CtrlK
BlogDocsLog inGet started
Tessl Logo

agui-dotnet-integration-tests

Write integration tests for the AG-UI .NET SDK. USE FOR: adding a new AG-UI event type and covering it end-to-end, testing SSE or protobuf streaming through the hosting pipeline, verifying AGUIChatClient maps events to ChatResponseUpdate, multi-turn conversation tests, parameterizing a test over Json/Protobuf transports, adding or updating a GettingStarted sample replay/Verify snapshot. Covers: WebApplicationFactory + DelegatingStreamingChatClient setup, IChatClient-based assertions with Assert.Collection, TransportFormat [Theory] (Json/Protobuf), recording/replay capture infrastructure, and the 8-capture-point Verify baselines. DO NOT USE FOR: unit tests of event serialization (use tests/AGUI.Abstractions.UnitTests) or stream-conversion unit tests (use tests/AGUI.Server.UnitTests).

72

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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, actionable skill body: executable code patterns, a clear authoring procedure, and well-organized reference sections that capture genuinely non-obvious project conventions. Minor gaps are a missing run-and-confirm validation step in the main procedure and a few trimmable inline reference blocks.

Suggestions

Add an explicit final step to the 'Procedure: writing a new integration test' sequence: run `dotnet test tests/AGUI.Hosting.AspNetCore.IntegrationTests/` and confirm the new test passes for both Json and Protobuf (and, for sample tests, that baselines were reviewed before committing).

Consider moving the full 8-capture-point baseline naming table and project-layout tree into a references file (e.g. references/capture-points.md) referenced one level deep, keeping SKILL.md as a leaner overview.

Trim the per-file annotations in the project-layout tree to one-line essentials; some descriptions (e.g. ChatResponseUpdateCaptureConverter, AGUIServerSentEventsResult) duplicate detail already covered in the Architecture section.

DimensionReasoningScore

Conciseness

Mostly lean and assumes .NET competence (no generic explanations of WebApplicationFactory or Assert.Collection); the dense project-layout tree and 8-capture-point table earn their place by capturing non-obvious project specifics, though a few inline reference blocks could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready, executable guidance: full [Theory]/[InlineData] skeletons, CreateClient(handler, format) usage, Emit* helpers, Assert.Collection assertions on u.RawRepresentation, and the 'dotnet test ...' run command covering the common cases.

5 / 5

Workflow Clarity

The numbered 'Procedure: writing a new integration test' (steps 1–6) gives a clear sequence and the 'Updating baselines' section includes a review/accept feedback loop, but the main procedure omits an explicit 'run dotnet test and confirm it passes' validation checkpoint.

4 / 5

Progressive Disclosure

A single well-sectioned file with clearly signaled one-level external pointers ('Read those first' → sdks/dotnet/AGENTS.md and docs/architecture.md); no bundle files are present, and the inline layout/capture-point reference material is appropriately placed for this test-writing skill.

4 / 5

Total

17

/

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.

An excellent description: concrete, third-person, with explicit USE FOR / DO NOT USE FOR trigger guidance and clear distinctiveness from sibling test skills. The only minor gap is trigger-term naturalness, which leans heavily on SDK-specific jargon.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'adding a new AG-UI event type and covering it end-to-end, testing SSE or protobuf streaming... verifying AGUIChatClient maps events to ChatResponseUpdate, multi-turn conversation tests, parameterizing a test over Json/Protobuf transports, adding or updating a GettingStarted sample replay/Verify snapshot' — with comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what ('Write integration tests for the AG-UI .NET SDK') and when ('USE FOR:' with concrete triggers plus 'DO NOT USE FOR:' redirection to sibling unit-test projects).

5 / 5

Trigger Term Quality

'USE FOR:' and 'DO NOT USE FOR:' supply concrete, natural trigger phrases ('adding a new AG-UI event type', 'multi-turn conversation tests', 'parameterizing a test over Json/Protobuf transports'), but the terms are domain-jargon-heavy and a few common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (AG-UI .NET SDK integration tests) and the 'DO NOT USE FOR:' clause explicitly redirects serialization and stream-conversion unit tests to other projects, minimizing conflict risk.

5 / 5

Total

19

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ag-ui-protocol/ag-ui
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.