notification-platform

Guide for adding notifications, custom renderers, or new providers to Sentry's NotificationPlatform. Use when asked to "add notification", "new notification", "notification platform", "send notification", "notification template", "notification renderer", "notification provider", "NotificationPlatform", "notify user", "send email notification", "send slack notification".

3.16x

Quality

100%

Does it follow best practices?

Impact

95%

3.16x

Average score across 2 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

100%Weight 40%Scale 1-3

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

The content is a well-sequenced, token-efficient guide with executable code throughout, a validation/test checkpoint, and a verify checklist. References are appropriately split into one-level-deep, real bundle files.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, using dense glossary/routing tables and executable snippets without explaining basic concepts or padding.	3 / 3
Actionability	Each step ships copy-paste-ready, executable Python with real imports (dataclass, template registration, sending pattern, tests) rather than pseudocode.	3 / 3
Workflow Clarity	A clear Step 1–9 sequence includes a routing table, an explicit Test checkpoint (Step 8) with commands, and a Verify checklist (Step 9) providing a validation feedback loop.	3 / 3
Progressive Disclosure	SKILL.md serves as an overview with well-signaled one-level-deep references (data-and-templates.md, targets-and-sending.md, custom-renderers.md, provider-template.md), all of which exist as real bundle files.	3 / 3
	Total	12 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 concise, specific, and complete, naming three concrete operations and pairing them with an explicit, well-populated "Use when" trigger clause. It is highly distinctive and unlikely to misfire.

Dimension	Reasoning	Score
Specificity	Names three concrete operations — "adding notifications, custom renderers, or new providers" — rather than vague abstractions, matching the multi-action anchor.	3 / 3
Completeness	Explicitly answers both what ("adding notifications, custom renderers, or new providers") and when via a "Use when asked to..." clause with many triggers.	3 / 3
Trigger Term Quality	Provides broad coverage of natural trigger phrases ("add notification", "send email notification", "notify user", etc.) that a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Tightly scoped to Sentry's NotificationPlatform with distinctive terms, making conflict with unrelated skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: getsentry/sentry
Path: .agents/skills/notification-platform/SKILL.md
Commit: b4b3565

Reviewed: 2 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.