Name: adding-product-alerting
Rating: 67.2 (1 reviews)
Author: PostHog

adding-product-alerting

Recommended repo-engineering guide when adding alerting to a PostHog product or extending the shared alerts platform. Routes lifecycle state machines, AlertPolicy, destinations, HogFunction dispatch, email, fixed-cadence and calendar scheduling, insight evaluation, the AlertWizard, and shared alert editor components. Use for product alert implementations, shared destination types, lifecycle or scheduling options, advanced alert settings, and platform alert infrastructure. Not for configuring alerts in an existing product.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

71%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 well-structured, actionable engineering guide with clear routing and verification checkpoints. Its main weakness is progressive disclosure: all four reference files it points to are missing from the bundle.

Suggestions

Ship the four referenced reference files (references/adopting-platform-alerting.md, frontend-alerting.md, extending-platform-alerting.md, architecture.md) so the Route-first table and appendix resolve to real content.

Tighten the prose in 'Review shared changes as one alert system' and 'Treat alerting as an end-to-end system' into terser bullets to lift conciseness toward 5.

Make the per-change feedback loops explicit (e.g., 'on mismatch → isolate stage → re-run synthetic check') so the recovery path reads as a closed loop rather than scattered guidance.

Dimension	Reasoning	Score
Conciseness	Dense, domain-specific guidance that assumes Claude's competence (no padding about what state machines or email are), with only minor prose in the 'Review shared changes' and end-to-end sections that could be tightened.	4 / 5
Actionability	Concrete, actionable instruction — names exact files (products/alerts/backend/facade/lifecycle.py, scheduling.py), contracts (AlertPolicy, CheckInput, apply_outcome), and a 4-step test procedure; minor gaps as it is routing/overview rather than copy-paste code.	4 / 5
Workflow Clarity	A Route-first decision table plus a numbered end-to-end test path with explicit verification checkpoints ('Read the alert back and confirm the destination is visible', 'Confirm the delivery worker accepts the notification'), though feedback loops are distributed rather than fully self-contained per flow.	4 / 5
Progressive Disclosure	The structure is well-designed — an overview with a Route table and appendix pointing one level deep to adopting-platform-alerting.md, frontend-alerting.md, extending-platform-alerting.md, and architecture.md — but none of those referenced files exist in the bundle, so navigation is broken and the reader is stranded.	3 / 5
	Total	15 / 20 Passed

Description

92%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.

A strong, specific description that clearly states what it routes and when to use it, with an explicit not-for boundary. Slightly jargon-heavy in its trigger terms but otherwise excellent.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'Routes lifecycle state machines, AlertPolicy, destinations, HogFunction dispatch, email, fixed-cadence and calendar scheduling, insight evaluation, the AlertWizard, and shared alert editor components' — giving comprehensive coverage of the domain.	5 / 5
Completeness	Explicitly answers both what ('Recommended repo-engineering guide… Routes lifecycle state machines…') and when ('Use for product alert implementations, shared destination types…'), capped with a 'Not for configuring alerts in an existing product' boundary clause.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('adding alerting to a PostHog product', 'extending the shared alerts platform', 'advanced alert settings'), but leans on product-specific jargon (HogFunction dispatch, AlertWizard) and omits a few plainer synonyms.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (PostHog shared alerting platform engineering) with distinct triggers and an explicit out-of-scope boundary, so conflict risk with other skills is minimal.	5 / 5
	Total	19 / 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
relative_links	Relative link issues: 9 missing	Warning
referenced_paths_exist	Referenced path issues: 9 missing	Warning

	Total	14 / 16 Passed

Repository: PostHog/posthog
Path: .agents/skills/adding-product-alerting/SKILL.md
Commit: 130f3a1

Reviewed: 9 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.