CtrlK
BlogDocsLog inGet started
Tessl Logo

generate-code-cs

Generate the code from typespec for C#. Parameter: C# SDK repository root location <cs_root>.

54

Quality

60%

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

Fix and improve this skill with Tessl

tessl review fix ./sdk/ai/.github/skills/azure-ai-projects-generate-code/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

The body is a thorough, largely executable workflow with good section structure and an appropriately offloaded customization reference. Its main weaknesses are powershell/bash command duplication and trivial git examples that inflate token count, plus somewhat implicit validation checkpoints across the batch package operations.

Suggestions

Collapse the near-identical powershell and bash blocks (e.g., note once that commands run in either shell, or show a single block per command) to cut a substantial amount of duplicated tokens.

Remove or shorten trivial git examples (git diff, git stash/checkout/pull) that Claude already knows, keeping only the repo-specific commands.

Make the customization reference a clearly signaled nav entry (e.g., a '## Code customization → See references/customization.md' section) and add an explicit validation checklist for the three-package post-processing loop.

DimensionReasoningScore

Conciseness

The body is mostly efficient with direct imperative steps and no basic-concept padding, but it duplicates nearly every command in both powershell and bash blocks and includes trivial git examples (git diff, git stash) Claude already knows, which could be tightened.

3 / 5

Actionability

It provides concrete, mostly copy-paste-ready commands (dotnet build /t:GenerateCode, npm exec tsp-client update, gh pr create, dotnet pack) with real flags and an EPERM recovery path, but placeholders like <cs_root>/<package>/<branch> and a mismatched bash invocation of a .ps1 script leave minor gaps.

4 / 5

Workflow Clarity

A clearly sequenced multi-section workflow (update code, post-process, samples, changelog, PR, alpha, package) with an EPERM feedback loop and a compile-check/customize-on-error loop; validation is present but somewhat implicit and there is no explicit checklist for the batch three-package operations.

4 / 5

Progressive Disclosure

The body is a well-structured overview and correctly offloads the large customization detail to a real, well-organized references/customization.md (one level deep), but the reference is signaled only in prose rather than a clearly labeled navigation section.

4 / 5

Total

15

/

20

Passed

Description

53%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.

The description is specific and distinct, clearly conveying a single concrete action for a narrow domain, but it omits any 'Use when' trigger guidance and has limited keyword coverage. Adding an explicit trigger clause and a few synonyms would raise completeness and trigger-term quality.

Suggestions

Add a 'Use when...' clause naming concrete trigger phrases, e.g. 'Use when the user needs to regenerate the C# SDK from TypeSpec or update generated Azure.AI.* packages.'

Broaden trigger terms with natural synonyms users might say, such as 'regenerate', 'Azure SDK', 'tsp-client', or 'code generation'.

Mention the key packages (Azure.AI.Projects, Azure.AI.Projects.Agents, Azure.AI.Extensions.OpenAI) to strengthen specificity and distinctiveness.

DimensionReasoningScore

Specificity

The description names the domain (C# typespec code generation) and one concrete action ('Generate the code') plus a parameter, matching the anchor that names a domain with 1-2 concrete actions but is not comprehensive.

3 / 5

Completeness

It states a clear 'what' (generate code from typespec for C#) but has no 'Use when...' or equivalent 'when' clause, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

It includes some relevant keywords ('Generate the code', 'typespec', 'C#') but misses common variations or synonyms, fitting the anchor for some relevant keywords without comprehensive coverage.

3 / 5

Distinctiveness Conflict Risk

'Generate the code from typespec for C#' is a narrow, distinct niche with minor overlap risk against closely related skills, though the lack of an explicit trigger phrase keeps it below a 5.

4 / 5

Total

13

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Azure/azure-sdk-for-net
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.