skill-creator（技能创建器）

Skill Creator

Guide for creating skills that extend AI agent capabilities, with emphasis on Azure SDKs and Microsoft Foundry.

Required Context: When creating SDK or API skills, users MUST provide the SDK package name, documentation URL, or repository reference for the skill to be based on.

About Skills

Skills are modular knowledge packages that transform general-purpose agents into specialized experts:

1. Procedural knowledge — Multi-step workflows for specific domains
2. SDK expertise — API patterns, authentication, error handling for Azure services
3. Domain context — Schemas, business logic, company-specific patterns
4. Bundled resources — Scripts, references, templates for complex tasks

Core Principles

1. Concise is Key

The context window is a shared resource. Challenge each piece: "Does this justify its token cost?"

Default assumption: Agents are already capable. Only add what they don't already know.

2. Fresh Documentation First

Azure SDKs change constantly. Skills should instruct agents to verify documentation:

## Before Implementation

Search `microsoft-docs` MCP for current API patterns:

- Query: "[SDK name] [operation] python"
- Verify: Parameters match your installed SDK version

3. Degrees of Freedom

Match specificity to task fragility:

4. Progressive Disclosure

Skills load in three levels:

1. Metadata (~100 words) — Always in context
2. SKILL.md body (<5k words) — When skill triggers
3. References (unlimited) — As needed

Keep SKILL.md under 500 lines. Split into reference files when approaching this limit.

Skill Structure

skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter (name, description)
│   └── Markdown instructions
└── Bundled Resources (optional)
    ├── scripts/      — Executable code
    ├── references/   — Documentation loaded as needed
    └── assets/       — Output resources (templates, images)

SKILL.md

• Frontmatter: name and description. The description is the trigger mechanism.
• Body: Instructions loaded only after triggering.

Bundled Resources

Don't include: README.md, CHANGELOG.md, installation guides.

Creating Azure SDK Skills

When creating skills for Azure SDKs, follow these patterns consistently.

Skill Section Order

Follow this structure (based on existing Azure SDK skills):

1. Title — # SDK Name
2. Installation — pip install, npm install, etc.
3. Environment Variables — Required configuration, with an inline comment explaining when it's required. If using DefaultAzureCredentialin production,include AZURE_TOKEN_CREDENTIALS (set to prod or <specific_credential>)
4. Authentication — Use a specific Microsoft Entra Token credential like ManagedIdentityCredential or WorkloadIdentityCredential for production. DefaultAzureCredential is only recommended for local development. To use DefaultAzureCredential in production, set the environment variable AZURE_TOKEN_CREDENTIALS to prod or the specific target credential.
5. Core Workflow — Minimal viable example
6. Feature Tables — Clients, methods, tools
7. Best Practices — Numbered list
8. Reference Links — Table linking to /references/*.md

Authentication Pattern (All Languages)

For local development, use DefaultAzureCredential which supports multiple auth methods. For production, use a specific credential type or configure DefaultAzureCredential with environment variable AZURE_TOKEN_CREDENTIALS set to prod or specify the target credential.

# Python
from azure.identity import DefaultAzureCredential, ManagedIdentityCredential
# Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=<specific_credential>
credential = DefaultAzureCredential(require_envvar=True)
# Or use a specific credential directly in production:
# See https://learn.microsoft.com/python/api/overview/azure/identity-readme?view=azure-python#credential-classes
# credential = ManagedIdentityCredential()
client = ServiceClient(endpoint, credential)

// C#
var credential = new DefaultAzureCredential();
var client = new ServiceClient(new Uri(endpoint), credential);

// Java
TokenCredential credential = new DefaultAzureCredentialBuilder().build();
ServiceClient client = new ServiceClientBuilder()
    .endpoint(endpoint)
    .credential(credential)
    .buildClient();

// TypeScript
import {
  DefaultAzureCredential,
  ManagedIdentityCredential,
} from "@azure/identity";
// Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=<specific_credential>
const credential = new DefaultAzureCredential({
  requiredEnvVars: ["AZURE_TOKEN_CREDENTIALS"],
});
// Or use a specific credential directly in production:
// See https://learn.microsoft.com/javascript/api/overview/azure/identity-readme?view=azure-node-latest#credential-classes
// const credential = new ManagedIdentityCredential();
const client = new ServiceClient(endpoint, credential);

Never hardcode credentials. Use environment variables.

