creating-replay-vision-scanners
This skill guides agents through creating Replay Vision scanners, which are standing LLM probes that automatically scan future session recordings on a…
Identity proven by GitHub's verified organisation badge (PostHog)
- Agents
- Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, claude.ai and API
- License
- No license stated
- Pin
- e0fbf5epinned Oct 9, 2026
- Context cost
- about 3,200 tokenswhen the skill loads
- GitHub stars
- 88on posthog/ai-plugin
- Scripts
- None found
What it does
“Guides agents through creating and safely sizing a Replay Vision scanner: choosing the scanner type (monitor/classifier/scorer/summarizer), shaping the RecordingsQuery that selects sessions, and — crucially — estimating the credits it will spend and checking the org's remaining budget before creating, so a broad scanner doesn't exhaust the budget on its first scheduled sweep. TRIGGER when: user asks to create, set up, or configure a Replay Vision scanner, OR when you are about to call vision-scanners-create, OR when widening an existing scanner's query, sampling_rate, or sampling_mode (or moving it to a pricier model) via vision-scanners-update. DO NOT TRIGGER when: only reading scanners or observations, deleting a scanner, or running an existing scanner against sessions on demand (vision-scanners-scan-session/-scan-sessions). For a one-off question about sessions you already have, use vision-scanners-inline-scan rather than creating a scanner — the skill's first section covers when that applies.”
Generated summary from the skill's own text
This skill guides agents through creating Replay Vision scanners, which are standing LLM probes that automatically scan future session recordings on a 5-minute schedule. It handles choosing scanner type (monitor, classifier, scorer, or summarizer), building the sessions query, estimating credit spend before creation, and comparing projected costs against the organization's remaining budget to prevent overspending.
When to use it
- User requests creating or configuring a new Replay Vision scanner
- Updating an existing scanner's query, sampling rate, or model
- Need to estimate scanner costs before committing to creation
- Checking if budget remains to support a scanner's monthly spend
When not to
- Only reading existing scanner results or observations
- Deleting a scanner or running a scanner once against known sessions
- Answering a one-off question about specific sessions already recorded
Install
No license stated: install from the publisher's repository, and ask the author before you reuse or share it.
These commands install from the publisher's repository and need no account.
skills CLI
npx skills add posthog/ai-plugin --skill creating-replay-vision-scannersInstalls from the repository's default branch, which may have changed since the commit we checked.
GitHub CLI 2.90 or later
gh skill install posthog/ai-plugin creating-replay-vision-scanners@e0fbf5e742fb4242c4ea509b395b2e343642f0b7Installs the commit we checked (e0fbf5e).
Copy by hand
Download the folder at e0fbf5e and put it in .claude/skills/creating-replay-vision-scanners for Claude Code and in .agents/skills/creating-replay-vision-scanners for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.
Claude Code plugin
/plugin install posthog@claude-plugins-officialThe publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.
Copy for your agent
A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.
Prompt
Install the agent skill "creating-replay-vision-scanners" by PostHog. Source, pinned to commit e0fbf5e742fb4242c4ea509b395b2e343642f0b7: https://github.com/posthog/ai-plugin/tree/e0fbf5e742fb4242c4ea509b395b2e343642f0b7/skills/creating-replay-vision-scanners 1. Download that folder at exactly this commit. Do not use the default branch. 2. Copy every file unchanged, keeping the folder structure, into .claude/skills/creating-replay-vision-scanners/ for Claude Code and .agents/skills/creating-replay-vision-scanners/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist. 3. Do not edit the files, and do not run any script in the folder unless I ask you to. 4. When you are done, list the files you copied and where you put them. Its license is restricted or not stated. Show me the license terms from the repository before you copy anything. Listing and checks: https://www.agentnative.dev/skills/posthog/creating-replay-vision-scanners
SKILL.md at the pin
The license of this skill does not let us show its files here.
Files
- SKILL.md14 KB · d0b99df94a67
1 file, 14 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.
Skill folder on GitHub at e0fbf5eMore from PostHog
analyzing-experiment-session-replays
This skill enables agents to analyze session recordings from experiment variants to identify behavioral differences between control and test groups.
Claude Code, Codex, Cursor +4 · about 2.3K tokens · pinned 6 days ago
analyzing-offline-evaluations
This skill inspects and compares offline AI evaluation experiments stored in PostHog, diagnoses case-level regressions, and tracks scorer changes across…
Claude Code, Codex, Cursor +4 · about 1.5K tokens · pinned 6 days ago
auditing-warehouse-view-health
Audits materialized views in a PostHog data warehouse to identify failed views and flag unused ones that waste compute resources.
Claude Code, Codex, Cursor +4 · about 1.4K tokens · pinned 6 days ago
authoring-data-quality-checks
This skill adds data quality checks (like dbt tests) on warehouse tables, views, and HogQL metrics, supporting assertions such as not-null, uniqueness…
Claude Code, Codex, Cursor +4 · about 2.5K tokens · pinned 6 days ago
authoring-scouts
This skill helps engineers write, edit, and adapt PostHog Signals scouts, scheduled agents that scan projects and report findings to an inbox.
Claude Code, Codex, Cursor +4 · about 10.6K tokens · pinned 6 days ago
building-a-dashboard
This skill constructs or modifies PostHog dashboards by selecting and arranging insight tiles.
Claude Code, Codex, Cursor +4 · about 2.1K tokens · pinned 6 days ago
Related in Observability
debugging-executions
Debug workflow execution failures by inspecting failed nodes, re-running executions, and comparing expected versus actual values.
by n8nOfficial publisher
Claude Code, Codex, Cursor +3 · about 2.5K tokens · pinned 6 days ago
instance-awareness
This skill teaches the agent to resolve ambiguous requests by reading the instance's activity log and workflow history instead of asking the user to clarify.
by n8nOfficial publisher
Claude Code, Codex, Cursor +3 · about 1.3K tokens · pinned 6 days ago
creating-replay-vision-scanners
Guides agents through creating Replay Vision scanners, LLM probes that watch session recordings on a schedule and log findings as observations.
by PostHogOfficial publisher
Claude Code, Codex, Cursor +4 · about 3.3K tokens · pinned 6 days ago
exploring-replay-vision-observations
This skill guides agents through reading observations from Replay Vision scanners, understanding their findings across session recordings, and taking action…
by PostHogOfficial publisher
Claude Code, Codex, Cursor +4 · about 3.3K tokens · pinned 6 days ago
exploring-scouts
Explore and understand PostHog Signals scouts through read-only tools, examining fleet configuration, recent runs, performance metrics, and durable team…
by PostHogOfficial publisher
Contains scripts
Claude Code, Codex, Cursor +3 · about 11K tokens · pinned 6 days ago
investigating-replay
Gathers session recording metadata, user profile, event timeline, and linked error issues in parallel to give a complete investigation when a user provides a…
by PostHogOfficial publisher
Claude Code, Codex, Cursor +4 · about 2.3K tokens · pinned 6 days ago