CtrlK
BlogDocsLog inGet started
Tessl Logo

agui-dotnet-agents-sync

Keep the AG-UI .NET SDK docs (sdks/dotnet/AGENTS.md and docs/architecture.md) in sync with the real code tree after structural changes. USE FOR: "update AGENTS.md / docs/architecture.md", "check the dotnet docs are current", verifying docs after a .NET SDK refactor (package rename, added/removed project, changed endpoint pattern, new/renamed test project, sample step added, new convention). DO NOT USE FOR: writing product code or tests (follow AGENTS.md itself), Python/TypeScript SDK docs, or generic markdown editing unrelated to the dotnet SDK structure.

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

85%

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

A high-quality, highly actionable docs-sync skill with explicit commands, a concrete drift checklist, and a verification loop. The only weakness is repetition of the 'derive from the tree' rule across multiple sections, which inflates token cost without adding new guidance.

Suggestions

Consolidate the 'derive from the tree, not from memory' guidance into one place (e.g. Process step 1) and reference it from the intro quote and anti-pattern #1 rather than restating it fully each time.

Merge the Microsoft.AspNetCore grep fact so it appears once — either in the Drift checklist table or the 'Deriving ground truth' command block — instead of being repeated in both.

Consider folding the 'Deriving ground truth' command block into the Drift checklist as a third column, since both already pair each claim with its reconciliation command.

DimensionReasoningScore

Conciseness

The body is dense and free of concept-explanation fluff, but the core rule 'derive from the tree, not from memory/the doc' is restated in the intro quote, Process step 1, the 'Deriving ground truth' section, and anti-pattern #1, and the Microsoft.AspNetCore grep is repeated across the checklist and command block — it could be tightened.

2 / 3

Actionability

Provides fully executable PowerShell commands (Select-String, Get-ChildItem) with concrete paths and patterns, plus a precise drift-checklist table mapping each doc claim to a reconciliation command — copy-paste ready.

3 / 3

Workflow Clarity

A clear four-step Process (establish ground truth → drift scan → fix surgically → verify) with an explicit validation checkpoint in step 4 ('Re-grep every symbol/name you wrote to confirm it exists') and an optional build verification.

3 / 3

Progressive Disclosure

No bundle files exist, so the skill is a single well-organized SKILL.md with clearly labeled sections (Process, Drift checklist, Deriving ground truth, Anti-patterns, Files to mine); organization is clean and navigation is trivial.

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 tight, third-person description that nails what, when, and when-not with concrete trigger language and a narrow scope. It is among the stronger examples in the rubric's reference set.

DimensionReasoningScore

Specificity

Lists concrete actions (keep AGENTS.md and docs/architecture.md in sync with the code tree) and enumerates specific structural-change scenarios such as 'package rename, added/removed project, changed endpoint pattern, new/renamed test project, sample step added'.

3 / 3

Completeness

Explicitly states both what it does (reconcile docs against the live tree after structural changes) and when to use it via a clear 'USE FOR' clause, plus a 'DO NOT USE FOR' boundary; both what and when are present and explicit.

3 / 3

Trigger Term Quality

Includes natural phrases a user would actually say — 'update AGENTS.md / docs/architecture.md', 'check the dotnet docs are current' — alongside concrete refactor triggers, giving good coverage of likely invocation language.

3 / 3

Distinctiveness Conflict Risk

Scoped tightly to the AG-UI .NET SDK docs and explicitly excludes Python/TypeScript SDK docs, product code, and generic markdown editing, giving it a clear niche unlikely to trigger the wrong skill.

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.