Automate PostHog tasks via Rube MCP (Composio): events, feature flags, projects, user profiles, annotations. Always search tools first for current schemas.
Install with Tessl CLI
npx tessl i github:Lingjie-chen/MT5 --skill posthog-automation64
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Event naming conventions and setup workflow
RUBE_SEARCH_TOOLS first
0%
100%
RUBE_MANAGE_CONNECTIONS setup
0%
100%
distinct_id in every event
100%
100%
System event $ prefix
100%
100%
Custom events no $ prefix
100%
100%
Consistent property schemas
100%
100%
POSTHOG_CAPTURE_EVENT used
0%
100%
Multiple users captured
100%
100%
Properties object present
100%
100%
Without context: $0.3643 · 1m 37s · 12 turns · 19 in / 8,677 out tokens
With context: $0.5595 · 2m 11s · 23 turns · 278 in / 9,040 out tokens
Feature flag creation and targeting
RUBE_SEARCH_TOOLS first
25%
100%
Project ID resolved first
83%
100%
Kebab-case flag key
100%
100%
Filters with groups array
100%
100%
Internal users group first
100%
100%
Rollout percentages set
100%
100%
active: true on creation
100%
100%
project_id numeric parameter
50%
100%
POSTHOG_CREATE_FEATURE_FLAGS_FOR_PROJECT used
25%
100%
Flag name included
100%
100%
Without context: $0.2052 · 58s · 12 turns · 17 in / 3,251 out tokens
With context: $0.3141 · 58s · 17 turns · 20 in / 3,358 out tokens
Event querying with pagination and project ID resolution
RUBE_SEARCH_TOOLS first
0%
100%
RUBE_MANAGE_CONNECTIONS included
0%
100%
Project ID resolved first
100%
100%
ISO 8601 date format
100%
100%
Correct time window
100%
100%
POSTHOG_LIST_AND_FILTER_PROJECT_EVENTS used
0%
100%
Pagination with offset and limit
0%
100%
Pagination termination condition
50%
100%
Response data key awareness
100%
100%
project_id as parameter
100%
100%
Without context: $0.4653 · 2m 4s · 25 turns · 1,747 in / 6,871 out tokens
With context: $0.4983 · 1m 43s · 24 turns · 313 in / 5,973 out tokens
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.