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).

76

Quality

93%

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

87%

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 tight, actionable troubleshooting reference with concrete code fixes per symptom and a verification step. The only mild gap is that the verify loop is described rather than prescribed as an explicit validation gate.

Suggestions

Make 'Verify the fix' an explicit numbered checklist with pass/fail criteria per symptom (e.g., '2. Re-run the second turn; FAIL if history still truncated') to strengthen the validation checkpoint.

Add a short ordering hint at the top (e.g., 'Match your symptom to a section below; if none match, inspect the wire stream') so the diagnostic workflow path is explicit before the symptom list.

DimensionReasoningScore

Conciseness

The body is lean: each section is symptom → cause → 'Fix:' with code, assuming Claude's competence and explaining no general concepts, so every token earns its place.

3 / 3

Actionability

Fixes are fully executable — 'UseFunctionInvocation(fic => fic.TerminateOnUnknownCalls = true)', the curl SSE command, and the RawEvent pattern match — copy-paste ready with specific API calls.

3 / 3

Workflow Clarity

A 'Verify the fix' section gives a reproduce→confirm feedback loop, but the checkpoints are described loosely rather than as strict validation gates, leaving the sequence present but checkpoints somewhat implicit.

2 / 3

Progressive Disclosure

No bundle files exist, so the single-task troubleshooting skill is well-organized into discrete sections; per the simple-skill note, well-organized sections score 3 without external references.

3 / 3

Total

11

/

12

Passed

Description

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.

A high-quality description: concise, concrete, and explicitly scoped with both positive and negative triggers. It distinguishes itself clearly from sibling skills and uses natural symptom language.

DimensionReasoningScore

Specificity

Lists multiple concrete symptom areas (streaming chat, tools, state, interrupts, transport) and specific failure modes like 'update.ConversationId always null' and '406 Not Acceptable', matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicit 'USE FOR:' and 'DO NOT USE FOR:' clauses answer both what the skill does and when to use it, exceeding the explicit-trigger requirement.

3 / 3

Trigger Term Quality

Triggers are phrased as a developer would report them ('the agent forgetting earlier turns', 'an interrupt or approval that won't resume', '406 Not Acceptable'), giving good coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

Names sibling skills explicitly (agui-dotnet-streaming-chat, agui-dotnet-* skills) and scopes to the AG-UI SDK troubleshooting niche, making wrong-skill triggering unlikely.

3 / 3

Total

12

/

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.

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.