
managing-subscriptions
Create and manage scheduled PostHog subscriptions for insight snapshots, dashboard snapshots, and AI prompt reports. Use when a user wants recurring email, Slack, or Microsoft Teams delivery; an AI summary; delivery history; schedule or recipient changes; a test delivery; pause, resume, or deletion; or help with subscription permissions, limits, billing, and failures. Use product alerts when delivery must depend on a threshold or anomaly.
- Installs
- 219
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/posthog/ai-plugin --skill managing-subscriptions- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads managing-subscriptions automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Managing subscriptions
Subscriptions deliver product data on a fixed schedule. They support insight snapshots, dashboard snapshots, and AI prompt reports.
Read the relevant references
- Read subscription-types.md before you select or change a resource type.
- Read destinations.md before you create or change a destination.
- Read operations.md for schedules, limits, billing, delivery checks, and failures.
- Use
creating-ai-subscriptionfor the detailed prompt report creation workflow.
Choose the correct product
- Use a subscription for fixed delivery, such as "send this dashboard every Monday."
- Use a product alert for a condition, such as "notify me when conversion falls below 10%."
- Use a reminder when the user wants a private prompt to inspect a resource later.
- Use a Signals scout when an agent must decide what is important to report.
Subscriptions do not evaluate thresholds, recovery, consecutive breaches, or quiet hours. Snapshot subscriptions attempt each scheduled occurrence even when the saved results do not change.
Tools
| Tool | Purpose |
|---|---|
posthog:subscriptions-list | Find subscriptions |
posthog:subscriptions-retrieve | Read one subscription |
posthog:subscriptions-create | Create a subscription |
posthog:subscriptions-partial-update | Change, pause, or resume a subscription |
posthog:subscriptions-test-delivery-create | Send a test delivery |
posthog:subscriptions-deliveries-list | List delivery attempts |
posthog:subscriptions-deliveries-retrieve | Read one delivery |
posthog:subscriptions-delete | Stop all future deliveries |
posthog:integrations-list | Find a Slack integration |
posthog:integrations-channels-retrieve | Find Slack channels |
posthog:dashboard-get | Read dashboard tiles |
posthog:insight-get | Resolve an insight ID |
Create a subscription
- Call
posthog:subscriptions-listand check for a duplicate. - Select one resource type from subscription-types.md.
- Resolve the destination with destinations.md.
- Resolve the schedule with operations.md.
- Ask whether the user wants an immediate delivery.
- Set
send_test_nowto the user's choice. - Call
posthog:subscriptions-create. - Read the saved subscription and check each requested field.
- If the user approved an immediate delivery, check its delivery record.
If creation times out or returns an uncertain result, list matching subscriptions before you retry. Creation is not idempotent. A blind retry can create a duplicate subscription and send a duplicate immediate delivery.
Do not infer missing recipients, channels, times, or time zones. Ask for these values before creation.
Find existing subscriptions
Use these list filters when they reduce ambiguity:
resource_type:insight,dashboard, orai_prompt.target_type:email,slack, orteams.insightorinsights: One insight ID or a comma-separated ID list.dashboard: One dashboard ID.dashboard_tiles: Insight subscriptions for live tiles on one dashboard.created_by: One creator UUID.
Check for duplicates
Use search when the user supplied a title, insight name, dashboard name, or prompt text.
Prompt subscriptions match their title and prompt text.
Compare the resource, destination type, target, schedule, and enabled state.
A Teams result contains only the webhook host. One host can serve many channels. Do not use the host to identify a duplicate.
Show the title, schedule, creator, and creation date for possible Teams matches. Ask the user to select a subscription when these fields identify it. Create a new subscription when no field identifies the target channel.
Confirm the saved result
Check these fields after creation:
resource_typematchesinsight,dashboard, orai_prompt.target_typeand the safe target label match the request.enabledistrue.next_delivery_datematches the schedule and time zone.- The AI and delivery options match the user's choices.
Change a subscription
Call posthog:subscriptions-retrieve before each update.
Before an update that can send a delivery, list the current delivery IDs.
Then call posthog:subscriptions-partial-update with the changed fields.
Ask before an update that can send an immediate delivery. The MCP update tool cannot suppress an immediate delivery for these changes. If the user does not approve delivery, do not make the update.
- Set
enabled: falseto pause delivery. - Set
enabled: trueto resume delivery. - Send the complete new target when you change recipients.
- Send
target_typeandtarget_valuetogether when you change the destination type. - Omit
target_valueto keep a saved Teams webhook URL. - Send the full new Teams webhook URL when you replace it.
The resource type cannot change. Create a new subscription when the user wants a different resource type.
Check the new next_delivery_date after a schedule update.
An exhausted schedule cannot resume until the user extends or removes its end condition.
After an update that sends a delivery, poll for a new target_change delivery ID.
Read that delivery until it reaches a final state.
Then retrieve the subscription and check its final enabled value.
Test and inspect delivery
- Ask for approval unless the user already requested a test.
