Draft monthly investor updates from Stripe, Postgres, and the previous report. Compare revenue, recurring subscription revenue, account activity, cash burn, and runway against last month and plan, then create a new document for the founder to review.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Monthly investor-update runbook. Reads last month's update from {{updates_folder}} for the prior numbers and the format to match, pulls MRR and revenue from Stripe and active accounts, growth, burn, and runway from Postgres, compares every metric to last month and to plan, and drafts this month's update as a new document — read-only across every connected system.
설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Open the most recent update in {{updates_folder}} and extract:
If {{updates_folder}} has no prior update yet, use the Format table below as the default structure and note in the draft that this is the first run.
Pull for the current calendar month:
| Metric | Definition |
|---|---|
| MRR | Sum of active subscription value, normalized to monthly |
| MRR growth | (this month MRR − last month MRR) / last month MRR |
| Revenue | Total collected revenue for the month |
| New / expansion / churned MRR | Movement components behind the net MRR delta |
Query for the current calendar month:
| Metric | Definition |
|---|---|
| Active accounts | Accounts with qualifying activity in the month |
| Account growth | Net new active accounts vs. last month |
| Burn | Net cash spent in the month (cash out − cash in, excluding financing) |
| Runway | Current cash balance ÷ trailing average monthly burn |
For every metric in Steps 2–3, compute both deltas:
Flag anything moving more than one plan-implied standard deviation, or any metric moving in the wrong direction two months running, as a line the narrative must address explicitly — don't bury a miss in a table.
Match last month's section order exactly. A typical structure:
Write the commentary as a draft for a founder to edit, not a finished statement — flag genuine uncertainty (e.g. "likely driven by X — confirm") rather than asserting a cause you can't verify from the data.
Create a new document under {{updates_folder}} (do not overwrite last month's), named/dated for the current month, following Step 5's structure. This document is the only thing that leaves the sandbox.
State the new document's name and location under {{updates_folder}} so the founder can find, edit, and send it. Do not send, share, or publish it yourself.
</workflow> <guardrails> - **Read-only, always.** Postgres and Stripe are read-only connectors; the agent cannot change a record in either, even if the connector would technically permit it. - **Never overwrite history.** Last month's update (and every prior one) is read-only. The agent only ever adds a new document; it never edits or replaces a past one. - **One output.** The new draft document under {{updates_folder}} is the only thing that leaves the sandbox — no emails, no chat posts, no other writes. - **No memory between runs.** Each run is a fresh session. Recompute every metric from the current state of Postgres and Stripe, and re-derive last month's figures from the update it wrote rather than assuming anything carried over. - **Scoped secrets.** Postgres, Stripe, and document access are brokered server-side through connectors; no raw credential is ever pasted into chat. - **The founder sends, not the agent.** The agent's job ends at a finished draft. It never emails, messages, or publishes the update to investors. </guardrails> </skill>아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Review Slack access requests against Okta role and team information, then prepare narrowly scoped GitHub or AWS IAM permissions. Apply changes only after an eligible person's approval and record the grant, reasoning, approver, and timestamp.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Research companies and people before outreach or meetings. Combines business profiles, recent news, hiring signals, and key contacts into a sourced brief with talking points and suggested questions, adding relationship history when CRM data is connected.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Review daily Google Ads and Meta Ads results for budget pacing, declining performance, and unusual activity. Get prioritized findings with supporting numbers and concrete recommendations for a marketing team to assess and carry out.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Automate website tasks such as navigating pages, filling forms, clicking buttons, taking screenshots, and extracting data. The skill also supports web app testing, with specialized guides for Electron desktop apps, Slack, and cloud browsers.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Process emailed vendor invoices by extracting details, comparing them with purchase orders and invoice history, and recording duplicates, overcharges, or missing orders. Summarize results in Slack for human review; payment approval and execution remain with people.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Guide changes to Kortix billing code, admin controls, and pricing screens. Explain how plans, trials, enterprise contracts, and access exceptions should work, where pricing is defined, and which audited routes must handle account changes.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.