Name: authoring-scouts
Rating: 73.6 (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 to customize a canonical scout (narrow its scope, retune thresholds, add disqualifiers), tweak a scout's schedule or dry-run posture, write a new scout for a surface the fleet doesn't cover, build a measurement scout that records structured output (an LLM-judge scoring a sample on a schedule — a custom metric no query can compute), or steer a scout without editing it by leaving it a note. Covers the scout SKILL.md anatomy, the report contract, the structured-output channel, the dedupe + scratchpad-memory conventions, scout notes, the per-team skills-store path vs the canonical in-repo path, and the test loop. 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", "leave a note for / give feedback to a scout".

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%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.

A strong, well-architected body: highly actionable tool calls, clear sequenced workflows with checkpoints and a checklist, and excellent progressive disclosure into verified reference files. The only real weakness is conciseness — repeated guidance and lengthy config prose.

Suggestions

Consolidate the dogfood guidance, which is restated three times (Test loop intro, standard loop step 1, and the 'Want to be extra careful?' note) into one authoritative statement to cut recurring tokens.

Tighten the Run posture config bullets — the structured_output_schema and auto_pause_exempt entries read as paragraphs; trim to the essential field semantics and defer extended rationale to a reference file.

Avoid re-explaining dry-run (emit=false) each time it recurs; state it once and reference back rather than re-deriving the guidance.

Dimension	Reasoning	Score
Conciseness	Dense and specific, but the dogfood guidance is repeated three times, dry-run is re-explained repeatedly, and the run-posture and structured_output_schema prose runs long — more than minor over-explanation that could be trimmed.	3 / 5
Actionability	Copy-paste-ready tool calls with exact parameters and argument shapes, concrete config ranges ('run_interval_minutes — 30 to 43200'), and specific error codes (403/429/409) cover the common cases fully.	5 / 5
Workflow Clarity	Numbered sequences (job-before-writing 1–4, test loop 1–4), explicit checkpoints (confirm-hash gate, 'dead on arrival' event check), feedback loops (dogfood → refine → repeat), and a 'Quality bar for a v1 scout' checklist.	5 / 5
Progressive Disclosure	The body is an overview that pushes depth into five well-signaled one-level-deep references (lifecycle-and-testing, scout-patterns, scout-anatomy, report-contract, dedupe-and-memory), all verified present on disk.	5 / 5
	Total	18 / 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.

An exemplary description: concrete capabilities, an explicit Trigger-on clause with natural phrasings, clear what/when coverage, and a distinctive niche. Voice is third-person/infinitive throughout, incurring no voice penalty.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions — 'customize a canonical scout (narrow its scope, retune thresholds, add disqualifiers)', 'tweak a scout's schedule or dry-run posture', 'write a new scout', 'build a measurement scout', 'steer a scout... by leaving it a note' — comprehensive rather than just several.	5 / 5
Completeness	Clearly states both what ('How to author, edit, and adapt PostHog Signals scouts' plus enumerated sub-tasks) and when (concrete 'Trigger on...' phrases), matching the anchor that answers both explicitly.	5 / 5
Trigger Term Quality	Explicit 'Trigger on' list gives natural phrases users would say ('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') with synonym coverage.	5 / 5
Distinctiveness Conflict Risk	A narrow, well-defined niche — PostHog Signals scheduled agents writing reports to the Signals inbox — with distinctive triggers and minimal overlap with other 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: 1 missing	Warning

	Total	14 / 16 Passed

Repository: PostHog/posthog
Path: products/signals/skills/authoring-scouts/SKILL.md
Commit: d293866

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.