Name: exploring-scouts
Rating: 68 (1 reviews)
Author: PostHog

exploring-scouts

How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox. Use when a user wants to understand what scouts they have, how each one is behaving, and whether the fleet is actually working. Covers surveying the fleet and its schedules, reading recent scout runs and drilling into a single run's reasoning, inspecting the durable scratchpad memory the fleet has built up, tracing a run to the reports it wrote or edited, and assessing a scout's health and performance over time (cadence, success rate, report rate, signal-to-noise). Read-only and exploratory — to write or tune a scout, use `authoring-scouts` instead. Trigger on "what are my scouts doing", "how is my <x> scout performing", "show me recent scout runs", "why did this scout find/report nothing", "what has the fleet learned", "explore scout run <id>", "is my scout working".

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with exact tooling, well-sequenced workflows, and a sound progressive-disclosure structure backed by real reference and script files. Its main weakness is conciseness: repeated caveats and length make it noticeably verbose despite the accuracy of its content.

Suggestions

Consolidate the legacy emitted_count / emitted_finding_ids caveat into a single canonical explanation (in scout-data-model.md) and reference it from the other sections instead of restating it four times.

Tighten the last_run_at dispatch-vs-execution point — define the cross-check once in 'Start here' and link back rather than re-explaining it in the survey and health workflows.

Trim the long exclude_types warning and a few gotcha paragraphs to their operative sentences; the current detail is sound but exceeds what each token earns.

Dimension	Reasoning	Score
Conciseness	Largely avoids explaining concepts Claude already knows and earns its tokens with operational gotchas, but it is noticeably verbose: the legacy-channel emitted_count caveat recurs four-plus times, the last_run_at dispatch-vs-execution point repeats, and several passages could be tightened without loss.	3 / 5
Actionability	Provides exact tool names, parameter/field flips (run_id -> id), concrete filter values, and three bundled executable scripts with copy-paste command lines; falls short of a 5 only because some invocations use placeholders (<run_id>) and json-labeled blocks are pseudo tool-calls rather than verbatim runnable commands.	4 / 5
Workflow Clarity	Multiple clearly sequenced numbered workflows plus strong diagnostic branching (three explicit cases, last_run_at vs run-row cross-check, provenance segmentation) for a read-only skill; not a 5 because it stops short of explicit validate->fix->retry feedback loops.	4 / 5
Progressive Disclosure	Real bundle files exist and are referenced one level deep with clear signaling (full field schema in scout-data-model.md, performance playbook in assessing-performance.md, three scripts documented inline); not a 5 because the main body remains long even after offloading detail.	4 / 5
	Total	15 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and well-triggered, naming many concrete read-only actions and providing both an explicit 'Use when' clause and a list of natural trigger phrases. It also cleanly distinguishes itself from the write-side authoring skill, leaving minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — surveying fleet/schedules, reading recent runs and drilling into a single run's reasoning, inspecting the scratchpad memory, tracing runs to emitted/edited reports, and assessing health across cadence/success rate/report rate/signal-to-noise — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (read-only exploration of scout fleet behavior and health) and 'when' (a clear 'Use when...' clause plus concrete trigger phrases), matching the top anchor exactly.	5 / 5
Trigger Term Quality	Explicit 'Trigger on' clause enumerates natural phrasings a user would actually say ('what are my scouts doing', 'how is my <x> scout performing', 'show me recent scout runs', 'is my scout working'), covering multiple synonyms and intent shapes.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (read-only observability of Signals scouts) with an explicit boundary hand-off — 'to write or tune a scout, use authoring-scouts instead' — minimizing overlap with sibling skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: PostHog/posthog
Path: products/signals/skills/exploring-scouts/SKILL.md
Commit: b0fece0

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.