Standard Verb Patterns

Azure SDKs use consistent verbs across all languages:

Language-Specific Patterns

See references/azure-sdk-patterns.md for detailed patterns including:

• Python: ItemPaged, LROPoller, context managers, Sphinx docstrings
• .NET: Response<T>, Pageable<T>, Operation<T>, mocking support
• Java: Builder pattern, PagedIterable/PagedFlux, Reactor types
• TypeScript: PagedAsyncIterableIterator, AbortSignal, browser considerations

Handling Deprecated or Rebranded SDKs

When an Azure SDK has been deprecated or rebranded, update skills to guide users toward the current package while maintaining backward compatibility:

1. Add a migration notice at the top of the skill:

> **⚠️ MIGRATION NOTICE**: The [Old Service Name] has been rebranded to **[New Service Name]**. While the package `old-package-name` remains available for compatibility, **new projects should use `new-package-name`** which provides the latest features and updates.
>
> **For new projects**: Use the `new-package-name` package instead.
>
> **This skill remains valid** for existing projects using `old-package-name`, but be aware you're using the legacy package name. The API patterns shown here are compatible with both packages.

2. Show both installation options:

## Installation

### Legacy Package (Old Name)

\`\`\`xml
<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-old-package</artifactId>
    <version>4.2.0</version>
</dependency>
\`\`\`

### Recommended Package (New Name)

**For new projects, use the rebranded package:**

\`\`\`xml
<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-new-package</artifactId>
    <version>1.0.0</version>
</dependency>
\`\`\`

> **Note**: The API patterns in this skill apply to both packages. Replace package names and imports as needed when using `azure-new-package`.

3. When to create a new skill vs. update existing:

• Update existing skill if the API is largely compatible (same or similar class/method names)
• Create new skill + migration guide if the API changed significantly (use references/migration.md)
• Always cross-reference between old and new skills

Examples:

• azure-ai-formrecognizer-java → azure-ai-documentintelligence (rebranded service)
• azure-communication-callingserver-java → azure-communication-callautomation (deprecated, with migration guide)

Example: Azure SDK Skill Structure

---
name: skill-creator
description: |
  Azure AI Example SDK for Python. Use for [specific service features].
  Triggers: "example service", "create example", "list examples".
---

# Azure AI Example SDK

## Installation

\`\`\`bash
pip install azure-ai-example
\`\`\`

## Environment Variables

\`\`\`bash
AZURE_EXAMPLE_ENDPOINT=https://<resource>.example.azure.com
AZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production
\`\`\`

## Authentication

\`\`\`python
from azure.identity import DefaultAzureCredential, ManagedIdentityCredential
from azure.ai.example import ExampleClient

# Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=<specific_credential>
credential = DefaultAzureCredential(require_envvar=True)
# Or use a specific credential directly in production:
# See https://learn.microsoft.com/python/api/overview/azure/identity-readme?view=azure-python#credential-classes
# credential = ManagedIdentityCredential()
client = ExampleClient(
endpoint=os.environ["AZURE_EXAMPLE_ENDPOINT"],
credential=credential
)
\`\`\`

## Core Workflow

\`\`\`python

# Create

item = client.create_item(name="example", data={...})

# List (pagination handled automatically)

for item in client.list_items():
print(item.name)

# Long-running operation

poller = client.begin_process(item_id)
result = poller.result()

# Cleanup

client.delete_item(item_id)
\`\`\`

## Reference Files

| File                                               | Contents                 |
| -------------------------------------------------- | ------------------------ |
| [references/tools.md](references/tools.md)         | Tool integrations        |
| [references/streaming.md](references/streaming.md) | Event streaming patterns |

Skill Creation Process

1. Gather SDK Context — User provides SDK/API reference (REQUIRED)
2. Understand — Research SDK patterns from official docs
3. Plan — Identify reusable resources and product area category
4. Create — Write SKILL.md in .github/skills/<skill-name>/
5. Categorize — Create symlink in skills/<language>/<category>/
6. Test — Create acceptance criteria and test scenarios
7. Document — Update README.md skill catalog
8. Iterate — Refine based on real usage

