Search
AI & LLM Engineering · PostHog/posthog
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions. | PostHog/ | 40k | — | ~2.9k | Automated safety check: Pass | Unknown | yesterday |
| 2 | Teaches how to write and run evals on the products/posthogai/evalharness/ harness — sandboxed agent suites that execute the real coding agent in a Docker or Modal sandbox against a seeded Hedgebox… | PostHog/ | 40k | — | ~4k | Automated safety check: Notes | Unknown | yesterday |
| 3 | Analyze the most expensive users in AI observability and explain why they cost so much. | PostHog/ | 40k | — | ~3.9k | Automated safety check: Pass | Unknown | yesterday |
| 4 | Audits services/llm-gateway against PostHog/ai-gateway and updates services/llm-gateway/PARITY.md from current implementation evidence. | PostHog/ | 40k | — | ~1.2k | Automated safety check: Pass | Unknown | yesterday |
| 5 | Build a Loop for PostHog Desktop: a workflow that creates an AI task each time its trigger fires, optionally followed by a Slack or email notification with the task's result. | PostHog/ | 40k | — | ~3.6k | Automated safety check: Pass | Unknown | yesterday |
| 6 | Author continuously-running online evaluations in PostHog AI observability, grounded in real failure modes you've identified. | PostHog/ | 40k | — | ~6.7k | Automated safety check: Pass | Unknown | yesterday |
| 7 | Debug the signals pipeline locally end-to-end. An agent skill from PostHog/posthog. | PostHog/ | 40k | — | ~2.4k | Automated safety check: Notes | Unknown | yesterday |
| 8 | How to query the documentembeddings table for raw signal data using HogQL. | PostHog/ | 40k | — | ~4.3k | Automated safety check: Pass | Unknown | yesterday |
| 9 | Run an improve-my-MCP campaign: an autoresearch-style loop that measures the MCP agent experience with the eval harness, picks the highest-impact tool problem from production data, makes one bounded… | PostHog/ | 40k | — | ~1.5k | Automated safety check: Pass | Unknown | yesterday |
| 10 | Migrates an LLM caller from services/llm-gateway to PostHog/ai-gateway. | PostHog/ | 40k | — | ~1.3k | Automated safety check: Pass | Unknown | yesterday |
| 11 | Investigate AI observability evaluations — hog (deterministic code-based), llmjudge (LLM-prompt-based), and sentiment (user-message sentiment). | PostHog/ | 40k | — | ~5.7k | Automated safety check: Pass | Unknown | yesterday |
| 12 | Set up an LLM-judge evaluation that extracts canonical use cases for a PostHog feature at scale and streams the results to a Slack channel as a live feed. | PostHog/ | 40k | — | ~7.6k | Automated safety check: Pass | Unknown | yesterday |
| 13 | Write, edit, and adapt PostHog Signals scouts: scheduled agents that scan a project and report findings. | PostHog/ | 40k | — | ~11k | Automated safety check: Pass | Unknown | yesterday |
| 14 | Finds and ranks callers that could move from services/llm-gateway to PostHog/ai-gateway. | PostHog/ | 40k | — | ~1.7k | Automated safety check: Pass | Unknown | yesterday |
| 15 | Scopes work to the desktop app at products/desktop — a nested standalone pnpm/turbo/Biome workspace imported from the now-archived PostHog/code repo, with posthog/posthog the only source of truth… | PostHog/ | 40k | — | ~1.6k | Automated safety check: Pass | Unknown | yesterday |
