← 返回 Skills 市场
🔌

PostHog

作者 OOMOL · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
33
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install oo-posthog
功能描述
PostHog (posthog.com). Use this skill for ANY PostHog request — reading, creating, updating, and deleting data. Whenever a task involves PostHog, use this sk...
使用说明 (SKILL.md)

PostHog

Operate PostHog through your OOMOL-connected account. This skill calls the posthog connector with the oo CLI; OOMOL injects credentials server-side, so you never handle raw tokens.

Category: Data & Analytics, Developer Tools. Exposes 57 action(s).

Running an action

Assume the user has already installed the oo CLI, signed in, and connected PostHog. Do not run oo auth login or open the connection URL proactively — just run the action. Fall back to First-time setup only when a command actually fails with an auth or connection error.

1. Inspect the contract to get the authoritative input/output schema before building a payload:

oo connector schema "posthog" --action "\x3Caction_name>"

2. Run the action with a JSON payload that matches the input schema:

oo connector run "posthog" --action "\x3Caction_name>" --data '\x3Cjson>' --json
  • --data takes a JSON object string or @path/to/file.json; omit it to send {}.
  • The response is { "data": ..., "meta": { "executionId": "..." } }; the execution id lives under meta.executionId.

Each action below links to a reference file with its purpose and exact commands. Read the linked file, then fetch the live schema with oo connector schema before constructing --data.

Available actions

Safety

  • Read actions (get / list / search) are safe to run directly.
  • Create, update, send, or post actions change PostHog state — confirm the exact payload and effect with the user before running.
  • Delete or remove actions are destructive — always confirm the target and get explicit approval first.

First-time setup

These are one-time steps — do not repeat them on every call. Run a step only when a command fails for the matching reason.

  • oo: command not found — install the oo CLI (other platforms: \x3Chttps://cli.oomol.com/install-guide.md>):

    curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
    
    irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell
    
  • Not signed in / authentication error — sign in to your OOMOL account once:

    oo auth login
    
  • scope_missing / credential_expired / app_not_ready / app_not_found — PostHog is not connected, or the connection expired or lacks a scope. Connect once (auth type: OAuth2, API key) at:

    https://console.oomol.com/app-connections?provider=posthog
    
  • HTTP 402 / OOMOL_INSUFFICIENT_CREDIT — billing stop. Recharge at https://console.oomol.com/billing/token-recharge before retrying.

Resources

安全使用建议
Install only if you trust OOMOL to broker your PostHog connection and are comfortable giving the skill read/write/delete authority over PostHog resources. Confirm every write or delete payload carefully, and avoid running the pipe-to-shell installer blindly; use the official install guide or inspect the installer first.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The skill’s stated purpose is to operate PostHog through OOMOL, and the 57 listed actions match that purpose, including dashboards, insights, cohorts, feature flags, queries, and deletes.
Instruction Scope
Runtime instructions are scoped to inspecting schemas and running the PostHog connector through the oo CLI, with explicit confirmation required before write or destructive actions.
Install Mechanism
First-time setup includes curl-to-bash and PowerShell pipe-to-execute installer commands for the oo CLI; this is disclosed and conditional, but users should verify the installer path or use safer install guidance before running it.
Credentials
The skill requires sensitive PostHog/OOMOL account access and can expose analytics, cohorts, users, and feature-flag data, which is proportionate for the integration but not risk-free.
Persistence & Privilege
No background worker, hidden persistence, sudo use, or executable artifact files were found; the expected persistent pieces are the installed oo CLI and user authentication/connection state.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install oo-posthog
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /oo-posthog 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release of the `oo-posthog` skill for operating PostHog through an OOMOL-connected account using the `oo` CLI. - Adds 57 actions covering projects, dashboards, insights, annotations, cohorts, event definitions, property definitions, feature flags, and query execution. - Supports common read workflows such as listing and fetching PostHog resources, running queries, checking async query status, and running dashboard insights. - Supports managed write workflows for creating, updating, tagging, copying, moving, and reordering PostHog resources. - Includes explicit safety guidance for state-changing and destructive actions, with live schema inspection before building action payloads.
元数据
Slug oo-posthog
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

PostHog 是什么?

PostHog (posthog.com). Use this skill for ANY PostHog request — reading, creating, updating, and deleting data. Whenever a task involves PostHog, use this sk... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 33 次。

如何安装 PostHog?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install oo-posthog」即可一键安装,无需额外配置。

PostHog 是免费的吗?

是的,PostHog 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

PostHog 支持哪些平台?

PostHog 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 PostHog?

由 OOMOL(@oomol)开发并维护,当前版本 v1.0.0。

💬 留言讨论