authoring-scouts

This skill teaches how to author, edit, and adapt PostHog Signals scouts: scheduled agents that scan projects and emit findings to an inbox.

by PostHogOfficial publisherNot reviewed

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 10,600 tokenswhen the skill loads
GitHub stars: 88on posthog/ai-plugin
Scripts: None found

What it does

“Write, edit, and adapt PostHog Signals scouts: scheduled agents that scan a project and report findings. Use to change a canonical scout's scope, thresholds, schedule, or dry-run settings; add a scout for an uncovered surface; record structured output from scheduled LLM scoring; or give feedback through notes. Covers SKILL.md structure, report requirements, follow-up report checks, structured output, duplicate detection, scratchpad memory, scout notes, per-team skills-store and canonical repository edits, and testing. Trigger on "write/edit/customize a signals scout", "new scout for X", "tune my scout schedule", "make a scout that watches <event>", "score/judge/measure X with a scout", "structured output from a scout", "scout output to Slack", "leave a note for / give feedback to a scout".”

The author's description, from SKILL.md

Generated summary from the skill's own text

This skill teaches how to author, edit, and adapt PostHog Signals scouts: scheduled agents that scan projects and emit findings to an inbox. It covers scout structure, report requirements, memory management, configuration, reference patterns, and deployment to either a team's own skill store or PostHog's canonical repository.

When to use it

Customizing existing scouts for a specific project's needs
Writing new scouts for surfaces not covered by canonical fleet
Tuning scout schedules, scopes, or output thresholds
Building scouts with structured LLM scoring and cross-run memory

When not to

Only wanting to change run schedule or enabled state without authoring
Projects where no suitable data source exists to monitor

Review

Not reviewed by a person yet. The trust card below shows what our automated checks found at the pinned commit.

Trust card

What our automated checks found

At commit e0fbf5e742fb4242c4ea509b395b2e343642f0b7, checked Oct 8, 2026.

License: No license statedno license file, field or repository license
Scripts: None found
Network domains: None found
allowed-tools: None requested
Unpinned packages: None found
Spec issues: None found
Files: 7 files, 303 KB in totalLargest: references/scout-patterns.md (149 KB)
Context cost: Description: 800 characters, in context whenever the agent runs.Body: about 10,600 tokens, in context when the skill loads.
Warnings: License not statedno license file, field or repository license

Automated checks look for known patterns and can be bypassed. They decide what a reviewer reads first. This is not a guarantee.

Pins

Pin history

e0fbf5eOct 9, 2026Current

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 authoring-scouts

Installs 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 authoring-scouts@e0fbf5e742fb4242c4ea509b395b2e343642f0b7

Installs the commit we checked (e0fbf5e).

Copy by hand

Download the folder at e0fbf5e and put it in .claude/skills/authoring-scouts for Claude Code and in .agents/skills/authoring-scouts for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at e0fbf5e

Claude Code plugin

/plugin install posthog@claude-plugins-official

The 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 "authoring-scouts" by PostHog.

Source, pinned to commit e0fbf5e742fb4242c4ea509b395b2e343642f0b7:
https://github.com/posthog/ai-plugin/tree/e0fbf5e742fb4242c4ea509b395b2e343642f0b7/skills/authoring-scouts

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/authoring-scouts/ for Claude Code and .agents/skills/authoring-scouts/ 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/authoring-scouts

SKILL.md at the pin

The license of this skill does not let us show its files here.

View SKILL.md on GitHub at e0fbf5e

Files

SKILL.md43 KB · 0d1bed8a1da5
references/
dedupe-and-memory.md19 KB · 7725f4dae5fa
lifecycle-and-testing.md12 KB · 9904bd56f85a
report-checks.md7.8 KB · 42cbd07b120c
report-contract.md59 KB · 81c916ea5e96
scout-anatomy.md13 KB · 43f37d5a6764
scout-patterns.md149 KB · 50fabe1d9fc9

7 files, 303 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at e0fbf5e

All 50 skills from PostHog

authoring-scouts

What it does

When to use it

When not to

Install

Copy for your agent

SKILL.md at the pin

Files

More from PostHog

analyzing-experiment-session-replays

analyzing-offline-evaluations

auditing-warehouse-view-health

authoring-data-quality-checks