CtrlK
BlogDocsLog inGet started
Tessl Logo

agui-dotnet-reasoning

Surface a reasoning/thinking model's intermediate thoughts separately from its final answer with the AG-UI .NET SDK — so a client can show the agent "thinking" before it responds, and handle that reasoning trace correctly across turns. USE FOR: distinguishing the model's reasoning trace from its answer on the client by matching TextReasoningContent vs TextContent in each ChatResponseUpdate's Contents; rendering thinking and answer in different ways as they stream; deciding whether to carry the reasoning text into later turns (whether to append/resend the model's reasoning back into conversation history). DO NOT USE FOR: plain text streaming with no reasoning display (use agui-dotnet-streaming-chat); tools, shared state, interrupts, multimodal, generative UI, or protobuf.

75

Quality

92%

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%

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

A tight, well-structured skill body: executable code, a clear single-action workflow, an explicit Verify section, and concise anti-patterns. No padding and no unnecessary external references for a skill this size.

DimensionReasoningScore

Conciseness

Lean body that skips generic primer material and only adds API-specific knowledge Claude would not already know (TextReasoningContent vs TextContent on update.Contents); every section earns its place.

3 / 3

Actionability

Provides a complete, executable C# snippet using pattern matching on update.Contents with clearly-labeled render hooks, plus concrete guidance to render deltas as they arrive rather than buffering.

3 / 3

Workflow Clarity

For a single-purpose skill the action is unambiguous (iterate Contents, branch on type, render), and a Verify section provides explicit checkpoints confirming the reasoning arrives before the answer and stays on a separate render path.

3 / 3

Progressive Disclosure

Under 50 lines with no external references needed; content is well-organized into Goal, the core pattern, Anti-patterns, and Verify sections, which satisfies the simple-skill bar.

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 trigger guidance and clear disambiguation from sibling skills. The only weakness is jargon density in the trigger phrasing, which blurs the natural-language terms a user might actually say.

Suggestions

Lead the USE FOR clause with plain phrasings a user would say ('show the model's thinking before its answer', 'stream reasoning separately') before the API type names, so trigger matching does not depend on type jargon.

Trim the parenthetical '(whether to append/resend the model's reasoning back into conversation history)' to one term to reduce verbosity.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'matching TextReasoningContent vs TextContent', 'rendering thinking and answer in different ways', 'deciding whether to carry the reasoning text into later turns' — rather than vague language.

3 / 3

Completeness

Clearly states what it does ('Surface a reasoning/thinking model's intermediate thoughts separately') and gives explicit when-guidance via 'USE FOR:' and 'DO NOT USE FOR:' clauses.

3 / 3

Trigger Term Quality

Natural terms like 'reasoning/thinking', 'show the agent thinking', and 'reasoning trace' are present, but the description is heavily interleaved with API type names (ChatResponseUpdate, TextReasoningContent) that a user would not naturally say.

2 / 3

Distinctiveness Conflict Risk

A clear narrow niche (reasoning display in AG-UI .NET) with an explicit 'DO NOT USE FOR' redirecting plain streaming to agui-dotnet-streaming-chat, making wrong-skill triggering unlikely.

3 / 3

Total

11

/

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.