القائمة
Requests Upstage API key via Channel.io when the key is not configured. Sends a message to Pete, waits for his reply, then writes the key to .env automatically.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
This sop executes automated clustering and tagging of customer support chat data through a Python pipeline, producing clustered data, cluster tags, and a comprehensive analysis report for Stage 2 (Pattern Extraction). The agent orchestrates the Python clustering script, monitors execution, validates outputs, and generates an analysis report to guide subsequent extraction work. **Language:** Auto-detects Korean (한국어) or Japanese (日本語) from user input.
Generate an ALF implementation package from all pipeline outputs. Produces rules draft, RAG knowledge items, dialog type cross-analysis heatmap, automation feasibility analysis, ROI calculation, task flowcharts (05_sales_report/tasks/), API requirements doc, and final ALF implementation guide. **Language:** Auto-detects Korean (한국어) or Japanese (日本語) from user input.
Split rules_draft.md into individual rule files and expand rag_items.md into standalone RAG knowledge documents for direct ALF registration.
Generate a client-facing deployment scenario and QA set from pipeline outputs (Stages 1-6). Maps consultation categories to resolution methods (RAG/Task) and deployment steps, with test queries per category. Outputs HTML + Markdown, optionally publishes to Notion.
Complete end-to-end pipeline for transforming Excel customer support data into production-ready Agent SOP documents, flowcharts, ALF implementation package, individual ALF registration files, and client-facing deployment scenario through 7 stages.
Channel.io 봇의 RAG 응답 품질을 Playwright로 자동 테스트합니다.
| name | request-api-key |
| description | Requests Upstage API key via Channel.io when the key is not configured. Sends a message to Pete, waits for his reply, then writes the key to .env automatically. |
When UPSTAGE_API_KEY is missing from .env, this skill:
.envLanguage: Detect the language from the user's first message and respond in that language throughout. Support Korean (한국어) and Japanese (日本語). Default to Korean if language is unclear.
Constraints:
grep -s "UPSTAGE_API_KEY" .envup_, and is NOT the placeholder up_YOUR_API_KEY_HERE → STOP and tell the user the key is already configuredhostname and whoamiConstraints:
mcp__team-chat-mcp__send_team_chat_message with groupId: "531940"userName to {username} ({hostname})messageId for thread lookup in Step 3Message template:
🔑 Upstage API 키 요청
안녕하세요, 피트님!
{username} ({hostname})에서 SOP 파이프라인을 실행하려고 합니다.
Upstage API 키가 필요합니다. 키를 이 스레드에 답장해 주세요 🙏
Expected Output:
✅ 피트님께 요청을 보냈습니다!
Channel.io에서 답장이 오면 아래 버튼을 눌러주세요.
Constraints:
/request-api-key when Pete replies and STOPPete may reply in the thread or directly in the group — check both.
Constraints:
mcp__team-chat-mcp__get_team_chat_thread with the messageId from Step 2, and scan replies for a message from personId 592317 containing up_[a-zA-Z0-9_]+mcp__team-chat-mcp__get_team_chat_messages with groupId: "531940", limit: 10, sortOrder: "desc" and scan for a message from personId 592317 containing up_[a-zA-Z0-9_]+up_ and is at least 20 characters.env does not exist, create it: cp .env.example .envgrep UPSTAGE_API_KEY .env...Constraints:
python3 -c "import sys; sys.path.insert(0, '.'); from scripts.config import UPSTAGE_API_KEY; print('OK')"/stage1-clustering or /userchat-to-sop-pipelineExpected Output:
🎉 API 키 설정 완료! (up_xxxxx...)
이제 파이프라인을 실행할 수 있습니다.
👉 /stage1-clustering 또는 /userchat-to-sop-pipeline
up_.env is in project root: cat .env