CtrlK
BlogDocsLog inGet started
Tessl Logo

azure-hosted-copilot-sdk

Build, deploy, and modify GitHub Copilot SDK apps on Azure. MANDATORY when codebase contains @github/copilot-sdk or CopilotClient in package.json. PREFER OVER azure-prepare when copilot-sdk markers detected. WHEN: copilot SDK, @github/copilot-sdk, copilot-powered app, build copilot app, prepare copilot app, add feature to copilot app, modify copilot app, BYOM, bring your own model, CopilotClient, createSession, sendAndWait, azd init copilot. DO NOT USE FOR: deploying already-prepared copilot-sdk apps (use azure-deploy), general web apps without copilot SDK (use azure-prepare), Copilot Extensions, Foundry agents (use microsoft-foundry).

68

Quality

81%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

This skill provides a well-structured orchestration workflow with clear routing logic and sequenced steps, but it leans heavily on reference files for actual implementation details while spending significant tokens on detection/routing meta-instructions. The detection section is overly verbose with repeated warnings, while the actionable steps (2B, 2C, 3) are too thin without the referenced files. The skill works well as a routing hub but would benefit from more inline executable content and less repetitive emphasis on detection priority.

Suggestions

Condense the detection section: merge the two warning callouts and the 'generic prompts' table into a single concise block — the marker table alone is sufficient for Claude to understand detection logic.

Add a minimal executable BYOM code snippet inline (even 3-4 lines showing DefaultAzureCredential + bearerToken pattern) rather than deferring entirely to auth-best-practices.md, since this is called out as MANDATORY.

Include at least a brief inline summary of what Steps 2B and 2C entail (e.g., key files to copy, azure.yaml structure) so the skill is useful even if reference files are unavailable.

DimensionReasoningScore

Conciseness

The detection procedure section is quite verbose with repeated warnings and tables that could be condensed. The routing table and model config are efficient, but the 'MANDATORY FIRST CHECK' section with multiple warning callouts and the 'generic prompts' table explain routing logic that is more meta-instruction than actionable skill content.

2 / 3

Actionability

Provides concrete commands like `azd init --template azure-samples/copilot-sdk-service` and clear routing tables, but most steps defer to reference files for actual implementation details. The scaffold step is actionable, but Steps 2B, 2C, and 3 are mostly pointers rather than executable guidance. BYOM auth mentions the pattern but doesn't include the actual code.

2 / 3

Workflow Clarity

The workflow is clearly sequenced: detect → route → scaffold → configure model → deploy. The routing table in Step 1 provides unambiguous decision logic. Step 4 explicitly sequences sub-skills (azure-prepare → azure-validate → azure-deploy). The yield-to-azure-deploy condition provides a clear validation checkpoint for routing decisions.

3 / 3

Progressive Disclosure

References to supporting files (references/copilot-sdk.md, references/deploy-existing.md, references/azure-model-config.md, references/auth-best-practices.md, references/existing-project-integration.md) are well-signaled and one level deep. However, no bundle files were provided, so we cannot verify these references exist. The main file also includes substantial detection/routing content that could arguably be separated, and the inline content for Steps 2B/2C is too thin — they're essentially just pointers.

2 / 3

Total

9

/

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.

This is an excellent skill description that covers all dimensions thoroughly. It provides specific actions, comprehensive trigger terms, explicit when/when-not guidance, and proactively addresses potential conflicts with related skills. The inclusion of MANDATORY conditions, PREFER OVER directives, and DO NOT USE FOR exclusions makes this highly effective for skill selection in a large skill library.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'Build, deploy, and modify GitHub Copilot SDK apps on Azure.' Also specifies concrete markers like '@github/copilot-sdk', 'CopilotClient', 'createSession', 'sendAndWait', and 'azd init copilot'.

3 / 3

Completeness

Clearly answers both 'what' (build, deploy, modify GitHub Copilot SDK apps on Azure) and 'when' (explicit WHEN clause with trigger terms, MANDATORY conditions, and a DO NOT USE FOR section that clarifies boundaries). The explicit trigger guidance is thorough.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms users would say, including package names ('@github/copilot-sdk', 'CopilotClient'), action phrases ('build copilot app', 'modify copilot app'), acronyms ('BYOM', 'bring your own model'), and specific API calls ('createSession', 'sendAndWait', 'azd init copilot').

3 / 3

Distinctiveness Conflict Risk

Exceptionally distinctive with explicit conflict resolution: specifies when to prefer this over 'azure-prepare', when to use 'azure-deploy' instead, and explicitly excludes Copilot Extensions and Foundry agents. The DO NOT USE FOR section directly addresses potential overlaps.

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
microsoft/github-copilot-for-azure
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.