跳到正文
cccskills
免费在 GitHub 公开

churn-signals

Combine product usage, support issues, payment status, and renewal dates to rank accounts by churn risk, meaning the risk of cancellation. Produce a Slack list with specific evidence and a suggested next action for each account.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Scoring rules for daily churn-risk detection — usage decline, support friction, billing/payment risk, and renewal proximity — plus how to combine them into a ranked at-risk list with a reason and a suggested next step per account.

集成工具StripePostgreSQL

实测评分 未实测

查看安装方法

适用场景

  • Reviewing accounts at risk of cancellation each day
  • Prioritizing outreach before contract renewals
  • Understanding why an account received a high risk rating
  • Combining usage, support, and payment signals

包含的文件(1)

  • SKILL.md4.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

<skill name="churn-signals"> <overview> Turn four partial views — product usage, support friction, payment health, and renewal timing — into one ranked at-risk list. A daily cron spawns a fresh session with read-only access to Postgres, Plain, and Stripe; this skill turns those raw signals into a score, a reason, and a next step per account. No signal is scored in isolation: an account with declining usage but nothing else is very different from one with declining usage, rising support load, and a renewal next month. </overview> <when-to-load> - The daily cron fires the churn-risk scan. - A human asks for the current at-risk list, or why a specific account scored the way it did. </when-to-load> <workflow>

Step 1 — Pull usage from Postgres (read-only)

Query per-account activity trend over a rolling window (active seats, key-feature events, login frequency over the last 30 days vs. the prior 30). Classify:

Usage signalCriteria
Stable/growingFlat or increasing vs. prior window
Declining≥20% drop in core activity vs. prior window
DormantNear-zero activity for 14+ days on a previously active account

Step 2 — Pull support friction from Plain (read-only)

Pull thread volume and tone per account over the same window.

Support signalCriteria
NormalThread volume in line with the account's history
Rising frictionThread count up materially vs. baseline, or repeated unresolved threads
EscalatedAn open thread flagged urgent/escalated, or explicit cancellation language

Step 3 — Pull billing state from Stripe (read-only)

Pull payment status and renewal date per account.

Billing signalCriteria
HealthyPayments current, renewal more than 45 days out
At riskOne missed or failed payment in the last billing cycle
Renewal-imminentRenewal within 30 days

Step 4 — Combine into one score per account

No single signal alone is high risk. Weigh combinations:

CombinationRisk
Declining/dormant usage aloneLow–medium — watch
Declining usage + rising/escalated supportMedium–high
Any usage signal + a failed paymentHigh
Declining/dormant usage + renewal-imminentHigh
Rising/escalated support + renewal-imminentHigh
Declining usage + rising support + (renewal-imminent or failed payment)Highest — surface first
Stable usage, normal support, healthy billingNot at risk — omit from the list

Step 5 — Write the reason and the next step

For every account that clears the "watch" bar, write:

  • Reason — the specific signals that fired, e.g. "usage down 34% in 30d, 2 escalated threads, renewal in 12 days."
  • Next step — one concrete, human-actionable suggestion tied to the dominant signal:
    • Usage decline → a check-in call or re-onboarding nudge.
    • Support friction → proactive outreach from the account's CSM.
    • Payment risk → a billing follow-up (the agent does not send this itself).
    • Renewal-imminent combined with any other signal → prioritize a renewal conversation now, not at the renewal date.

Step 6 — Rank and post

Sort highest risk first. Post one message to {{alert_channel}}: for each account, its rank, risk level, the reason, and the next step. Post exactly once per run — this is a fresh session, so there is no prior list to update or diff against; the whole list is recomputed and reposted every day.

</workflow> <guardrails> - **Read-only, always.** Postgres and Stripe are read-only connectors, and the Plain API key (`PLAIN_API_KEY`) is scoped to read access only. Never write to an account, a ticket, or a subscription, even if the credential would technically allow it. - **One output.** The Slack post to {{alert_channel}} is the only thing that leaves the sandbox. No emails, no ticket replies, no billing actions. - **No memory between runs.** Each run is a fresh session; recompute from the current state of all three systems rather than assuming anything from the prior day's list. - **Scoped secrets.** Postgres and Stripe access is brokered server-side through connectors; the Plain API key is injected as an environment variable. No raw credential is ever pasted into chat. - **People decide, not the agent.** The list flags risk and suggests a next step; a human on customer success decides whether and how to act. </guardrails> </skill>

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

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.

中文简介正在准备中。当前显示英语简介。

  • Reviewing GitHub repository access requests from Slack
  • Preparing AWS IAM permissions for a specific task
  • Routing sensitive access requests for additional review
kortix-ai/suna2万2026年10月23日 更新

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.

中文简介正在准备中。当前显示英语简介。

  • Research a prospective customer before outreach
  • Prepare background information for meeting attendees
  • Compare a competitor's products and positioning
kortix-ai/suna2万2026年10月23日 更新

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.

中文简介正在准备中。当前显示英语简介。

  • Checking whether campaign budgets are being spent on schedule
  • Investigating rising acquisition costs or falling ad returns
  • Finding ads and keywords that spend without converting
kortix-ai/suna2万2026年10月23日 更新

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.

中文简介正在准备中。当前显示英语简介。

  • Automate form entry and page navigation
  • Capture screenshots and extract page data
  • Explore web apps for bugs
kortix-ai/suna2万2026年10月23日 更新

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.

中文简介正在准备中。当前显示英语简介。

  • Checking incoming invoices against purchase orders
  • Finding duplicate invoices and likely resends
  • Reviewing unit prices and remaining order balances
kortix-ai/suna2万2026年10月23日 更新

billing

免费

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.

中文简介正在准备中。当前显示英语简介。

  • Update billing logic and its specification together
  • Review how trials and enterprise contracts are handled
  • Find the code that defines prices and allowances
kortix-ai/suna2万2026年10月23日 更新

查看 kortix-ai 的全部技能

报告此技能的问题