subscription

Work with the OpenMeter subscription package. Use when modifying subscription creation, editing, cancellation, plan changes, addons, the sync algorithm, patch system, spec model, workflow layer, or subscription-related tests. Trigger this skill whenever the task touches `openmeter/subscription/...`, subscription views, billing cadences, or the relationship between subscriptions, plans, entitlements, and addons.

Quality

82%

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

65%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 body is a dense, actionable reference with concrete paths, code, and test commands, but it is monolithic with no progressive disclosure into bundle files and recapitulates several points in a pitfalls section. Risky sync operations lack explicit inline validation checkpoints.

Suggestions

Move the addon test-rate-card table and detailed test-wiring snippets into a reference file (e.g. references/testing.md) and link to it one level deep to improve progressive disclosure.

Collapse the 'Non-Obvious Pitfalls' section or cross-reference the canonical sections instead of restating phase timing, sync delete+recreate, and EditRunning/addons verbatim to save tokens.

Add an explicit validate-then-proceed checkpoint (e.g. run the relevant go test command and only continue on green) to the sync-algorithm and mutating-operation editing checklists.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's competence (no explanations of basic concepts), but the 'Non-Obvious Pitfalls' section recapitulates points already made earlier (phase timing, sync delete+recreate, EditRunning/addons, item index as version history), adding redundant tokens. Mostly efficient but could be tightened.	2 / 3
Actionability	Provides concrete file paths, real Go code snippets (interfaces, SpecPath examples, addon-item identification, test wiring), and copy-paste-ready test commands with exact flags, matching the 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	The Editing Checklist gives well-sequenced checklists for service/sync/patch/addon changes and the three-pass sync is laid out clearly, but destructive/batch operations (sync delete+recreate of items) lack inline validate-then-proceed checkpoints; per the rubric this caps workflow clarity at 2.	2 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), and the single ~330-line SKILL.md inlines detailed reference tables and test-fixture data that could be split into separate files. Section organization is good, but content that should be separate is inline with no one-level-deep references, fitting the level-2 anchor.	2 / 3
	Total	9 / 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 specific, third-person, and clearly states both what the skill does and when to trigger it, with concrete file-path and operation triggers. It is a strong, low-conflict description for a codebase-specific skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and subsystems — 'subscription creation, editing, cancellation, plan changes, addons, the sync algorithm, patch system, spec model, workflow layer' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what ('Work with the OpenMeter subscription package') and when with an explicit 'Use when modifying...' and 'Trigger this skill whenever the task touches...' clause, matching the level-3 anchor.	3 / 3
Trigger Term Quality	Covers natural trigger phrasings a developer would use ('modifying subscription...', 'plan changes', 'addons') plus concrete file-path triggers like 'openmeter/subscription/...', giving good coverage of terms users would say. Borderline due to subsystem jargon, but appropriate for a codebase-specific skill.	3 / 3
Distinctiveness Conflict Risk	Tied to a specific named package and concrete file paths, establishing a clear niche unlikely to conflict with other skills.	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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: openmeterio/openmeter
Path: .agents/skills/subscription/SKILL.md
Commit: 1cdc2cb

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.