feature-usage-feed
OfficialGet a live Slack feed of canonical feature usage.
Product & Management#automation#slack#data-analytics#trace-analysis#feature-usage#llm-eval#posthog-ai
AuthorPostHog
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill provides a scalable pattern to surface canonical usage patterns for a PostHog feature by streaming representative traces and AI-evaluation results to Slack, enabling teams to understand real user behavior without manual trace review.
Core Features & Use Cases
- Live Slack feed with canonical use cases extracted from large trace volumes (group/single session summaries, replay AI search, error tracking AI, etc.)
- Two filter patterns to scope evaluation to a feature: Pattern A (trace_id prefix) or Pattern B (agent_mode + supermode)
- Guided eval prompt templates and sample workflows to validate signal quality and iterate on prompts
- UI/workflow integration guidance for end-to-end deployment including sampling and validation
Quick Start
Configure the feature-usage-feed to begin streaming canonical feature-use cases to your Slack channel.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: feature-usage-feed Download link: https://github.com/PostHog/skills/archive/main.zip#feature-usage-feed Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.