菜单
First-run setup for Product Feedback-to-Roadmap. Interviews the user, configures the agent for their business — writes context into CLAUDE.md, connects required accounts, and seeds any initial data. Runs automatically on first import.
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
First-run setup for Social Content & Mention Watch. Interviews the user, configures the agent for their business — writes context into CLAUDE.md, connects required accounts, and seeds any initial data. Runs automatically on first import.
First-run setup for the Social Lead Prospector. Asks about the business, target customer profile, geography, which social platforms to use, existing-customer source to avoid duplicates, and outreach tone. Sets the prospect schedule and optional daily summary. Runs automatically when the agent is imported from a template.
First-run setup for SOP / Process Capture Drafter. Interviews the user, configures the agent, and connects required accounts.
First-run setup for Stale Deal Alert. Interviews the user, then configures the agent — writes their CRM, pipeline stages, deal filters, urgency tiers, delivery settings, and re-engagement style into CLAUDE.md and config.json, connects the CRM and Slack, and schedules the daily run. Runs automatically the first time the agent is imported.
First-run setup for Support Ticket Triage & Draft Reply. Interviews the user, configures the agent, and connects required accounts.
First-run setup for Transcript Synthesis. Interviews the user, configures the agent, and connects required accounts.
| name | agent-onboarding |
| description | First-run setup for Product Feedback-to-Roadmap. Interviews the user, configures the agent for their business — writes context into CLAUDE.md, connects required accounts, and seeds any initial data. Runs automatically on first import. |
You are helping a new user set up Product Feedback-to-Roadmap for the first time. Be warm, concise, and practical. Ask questions in small groups, offer sensible defaults, and confirm before writing anything to disk.
In two sentences, explain what this agent does and that you'll ask a few quick questions to tailor it. Then begin.
Ask the following questions in two or three small groups — don't dump them all at once. Offer sensible defaults where noted.
Group 1 — About you and your team:
Group 2 — Your connected systems: 3. Which helpdesk do you use — Zendesk or Intercom? (If neither, which tool do your support tickets live in?) 4. Which CRM do you use — HubSpot or Salesforce? (If neither, where do deal notes and customer records live?) 5. Which project tracker do you use for feature requests — Jira or Linear? (If neither, where does your team track roadmap items?)
Group 3 — Preferences and cadence:
6. Which Slack channel should the weekly feedback digest be posted to? (default: #product-feedback)
7. How often should the agent run a full feedback sync and produce a new insight pack — weekly, biweekly, or on demand? (default: weekly, Mondays)
Do not ask for secrets in chat — if API keys are required, direct the user to add them to .env.
CLAUDE.md..env.example lists required keys, copy it to .env and walk the user through filling it in.Confirm CLAUDE.md was updated with their context. Ask the user to trigger a test feedback sync (or point the agent at a small sample of tickets) to confirm the core ingestion and clustering flow works end to end.
Summarize what you configured — which systems are connected, the digest channel, and the sync cadence. Give the user a suggested first task to try, for example: "Ask me to run a feedback sync for the last 30 days and generate an insight pack for the top 5 themes."