Step 1: Gather SDK Context (REQUIRED)

Before creating any SDK skill, the user MUST provide:

Prompt the user if not provided:

To create this skill, I need:
1. The SDK package name (e.g., azure-ai-projects)
2. The Microsoft Learn documentation URL or GitHub repo
3. The target language (py/dotnet/ts/java)

Search official docs first:

# Use microsoft-docs MCP to get current API patterns
# Query: "[SDK name] [operation] [language]"
# Verify: Parameters match the latest SDK version

Step 2: Understand the Skill

Gather concrete examples:

• "What SDK operations should this skill cover?"
• "What triggers should activate this skill?"
• "What errors do developers commonly encounter?"

Step 3: Plan Product Area Category

Skills are organized by language and product area in the skills/ directory via symlinks.

Product Area Categories:

Determine the category based on:

1. Azure service family (Storage → data, Event Hubs → messaging)
2. Primary use case (AI agents → foundry)
3. Existing skills in the same service area

Step 4: Create the Skill

Location: .github/skills/<skill-name>/SKILL.md

Naming convention:

• azure-<service>-<subservice>-<language>
• Examples: azure-ai-agents-py, azure-cosmos-java, azure-storage-blob-ts

For Azure SDK skills:

1. Search microsoft-docs MCP for current API patterns
2. Verify against installed SDK version
3. Follow the section order above
4. Include cleanup code in examples
5. Add feature comparison tables

Write bundled resources first, then SKILL.md.

Frontmatter:

---
name: skill-name-py
description: |
  Azure Service SDK for Python. Use for [specific features].
  Triggers: "service name", "create resource", "specific operation".
---

Step 5: Categorize with Symlinks

After creating the skill in .github/skills/, create a symlink in the appropriate category:

# Pattern: skills/<language>/<category>/<short-name> -> ../../../.github/skills/<full-skill-name>

# Example for azure-ai-agents-py in python/foundry:
cd skills/python/foundry
ln -s ../../../.github/skills/azure-ai-agents-py agents

# Example for azure-cosmos-db-py in python/data:
cd skills/python/data
ln -s ../../../.github/skills/azure-cosmos-db-py cosmos-db

Symlink naming:

• Use short, descriptive names (e.g., agents, cosmos, blob)
• Remove the azure- prefix and language suffix
• Match existing patterns in the category

Verify the symlink:

ls -la skills/python/foundry/agents
# Should show: agents -> ../../../.github/skills/azure-ai-agents-py

Step 6: Create Tests

Every skill MUST have acceptance criteria and test scenarios.

6.1 Create Acceptance Criteria

Location: tests/scenarios/<skill-name>/acceptance-criteria.md

Source materials (in priority order):

1. Official Microsoft Learn docs (via microsoft-docs MCP)
2. SDK source code from the repository
3. Existing reference files in the skill

Format:

# Acceptance Criteria: <skill-name>

**SDK**: `package-name`
**Repository**: https://github.com/Azure/azure-sdk-for-<language>
**Purpose**: Skill testing acceptance criteria

---

## 1. Correct Import Patterns

### 1.1 Client Imports

#### ✅ CORRECT: Main Client

\`\`\`python
from azure.ai.mymodule import MyClient
from azure.identity import DefaultAzureCredential
\`\`\`

#### ❌ INCORRECT: Wrong Module Path

\`\`\`python
from azure.ai.mymodule.models import MyClient # Wrong - Client is not in models
\`\`\`

## 2. Authentication Patterns

#### ✅ CORRECT: DefaultAzureCredential

\`\`\`python
credential = DefaultAzureCredential()
client = MyClient(endpoint, credential)
\`\`\`

#### ❌ INCORRECT: Hardcoded Credentials

\`\`\`python
client = MyClient(endpoint, api_key="hardcoded") # Security risk
\`\`\`

Critical patterns to document:

• Import paths (these vary significantly between Azure SDKs)
• Authentication patterns
• Client initialization
• Async variants (.aio modules)
• Common anti-patterns

