CtrlK
BlogDocsLog inGet started
Tessl Logo

generate-code-cs

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

45

Quality

47%

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

56%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 content is highly actionable with concrete commands and a clear macro-sequence, but it is verbose from duplicating shell variants, lacks explicit validation feedback loops for batch and destructive operations, and is a monolithic file with a dangling reference rather than properly split materials.

Suggestions

Add explicit validate-then-proceed checkpoints for the batch steps (e.g. after each package's GenerateCode, fail fast on errors before moving to the next package) to lift workflow clarity above the cap.

Move the large sample-generation and CodeGenStubs sections into a separate reference file (e.g. references/samples.md) and link to it, fixing the missing references/customization.md reference.

De-duplicate the powershell/bash command duplication by presenting each command once with a cross-platform note, or collapse the near-identical GenerateCode/update blocks.

DimensionReasoningScore

Conciseness

The body is mostly step-oriented and assumes Claude's competence, but it duplicates every code block in both powershell and bash variants and repeats the same command clusters verbatim, adding avoidable tokens.

3 / 5

Actionability

Provides concrete, copy-paste-ready commands and code snippets (dotnet build, npm exec, git, gh) covering the common cases, with only minor gaps such as un-expanded <package> placeholders.

4 / 5

Workflow Clarity

Steps are well sequenced across clear sections, but batch/destructive operations (regenerating code for three packages, stashing and rebasing, running pipelines) lack explicit validation checkpoints beyond 'make sure it builds', so the cap applies.

3 / 5

Progressive Disclosure

The skill is a monolithic 240-line wall of text with section headers but no separation of the heavy command/script and sample content into reference files; the lone references/customization.md link points to a file that does not exist in the bundle.

2 / 5

Total

12

/

20

Passed

Description

38%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 names a specific, niche task but lacks any trigger guidance ('Use when...') and relies on jargon plus a parameter placeholder instead of natural user phrasing. It is concrete but incomplete as a discoverability signal.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when the user asks to regenerate or update Azure AI C# SDK code from a TypeSpec branch.'

Replace the '<cs_root>' parameter notation in the description with a trigger-phrase framing and reserve parameter details for the body.

Include natural synonyms users might say (e.g. 'regenerate', 'update generated code', 'tsp-client') to improve keyword coverage.

DimensionReasoningScore

Specificity

Names the concrete action ('Generate the code from typespec') and the parameter, but offers only one action with no enumeration of what generation entails, landing between anchor 3 and 4.

3 / 5

Completeness

States a clear 'what' (generate code from typespec for C#) but has no 'when' / 'Use when...' clause at all, so per the guidelines completeness is capped low and the 'what' alone pushes it just above the missing-when floor.

2 / 5

Trigger Term Quality

Contains technical jargon ('typespec', 'C# SDK repository root') and a parameter placeholder rather than natural phrases a user would say; missing common variations.

2 / 5

Distinctiveness Conflict Risk

The C#-SDK-from-typespec niche is quite specific with minimal overlap risk against unrelated skills, though it could conflict with a sibling non-C# codegen skill.

4 / 5

Total

11

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

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.