api/scheduler/current-project/task
{
"id": "task-1707321600000",
"name": "Stock prices email",
"prompt": "look up the stock prices for nvidia and write me an email",
"cronExpression": "0 16 7 2 *",
"timeZone": "Europe/Berlin",
"type": "one-time"
}
Response to user: "I've scheduled your task for today at 16:00. At that time, I'll look up Nvidia stock prices and send you an email. Task ID: task-1707321600000"
User: "Every day at 9am give me a summary of overnight news"
Analysis:
0 9 * * *API Call:
POST /api/scheduler/current-project/task
{
"id": "task-1707321600001",
"name": "Daily news summary",
"prompt": "give me a summary of overnight news",
"cronExpression": "0 9 * * *",
"timeZone": "Europe/Berlin",
"type": "recurring"
}
User: "Tomorrow at 14:00 check if the backup completed successfully"
Analysis:
0 14 {tomorrow's day} {tomorrow's month} *| Pattern | Example Input | Parsed As |
|---|---|---|
| Today at HH:MM | "today at 16:00" | Current date, specified time |
| Tomorrow at HH:MM | "tomorrow at 9am" | Next day, specified time |
| At HH:MM | "at 14:30" | Today, specified time |
| In X hours | "in 2 hours" | Current time + X hours |
| In X minutes | "in 30 minutes" | Current time + X minutes |
| Every day at HH:MM | "every day at 8am" | 0 8 * * * |
| Every X hours | "every 2 hours" | 0 */2 * * * |
| Every Monday at HH:MM | "every Monday at 10:00" | 0 10 * * 1 |
| Every weekday at HH:MM | "every weekday at 9am" | 0 9 * * 1-5 |
Default to Europe/Berlin unless the user specifies otherwise. Common timezones:
If time parsing is ambiguous, ask the user for clarification:
type must be "one-time"type: "recurring" with wildcard day/month fields in the cron expressioncharset=utf-8 in the Content-Type header to ensure proper encoding of non-ASCII characters