Agent skills

Generates polished 1080p technical explainer and demo videos with Chinese voiceover, automated subtitles, and structured visual cards…

Create high-quality animated explainer visuals for essays and blog posts.

Explain any topic at five escalating levels — High School, College, PhD, Philosopher, Gigabrain — where each level responds directly to…

Exploits Kerberos Constrained Delegation misconfigurations in Active Directory using Impacket's findDelegation.py and getST.py (or…

Tests and exploits deep link (URL scheme and App Link) vulnerabilities

Exploits JWT algorithm confusion where the server's verification library trusts the alg named in the token header, by switching RS256 to…

Performs systematic, hypothesis-driven exploration and debugging across complex codebases using tree-search algorithms and domain adapters.

Analyze datasets to discover patterns, anomalies, and relationships.

Explore the local codebase before changes; a folder outside any repo, or machine state, is research's.

Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known…

Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces.

Investigate AI observability evaluations — `hog` (deterministic code-based), `llm_judge` (LLM-prompt-based), and `sentiment` (user-message…

Investigates distributed application performance using PostHog APM (OpenTelemetry span) data via MCP.

Guides exploration of $autocapture events captured by posthog-js to understand user interactions, find CSS selectors (especially data-attr…

Explore and diagnose a PostHog endpoint's execution logs — error messages, failed runs, cache misses, slow runs, or unexpected row counts…

Debug and inspect LLM/AI agent traces using PostHog's MCP tools.

Explore PostHog MCP intent clusters — agent goals grouped by semantic similarity, with each cluster's tool distribution and error rates…

Investigate individual PostHog MCP sessions — the sequence of tool calls a single agent made in one run, what it was trying to do, and…

Investigate the quality of PostHog MCP tool calls — error rates, latency, reach, and which tools are failing or slow.

Starting point for exploring how a PostHog MCP server's tools are used — routes a broad question to the typed tool that answers it.

Explore PostHog's Inbox and act on what it surfaces — the place where signal reports cluster into actionable issues and trends.