- List the current delivery IDs.
- Call
posthog:subscriptions-test-delivery-create. - Poll for a new manual delivery ID.
- Read the new delivery when the list result needs more detail.
Wait between polls and stop after two minutes. If delivery does not reach a final state, report the last state and suggest another check later.
A test sends a real message.
The tool returns 202 after it queues the delivery.
It returns 409 when another test is active or the subscription is disabled.
Delivery states are starting, completed, failed, and skipped.
Filter the delivery list by status when you investigate a failure.
A queued workflow does not prove delivery.
A completed delivery can contain partial recipient failures.
The MCP tools hide per-recipient results.
Do not claim that each recipient succeeded.
Stop a subscription
Confirm the subscription ID and safe destination label.
Ask for approval unless the user already requested deletion or unsubscribe.
Then call posthog:subscriptions-delete.
Deletion is a one-way soft delete through MCP. It stops future deliveries and frees a plan slot. Create a new subscription if the user needs it again.
Report the result
- State the resource type, destination type, schedule, and next delivery date.
- State whether the subscription is enabled.
- State whether AI features can consume AI credits.
- Do not repeat email addresses unless the user needs them for confirmation.
- Never repeat a Teams webhook URL.
Related skills
creating-ai-subscription: Create a report from a free-text AI prompt.building-a-dashboard: Create a dashboard before you subscribe to it.adding-product-alerting: Notify users when data meets a condition.managing-reminders: Schedule a private prompt to inspect a resource.understanding-billing-usage: Investigate PostHog AI credit use.
FAQ
What does the managing-subscriptions skill do?
Create and manage scheduled PostHog subscriptions for insight snapshots, dashboard snapshots, and AI prompt reports. Use when a user wants recurring email, Slack, or Microsoft Teams delivery; an AI summary; delivery history; schedule or recipient changes; a test delivery; pause, resume, or deletion; or help with subscription permissions, limits, billing, and failures. Use product alerts when delivery must depend on a threshold or anomaly.
How do I install managing-subscriptions?
Run npx skills add https://github.com/posthog/ai-plugin --skill managing-subscriptions in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/managing-subscriptions/ (personal) or .claude/skills/managing-subscriptions/ (project).
Which AI agents can use managing-subscriptions?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is managing-subscriptions safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains managing-subscriptions?
It is published by posthog in posthog/ai-plugin, and it is an official skill from the maker of the technology it covers. It has 219 recorded installs.
More from posthog/ai-plugin
instrument-product-analytics
posthog/ai-plugin
Add PostHog product analytics events to track user behavior. Use after implementing new features or reviewing PRs to ensure meaningful user actions are captured. Also handles initial PostHog SDK setup if not yet installed.
instrument-feature-flags
posthog/ai-plugin
Open the skill to read its SKILL.md instructions.
cleaning-up-stale-feature-flags
posthog/ai-plugin
Identify stale feature flags in a PostHog project and clean up the code that checks them. Use when the user wants to find, audit, or remove unused, fully rolled out, or abandoned feature flags, run a feature flag hygiene review or a weekly cleanup, reduce feature flag tech debt, or asks "which flags can I remove?". When the agent can read and edit a repository it performs the code cleanup itself: tested local changes, and one draft PR per flag when the user authorizes publishing. Agents without repository access generate a tailored cleanup prompt instead. Covers staleness detection, dependency checking, retained-path rules, and the code-first ordering. This skill does not archive or otherwise change a flag in PostHog.
auditing-experiments-flags
posthog/ai-plugin
Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations. Read when the user asks to audit, health-check, or review experiments or feature flags, check flag hygiene, or verify experiment setup.
querying-posthog-data
posthog/ai-plugin
Explains how to query PostHog data, defaulting to typed runners for supported product analytics. Read it before you write HogQL/SQL. Also read it before you call execute-sql against PostHog. Use it to find or aggregate PostHog entities. These entities include insights, dashboards, cohorts, feature flags, experiments, surveys, hog flows, warehouse data, and persons. Use it for trends, funnels, retention, lifecycle, paths, stickiness, web analytics, error tracking, logs, sessions, and LLM traces. Before you calculate a governed business or telemetry measure, check system.informationschema.metrics for an approved definition. Examples include MRR, activation, billable usage, active organizations, and failure rates. Use the approved definition before you derive a measure from raw events or use a typed domain tool. It also covers HogQL differences, system table schemas, functions, query examples, and schema discovery.
creating-experiments
posthog/ai-plugin
Guides agents through experiment creation: reading the project's setup with experiment-setup-context, defining the hypothesis, configuring rollout and bucketing, setting up analytics and running time, and reporting which choices are guesses. Delegates rollout decisions to configuring-experiment-rollout and metric setup to configuring-experiment-analytics. TRIGGER when: user asks to create a new experiment or A/B test, OR when you are about to call experiment-create. DO NOT TRIGGER when: user is updating an existing experiment, managing lifecycle, or only browsing experiments.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。