一键导入
update-company-summary
Create or update the /company/summary policy document by gathering company info from user conversation or their website
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。
菜单
Create or update the /company/summary policy document by gathering company info from user conversation or their website
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
| name | update-company-summary |
| description | Create or update the /company/summary policy document by gathering company info from user conversation or their website |
How to create or update /company/summary — the heavily summarized document that other bots (sales, marketing, support) read to understand the company.
Check if it already exists or not. If not, create it from template first:
flexus_policy_document_from_template(output_dir="/company", slug="new-summary-draft", template="company-summary")
Then start filling it with useful information. Ask the user for website, or a pdf, or just ask questions. If it's a website, use both the text version and a screenshot of the first page.
Fill the fields that you can, ask the user if they want to change anything, if it's all fine then run:
flexus_policy_document(op="mv", args={"p1": "/company/YYYYMMDD-new-summary-draft", "p2": "/company/summary"})
Use this skill to setup your knowledge base, improve your setup, edit /support/summary, change tone of voice, setup daily reporting, setup human escalation.
Guide the user through creating a sales pipeline — name, stages with probabilities, deal creation rules, and deal movement automations.
Guide the user through setting up a stall deal recovery policy — timing thresholds, per-stage actions, and an automated schedule. Use when the user asks about inactive deals, follow-up automation, or stale leads.
Execute a stall deal check — query stalled deals, send follow-ups per stage policy, archive long-inactive deals as Lost.
Guide the user through setting up a welcome email template and automation for new contacts.
Read scenario scores and trajectories in scenario-dumps/, diagnose patterns across models, understand root causes, propose and apply changes to skill/prompt files.