6.2 Create Test Scenarios

Location: tests/scenarios/<skill-name>/scenarios.yaml

config:
  model: gpt-4
  max_tokens: 2000
  temperature: 0.3

scenarios:
  - name: basic_client_creation
    prompt: |
      Create a basic example using the Azure SDK.
      Include proper authentication and client initialization.
    expected_patterns:
      - "DefaultAzureCredential"
      - "MyClient"
    forbidden_patterns:
      - "api_key="
      - "hardcoded"
    tags:
      - basic
      - authentication
    mock_response: |
      import os
      from azure.identity import DefaultAzureCredential
      from azure.ai.mymodule import MyClient

      credential = DefaultAzureCredential()
      client = MyClient(
          endpoint=os.environ["AZURE_ENDPOINT"],
          credential=credential
      )
      # ... rest of working example

Scenario design principles:

• Each scenario tests ONE specific pattern or feature
• expected_patterns — patterns that MUST appear
• forbidden_patterns — common mistakes that must NOT appear
• mock_response — complete, working code that passes all checks
• tags — for filtering (basic, async, streaming, tools)

6.3 Run Tests

cd tests
pnpm install

# Check skill is discovered
pnpm harness --list

# Run in mock mode (fast, deterministic)
pnpm harness <skill-name> --mock --verbose

# Run with Ralph Loop (iterative improvement)
pnpm harness <skill-name> --ralph --mock --max-iterations 5 --threshold 85

Success criteria:

• All scenarios pass (100% pass rate)
• No false positives (mock responses always pass)
• Patterns catch real mistakes

Step 7: Update Documentation

After creating the skill:

1. Update README.md — Add the skill to the appropriate language section in the Skill Catalog

- Update total skill count (line ~73: > N skills in...) - Update Skill Explorer link count (line ~15: Browse all N skills) - Update language count table (lines ~77-83) - Update language section count (e.g., > N skills • suffix: -py) - Update category count (e.g., <summary><strong>Foundry & AI</strong> (N skills)</summary>) - Add skill row in alphabetical order within its category - Update test coverage summary (line ~622: **N skills with N test scenarios**) - Update test coverage table — update skill count, scenario count, and top skills for the language

1. Regenerate GitHub Pages data — Run the extraction script to update the docs site cd docs-site && npx tsx scripts/extract-skills.ts This updates docs-site/src/data/skills.json which feeds the Astro-based docs site. Then rebuild the docs site: cd docs-site && npm run build This outputs to docs/ which is served by GitHub Pages.
2. Verify AGENTS.md — Ensure the skill count is accurate

Progressive Disclosure Patterns

Pattern 1: High-Level Guide with References

# SDK Name

## Quick Start

[Minimal example]

## Advanced Features

- **Streaming**: See [references/streaming.md](references/streaming.md)
- **Tools**: See [references/tools.md](references/tools.md)

Pattern 2: Language Variants

azure-service-skill/
├── SKILL.md (overview + language selection)
└── references/
    ├── python.md
    ├── dotnet.md
    ├── java.md
    └── typescript.md

Pattern 3: Feature Organization

azure-ai-agents/
├── SKILL.md (core workflow)
└── references/
    ├── tools.md
    ├── streaming.md
    ├── async-patterns.md
    └── error-handling.md

Design Pattern References

Anti-Patterns

Checklist

Before completing a skill:

Prerequisites:

• User provided SDK package name or documentation URL
• Verified SDK patterns via microsoft-docs MCP

Skill Creation:

• Description includes what AND when (trigger phrases)
• SKILL.md under 500 lines
• Authentication uses DefaultAzureCredential
• Includes cleanup/delete in examples
• References organized by feature

Categorization:

• Skill created in .github/skills/<skill-name>/
• Symlink created in skills/<language>/<category>/<short-name>
• Symlink points to ../../../.github/skills/<skill-name>

Testing:

• tests/scenarios/<skill-name>/acceptance-criteria.md created with correct/incorrect patterns
• tests/scenarios/<skill-name>/scenarios.yaml created
• All scenarios pass (pnpm harness <skill> --mock)
• Import paths documented precisely

Documentation:

• README.md skill catalog updated
• Instructs to search microsoft-docs MCP for current APIs