agui-dotnet-sample-step

Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN_<Name> Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic FakeChatClient for replay, and registering it in the Step tables in AGENTS.md / docs/architecture.md. DO NOT USE FOR: the replay/Verify integration-test mechanics (use agui-dotnet-integration-tests), the dojo scenarios under samples/AGUIClientServer (use agui-dojo), or protocol/wire changes the sample exercises (use agui-dotnet-wire-types / agui-dotnet-transport).

Quality

92%

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

100%

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

An exemplary skill body: concise, highly actionable with real code and commands, a clearly sequenced wiring workflow with verification, and clean routing of details to sibling skills. No meaningful weaknesses to address.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence — it never explains what AG-UI, .NET, or MEAI are, and each section (Anatomy, Wiring, Verify, Anti-patterns) earns its place, matching the lean-and-efficient anchor.	3 / 3
Actionability	It provides concrete, copy-paste-ready guidance: exact csproj references, a code snippet for SampleClient.RunAsync, and specific 'dotnet build'/'dotnet test --filter' commands with real file paths, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The Wiring section is a numbered sequence (solution, integration-test refs, replay test, doc tables) followed by an explicit Verify block with build/test commands and an end-to-end run, giving clear validation checkpoints for a multi-artifact task.	3 / 3
Progressive Disclosure	The body is well-sectioned and routes deeper mechanics to sibling skills via bold skill names with a one-level-deep References section; with no bundle files present, the in-file organization is appropriate and navigable.	3 / 3
	Total	12 / 12 Passed

Description

85%

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, highly specific description with explicit USE FOR / DO NOT USE FOR triggers and clear boundary-setting against sibling skills. The only weakness is that its trigger terms lean on internal jargon rather than natural user phrasing.

Suggestions

Add natural-language trigger phrases (e.g. 'add a sample Step', 'new GettingStarted example') alongside the technical terms so users can surface the skill with everyday wording.

Consider a brief plain-language summary of the feature before the jargon-heavy 'USE FOR' list to improve first-readability.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'wiring it into AGUI.slnx and the integration-test project' and 'giving it a deterministic FakeChatClient for replay', matching the multiple-specific-actions anchor rather than the domain-only level below.	3 / 3
Completeness	It clearly answers what ('Add a GettingStarted sample Step ... that demonstrates one protocol feature') and when via explicit 'USE FOR' / 'DO NOT USE FOR' triggers, matching the both-what-and-when anchor and exceeding the implied-when level below.	3 / 3
Trigger Term Quality	The 'USE FOR' clause gives strong intent guidance, but the trigger terms are internal jargon (e.g. 'StepNN_<Name> Server+Client pair', 'AGUI.slnx', 'FakeChatClient') rather than phrases a user would naturally say; it lacks common natural variations, so it sits below the good-coverage anchor.	2 / 3
Distinctiveness Conflict Risk	The 'DO NOT USE FOR' clause carves explicit boundaries against sibling skills (integration-tests, dojo, wire-types, transport), giving it a clear niche unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 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: ag-ui-protocol/ag-ui
Path: .github/skills/agui-dotnet-sample-step/SKILL.md
Commit: 34c3e0c

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.