Skip to main content
skill CX Codex

signals-scout-tasks — Claude Code skill: what it does, how to install

signals-scout-tasks — a scout skill for PostHog Tasks: it tracks how task runs get delivered and, on a slower pass, looks for the same request coming up again in tasks people wrote.

no license 179 installs ★ 101 updated 2026-11-16

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add PostHog/ai-plugin --skill signals-scout-tasks -a claude-code
Open on GitHub

What signals-scout-tasks does

The skill runs inside the PostHog Signals agent in a Claude sandbox and looks at a project's tasks: what people asked for, and how their runs ended. It reads Postgres system tables system.tasks and system.task_runs with execute-sql. Findings go out through emit_report and edit_report, and only when they clear a bar.

That bar is failed runs divided by the number of distinct tasks that failed. Near 1 across many tasks points to one defect on a shared path, the best thing this lens can find. Far above 1 on a task or two points to something stuck and being retried. A repository at total failure is reported only when at least two different tasks broke. error_message shows up on nearly every failed run, so it proves nothing without a status = 'failed' filter. Probe task_runs.stage with countIf(stage != '') before relying on it.

Nothing runs without the MCP scopes task:read, signal_scout_internal:write and signal_scout_report:write, plus execute-sql, tasks-retrieve and the inbox tools. Always drop origin_product values signals_scout and scout_suggestions: those rows are the scout's own run containers, they can carry the most rows on a busy project, and a report that keeps them grades itself. To name a reviewer, take created_by_id (an integer with no lookup) through tasks-retrieve and read created_by.uuid. The SQL lives in references/queries.md.

What it helps with

  • spot failures piled into one repository instead of spread across the project
  • tell a shared defect apart from one task being retried
  • find repeated requests in human-written tasks
  • keep error messages on cancelled runs from reading as failures
  • filter the scout's own runs out of the sample

Example prompts for the agent

  • Run the tasks scout and show me where failures sit in one repository
  • Check whether people keep asking for the same thing in their tasks
  • Pull a delivery report for the last 14 days

How to install signals-scout-tasks

1Skills CLI (Vercel)

npx skills add PostHog/ai-plugin --skill signals-scout-tasks -a claude-code

2Manually: put the files in place

~/.claude/skills/signals-scout-tasks/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/signals-scout-tasks/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about signals-scout-tasks

How do I install signals-scout-tasks in Claude Code?

Run npx skills add PostHog/ai-plugin --skill signals-scout-tasks -a claude-code. The skill lands at ~/.claude/skills/signals-scout-tasks/SKILL.md.

What is signals-scout-tasks for?

It reads task runs in PostHog and looks for two shapes: one defect hitting many tasks, or a single task stuck on repeats. Less often it checks which requests people keep making.

What does the skill need in order to run?

The scopes task:read, signal_scout_internal:write and signal_scout_report:write, plus execute-sql, tasks-retrieve and the inbox tools. Task text comes through the tasks-* tools, not the system tables.

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set82

The whole set →
review-hog-perspective-logic-correctness review-hog-perspective-logic-correctness reviews one slice of a pull request for correctness: arithmetic, branches, data mapping, database queries. Useful when you want a focused second pass before merging. CX Codex +1 187installs copying-endpoints-across-projects copying-endpoints-across-projects duplicates PostHog API endpoints across projects in the same organization or clones them under a new name. Useful for promoting HogQL endpoints between environments. CX Codex +1 183installs signals-scout-conversations The signals-scout-conversations skill checks PostHog Conversations analytics for SLA breaches, slow first replies, and support-queue imbalances. Use it to spot operational changes across tickets. CX Codex +1 183installs setting-up-data-catalog setting-up-data-catalog fills a project's data catalog: canonical metric definitions, trust marks on warehouse tables, and reviewed join proposals. CX Codex +1 182installs managing-streamlit-apps managing-streamlit-apps controls Streamlit apps in PostHog sandboxes using MCP tools, handling everything from provisioning to safe code patching. CX Codex +1 179installs modeling-activation-metrics modeling-activation-metrics builds an activation model: a per-user or per-account activated flag plus an activation-rate metric. Useful while the “aha moment” is still a guess. CX Codex +1 178installs modeling-conversion-metrics modeling-conversion-metrics builds a reusable conversion model: funnel steps, a conversion window, drop-off and time to convert. Works on PostHog warehouse views in HogQL or in a dbt project. CX Codex +1 178installs writing-streamlit-apps The writing-streamlit-apps skill guides Python code for Streamlit apps that read PostHog data inside a sandbox. Use it when building or debugging dashboards with tables and charts. CX Codex +1 177installs

Project sponsors

Companies that keep this analytics open