CtrlK
BlogDocsLog inGet started
Tessl Logo

agui-dotnet-troubleshoot

Diagnose and fix problems in an AG-UI .NET app built on the AG-UI SDK — when streaming chat, tools, state, interrupts, or the transport misbehave. USE FOR: the agent forgetting earlier turns / history truncated; update.ConversationId always null; state or lifecycle updates that never arrive; a tool throwing at runtime or producing AOT/trim warnings; an unknown-tool error mid-run; 406 Not Acceptable from the endpoint; an interrupt or approval that won't resume; and inspecting the raw AG-UI event stream (curl SSE frames, RawEvent on ChatResponseUpdate.RawRepresentation) to see what's actually on the wire. DO NOT USE FOR: first-time setup or the happy path (use agui-dotnet-streaming-chat); implementing a specific feature cleanly (use the matching agui-dotnet-* skill).

80

Quality

100%

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

100%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 lean, high-signal troubleshooting reference: every section pairs a non-obvious root cause with an exact executable fix, and the closing verify section closes the loop. It is exemplary on conciseness and actionability with no notable weaknesses.

DimensionReasoningScore

Conciseness

Each section is 1–2 sentences of genuinely non-obvious SDK behavior ('the server is stateless and keeps nothing between turns', 'a non-null ConversationId would make wrappers send only deltas') followed by a concrete Fix — no padding and no explanation of concepts Claude already knows. Matches the lean 'every token earns its place' anchor.

5 / 5

Actionability

Every fix names the exact executable API (history.AddMessages(updates.ToChatResponse()), AIFunctionFactory.Create(method, serializerOptions: ctx.Options), .UseFunctionInvocation(fic => fic.TerminateOnUnknownCalls = true)), plus a copy-paste curl command and a runnable C# pattern for RawEvent inspection. Fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

A clear symptom→cause→fix structure with an explicit final validation step ('reproduce the original prompt and confirm the symptom is gone against the wire stream'), giving the diagnostic loop a feedback checkpoint. No destructive/batch operation applies, so the cap at 3 is not triggered.

5 / 5

Progressive Disclosure

The skill is self-contained with no bundle files; each per-symptom section is only a few lines and well-signaled with headers, so nothing that belongs in a separate file is inlined and navigation is trivial.

5 / 5

Total

20

/

20

Passed

Description

100%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.

Excellent description: concrete what/when, natural symptom-level trigger phrases, and explicit boundaries against sibling skills. It scores at the top of every dimension with no padding or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities (diagnose/fix streaming chat, tools, state, interrupts, transport problems) plus a comprehensive itemized symptom list ('update.ConversationId always null', '406 Not Acceptable', 'AOT/trim warnings'), matching the comprehensive-coverage anchor rather than the minor-gaps anchor at 4. No vague fluff, no first/second-person voice.

5 / 5

Completeness

Explicitly answers 'what' ('Diagnose and fix problems in an AG-UI .NET app built on the AG-UI SDK') and 'when' with a concrete 'USE FOR:' trigger list plus a 'DO NOT USE FOR:' clause. Both are explicit and concrete, matching the top anchor rather than the less-explicit 'when' of 4.

5 / 5

Trigger Term Quality

The symptom phrases are exactly what a user would naturally say ('history truncated', 'always null', '406 Not Acceptable', 'interrupt or approval that won't resume', 'AOT/trim warnings'), including synonyms and wire-level terms (curl SSE frames, RawEvent) — comprehensive natural-term coverage, above the 'a few natural terms missing' anchor at 4.

5 / 5

Distinctiveness Conflict Risk

Clear troubleshooting niche with distinct symptom triggers, and explicit disambiguation against sibling skills ('use agui-dotnet-streaming-chat' for the happy path, 'use the matching agui-dotnet-* skill' for clean feature work) minimizes conflict risk.

5 / 5

Total

20

/

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.

Validation — 16 / 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.