hybrid-cloud-test-gen
Generate hybrid cloud tests for the Sentry codebase. Use when asked to "generate HC test", "create hybrid cloud test", "write HC test", "add HC test", "write RPC test", "test RPC service", "silo test", "cross-silo test", "outbox test", "API gateway test", or "endpoint silo test". Covers RPC service tests, API gateway tests, outbox pattern tests, and API endpoint tests with silo decorators.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that clearly defines its scope, provides comprehensive trigger terms covering both abbreviations and full phrases, and explicitly states both what it does and when to use it. The description is concise yet thorough, targeting a very specific niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'RPC service tests, API gateway tests, outbox pattern tests, and API endpoint tests with silo decorators.' These are clearly defined, domain-specific test types. | 3 / 3 |
Completeness | Clearly answers both 'what' (generate hybrid cloud tests covering RPC service tests, API gateway tests, outbox pattern tests, and API endpoint tests with silo decorators) and 'when' (explicit 'Use when asked to...' clause with extensive trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including abbreviations ('HC test'), full phrases ('hybrid cloud test'), and domain-specific variations ('RPC test', 'silo test', 'cross-silo test', 'outbox test', 'API gateway test', 'endpoint silo test'). These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific niche (hybrid cloud tests for the Sentry codebase) with domain-specific terminology like 'silo decorators', 'outbox pattern', and 'cross-silo'. Extremely unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill that provides clear step-by-step guidance for generating hybrid cloud tests in the Sentry codebase. Its strengths are the concrete decision tables, decorator/base-class mappings, validation checklist, and critical constraints called out prominently. The main weakness is that the referenced template files are not provided in the bundle, making it impossible to verify the progressive disclosure structure, and some inline descriptions could be tightened.
Suggestions
Provide the four referenced template files (references/rpc-service-tests.md, references/api-gateway-tests.md, references/outbox-tests.md, references/endpoint-silo-tests.md) in the bundle to complete the progressive disclosure structure.
Trim the bullet lists under Steps 3-6 that describe what tests 'must cover' since this information is presumably detailed in the referenced template files — a one-line summary per category would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with good use of tables and quick references, but some sections are slightly verbose (e.g., the bullet lists describing what each test category 'must cover' repeat information that the referenced template files would contain). The context manager quick reference and imports section are well-structured but the inline comments on obvious imports add minor bloat. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific decorator-to-base-class mappings, exact import paths, mirror path conventions for test file placement, a validation checklist, and a run command. The quick reference tables and code blocks are copy-paste ready and leave no ambiguity about what to use in each scenario. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Steps 1-7) with an explicit validation checklist at the end that serves as a feedback loop before presenting generated tests. The decision table in Step 1 routes to the correct category, Step 2 gathers context by reading source files, and Step 7 provides a comprehensive verification checklist covering all critical constraints. | 3 / 3 |
Progressive Disclosure | The skill references four separate reference files (references/rpc-service-tests.md, references/api-gateway-tests.md, etc.) for detailed templates, which is good progressive disclosure design. However, no bundle files were provided, so these references are unverifiable. The SKILL.md itself contains a good amount of inline content that could potentially be further split, but the balance is reasonable for an overview. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- getsentry/sentry
- Commit
552fb5c
- Reviewed
Table of Contents
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.