CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

azsdk-common-generate-sdk-locally

Generate, build, and test Azure SDKs locally from TypeSpec with automatic customization. WHEN: "generate SDK locally", "build SDK", "run SDK tests", "run CI checks", "validate package", "run checks", "update changelog", "fix SDK build errors", "fix breaking changes", "resolve SDK generation errors", "customize TypeSpec", "rename SDK client", "rename SDK model", "hide operation from SDK", "fix analyzer errors", "resolve customization drift", "create subclient", "update metadata", "update version". DO NOT USE FOR: publishing to package registries, CI pipeline configuration, API design review. INVOKES: azsdk_verify_setup, azsdk_package_generate_code, azsdk_package_build_code, azsdk_package_run_check, azsdk_package_run_tests, azsdk_customized_code_update, azsdk_package_update_changelog_content, azsdk_package_update_metadata, azsdk_package_update_version.

72

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

—

The risk profile of this skill

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A well-structured, actionable orchestration skill with an excellent sequenced workflow and explicit validation and error-recovery checkpoints. The main weaknesses are redundancy (Triggers duplicating the description, triple-stated MCP fallback, repeated retry guidance) and reference files that are cited but missing from the bundle.

Suggestions

Deduplicate the MCP-fallback instruction: it appears three times in inconsistent forms ("npm exec --prefix eng/common/tsp-client -- tsp-client" in Rules vs "npx tsp-client" in Prerequisites and Troubleshooting) — keep one canonical form in Rules and drop the other two.

Remove or shrink the body's Triggers section, which repeats the frontmatter WHEN/DO NOT USE FOR lists verbatim; the description already carries this for skill selection.

Ship the three referenced files (references/sdk-repos.md, references/detailed-workflow.md, references/customization-workflow.md) — none exist in the bundle — and add one example invocation with arguments for the non-MCP tsp-client CLI fallback.

DimensionReasoningScore

Conciseness

Mostly dense and useful, but the Triggers section repeats the frontmatter WHEN/DO-NOT-USE lists verbatim, the MCP fallback instruction appears three times in inconsistent forms ("npm exec --prefix eng/common/tsp-client -- tsp-client" in Rules vs "npx tsp-client" in Prerequisites and Troubleshooting), and the failure/retry guidance is duplicated between Guardrails and Troubleshooting.

4 / 5

Actionability

Steps name exact tool invocations ("Run azure-sdk-mcp:azsdk_package_generate_code with the config file path") and concrete config resolution (tspconfig.yaml vs tsp-location.yaml), but there are no example arguments for build/test/check tools and no example invocation of the non-MCP CLI fallback.

4 / 5

Workflow Clarity

Eleven clearly sequenced steps with an explicit build-failure branch into customization, validation steps (azsdk_package_run_check and azsdk_package_run_tests), commit checkpoints, and explicit error-recovery feedback loops ("If the tool fails or times out, report the error to the user and suggest retrying").

5 / 5

Progressive Disclosure

References are well signaled via markdown links ([SDK repo](references/sdk-repos.md), [config file details](references/detailed-workflow.md), [customization workflow](references/customization-workflow.md)) and one level deep, but none of the three referenced files exist in the bundle, so the content split cannot be verified and the links break as shipped.

4 / 5

Total

17

/

20

Passed

Description

100%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.

An exemplary description: third-person voice, concrete capabilities, explicit and extensive trigger phrases, and clear negative boundaries. The trailing INVOKES tool list adds length but consists of concrete, non-vague information and does not dilute the core what/when clarity.

DimensionReasoningScore

Specificity

"Generate, build, and test Azure SDKs locally from TypeSpec with automatic customization" names multiple concrete actions, and the trigger list extends coverage to fix, rename, hide, and metadata-update operations — comprehensive for this domain with no meaningful gaps.

5 / 5

Completeness

Explicitly answers what (first sentence), when (quoted concrete trigger phrases), and when-not ("DO NOT USE FOR: publishing to package registries, CI pipeline configuration, API design review"), matching the top anchor exactly.

5 / 5

Trigger Term Quality

The WHEN list covers natural phrases users would say — "generate SDK locally", "build SDK", "run SDK tests", "fix SDK build errors", "rename SDK client", "create subclient" — with extensive synonym and variation coverage.

5 / 5

Distinctiveness Conflict Risk

A clear niche (local Azure SDK generation from TypeSpec via azure-sdk-mcp) with distinct triggers, plus explicit DO NOT USE FOR boundaries that proactively disambiguate adjacent skills; minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 8 missing

Warning

referenced_paths_exist

Referenced path issues: 8 missing

Warning

Total

14

/

16

Passed

Repository

Azure/azure-sdk-for-net

Path

.github/skills/azsdk-common-generate-sdk-locally/SKILL.md

Revision

c609269

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill