Name: authoring-scouts
Rating: 74.4 (1 reviews)
Author: PostHog

authoring-scouts

How to author, edit, and adapt PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox. Use when a user wants to customize a canonical scout for their own setup (narrow its scope, retune its thresholds, add disqualifiers), tweak a scout's schedule or dry-run posture, or write a brand-new scout from scratch for a specific use case (a custom event, a product surface no canonical scout covers), or steer a scout without editing it at all by leaving it a note. Covers the scout SKILL.md anatomy, the report contract, the dedupe + scratchpad-memory conventions, the scout-notes steering channel, the per-team skills-store path vs the canonical in-repo path, and the write-and-inspect test loop (with dry-run as an optional safety net). Trigger on "write/edit/customize a signals scout", "new scout for X", "tune my scout schedule", "make a scout that watches <event>", "leave a note for / give feedback to a scout", "tell the scouts about X".

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%

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

A well-architected instruction skill: actionable tool calls, a clearly sequenced test loop with validation checkpoints, and clean progressive disclosure to real reference files. The only weakness is conciseness — the body repeats the dry-run and tool-rename material and runs long, costing recurring tokens on every run.

Suggestions

Consolidate the dry-run / `emit=false` guidance into one place (Run posture or Test loop) and reference it rather than restating it three times across sections.

Move the legacy `signals-scout-*`→`scout-*` tool-rename aside into a single 'deprecated / old patterns' note instead of repeating it inline in 'The job before the writing'.

Tighten 'Steering with notes' and 'Quality bar for a v1 scout' by leading with the imperative and trimming the rationale sentences that restate earlier points.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence (no generic concept explanations), but at ~178 lines it repeats some material — the dry-run/`emit=false` guidance and the legacy `signals-scout-*` tool-rename aside each reappear across sections — and could be tightened to fully earn the top anchor.	2 / 3
Actionability	Highly executable: concrete tool calls with arguments (`posthog:scout-create-prepare`, `posthog:scout-config-update`, `posthog:scout-run-now {"id": <config_id>}`), exact parameter ranges (`run_interval_minutes` — 30 to 43200), and copy-ready command sequences.	3 / 3
Workflow Clarity	The standard 'dogfood → run once ready → inspect' loop is explicitly sequenced with validation checkpoints (confirm/hash handshake, async poll of `-runs-list`/`-runs-retrieve`, dry-run as a safety net, budget/quota warnings), and the destructive/batched-run risks carry explicit feedback-loop guidance.	3 / 3
Progressive Disclosure	SKILL.md is a clear overview that pushes depth into real, well-signaled one-level-deep references — `references/scout-patterns.md`, `scout-anatomy.md`, `report-contract.md`, `dedupe-and-memory.md`, `lifecycle-and-testing.md` — each of which exists and is linked with a one-line purpose statement; no nested-reference chaining.	3 / 3
	Total	11 / 12 Passed

Description

100%

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

A rich, specific third-person description that names concrete actions, gives an explicit 'Use when' clause, and quotes realistic trigger phrases for a well-scoped niche. It is on the longer side, but the content earns its length and the description is clearly distinguishable from sibling skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'customize a canonical scout (narrow its scope, retune its thresholds, add disqualifiers), tweak a scout's schedule or dry-run posture, write a brand-new scout from scratch, steer a scout without editing it at all by leaving it a note' — matching the top anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both 'what' (author/edit/adapt scouts, anatomy, report contract, dedupe/memory, notes, paths, test loop) and 'when' via an explicit 'Use when a user wants to...' clause plus quoted trigger phrases, hitting the top anchor.	3 / 3
Trigger Term Quality	Strong coverage of natural user phrasings quoted as triggers — 'write/edit/customize a signals scout', 'new scout for X', 'tune my scout schedule', 'make a scout that watches <event>', 'leave a note for / give feedback to a scout' — terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	A tight niche (PostHog Signals scouts, `signals-scout-` prefix) with distinctive triggers unlikely to fire for unrelated skills; the companion read-only skill is even named separately ('exploring-scouts'), reducing overlap.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: PostHog/posthog
Path: products/signals/skills/authoring-scouts/SKILL.md
Commit: 8454d73

Reviewed: about 13 hours 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.