Sync .github/skills and eng/common from azure-sdk-tools PR #15210

Picks up new updates from Azure/azure-sdk-tools#15210 (azsdk-common skill rename and content updates).

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: Copilot

.github/skills/README.md

@@ -0,0 +1,83 @@
+# Azure SDK Shared Copilot Skills
+
+Copilot skills that guide AI agents through the Azure SDK development and TypeSpec-to-SDK release workflow.
+These skills are consumed by GitHub Copilot (CLI, VS Code, and Coding Agent) when users work
+with TypeSpec API specifications and Azure SDK generation.
+
+Shared skills (those distributed to other Azure SDK repositories) are identified by
+`distribution: shared` in their SKILL.md frontmatter metadata block and use the
+`azsdk-common-` directory prefix. This prefix enables the `sync-.github.yml` pipeline
+to match and distribute them to all subscribed language SDK repos.
+
+---
+
+## Available Skills
+
+### Workflow & Utility Skills
+
+| Skill | Triggers | Description |
+| ----- | -------- | ----------- |
+| [azsdk-common-generate-sdk-locally](azsdk-common-generate-sdk-locally/SKILL.md) | "generate SDK locally", "build SDK", "run SDK tests" | Generate, build, and test Azure SDKs locally from TypeSpec |
+| [azsdk-common-prepare-release-plan](azsdk-common-prepare-release-plan/SKILL.md) | "create release plan", "link SDK PR to plan" | Create and manage release plan work items |
+| [azsdk-common-apiview-feedback-resolution](azsdk-common-apiview-feedback-resolution/SKILL.md) | "APIView comments", "resolve API review feedback" | Retrieve and resolve APIView review feedback |
+| [azsdk-common-pipeline-troubleshooting](azsdk-common-pipeline-troubleshooting/SKILL.md) | "pipeline failed", "build failure", "CI check failing" | Diagnose and resolve SDK CI and generation pipeline failures |
+| [azsdk-common-sdk-release](azsdk-common-sdk-release/SKILL.md) | "release SDK", "trigger release pipeline" | Check release readiness and trigger SDK releases |
+
+### Development & Meta Skills
+
+These skills help with skill development itself:
+
+| Skill | Triggers | Description |
+| ----- | -------- | ----------- |
+| [sensei](sensei/SKILL.md) | "run sensei", "improve skill", "fix frontmatter" | Iteratively improve skill frontmatter compliance using the Ralph loop |
+| [skill-authoring](skill-authoring/SKILL.md) | "create a skill", "new skill", "skill template" | Guidelines for writing Agent Skills per agentskills.io spec |
+| [markdown-token-optimizer](markdown-token-optimizer/SKILL.md) | "optimize markdown", "reduce tokens", "token count" | Analyze markdown files for token efficiency |
+
+### Skill Anatomy
+
+Each skill lives in `<name>/` and contains:
+
+```
+<name>/
+├── SKILL.md           # Skill definition: YAML frontmatter + steps + related skills
+├── references/        # Detailed reference docs (offloaded to keep SKILL.md under 500 tokens)
+│   └── *.md
+├── eval.yaml          # Evaluation config (graders, timeouts, model)
+├── tasks/             # Eval task definitions (4-5 per skill)
+│   └── *.yaml
+└── fixtures/          # Domain-specific test fixtures
+    └── <files>
+```
+
+
+---
+
+## Tooling
+
+| Tool | Purpose | Install |
+| ---- | ------- | ------- |
+| [**waza**](https://microsoft.github.io/waza/getting-started/) | Scaffold skills, run evals, check compliance | `go install github.com/microsoft/waza/cmd/waza@latest` |
+
+### Testing Skills
+
+```bash
+cd .github/skills
+
+# Check all skills
+waza check
+
+# Run evals
+waza run --discover
+```
+
+---
+
+## Project Configuration
+
+- **`.waza.yaml`** — Default engine (`copilot-sdk`) and model (`claude-sonnet-4.6`) for evals
+- **`.gitignore`** — Excludes waza output directories and temp files
+
+## Further Reading
+
+- [agentskills.io spec](https://agentskills.io) — Skill frontmatter specification
+- [waza docs](https://microsoft.github.io/waza/getting-started/) — Scaffold, check, and eval skills

.github/skills/azsdk-common-apiview-feedback-resolution/SKILL.md

@@ -4,7 +4,7 @@ license: MIT
 metadata:
   version: "1.0.0"
   distribution: shared
-description: "Analyze and resolve APIView review feedback on Azure SDK PRs. **UTILITY SKILL**. USE FOR: APIView comments, API review feedback, SDK API surface changes. DO NOT USE FOR: general code review, non-APIView feedback. INVOKES: azure-sdk-mcp:azsdk_apiview_get_comments, azure-sdk-mcp:azsdk_typespec_customized_code_update."
+description: "Analyze and resolve APIView review feedback on Azure SDK PRs. **UTILITY SKILL**. USE FOR: APIView comments, API review feedback, SDK API surface changes. DO NOT USE FOR: general code review, non-APIView feedback. INVOKES: azure-sdk-mcp:azsdk_apiview_get_comments, azure-sdk-mcp:azsdk_customized_code_update."
 compatibility:
   requires: "azure-sdk-mcp server, SDK pull request with APIView review link"
 ---
@@ -18,7 +18,7 @@ compatibility:
 | Tool | Purpose |
 |------|---------|
 | `azure-sdk-mcp:azsdk_apiview_get_comments` | Get APIView comments |
-| `azure-sdk-mcp:azsdk_typespec_customized_code_update` | Apply TypeSpec changes locally |
+| `azure-sdk-mcp:azsdk_customized_code_update` | Apply TypeSpec & code customization changes locally |
 | `azure-sdk-mcp:azsdk_typespec_delegate_apiview_feedback` | Delegate to CCA pipeline |
 | `azure-sdk-mcp:azsdk_run_typespec_validation` | Validate TypeSpec |
 | `azure-sdk-mcp:azsdk_package_generate_code` | Regenerate SDK |
@@ -27,7 +27,7 @@ compatibility:
 
 1. **Retrieve** — Get APIView URL from SDK PR, run `azsdk_apiview_get_comments`.
 2. **Categorize** — Group as Critical/Suggestions/Informational per [feedback steps](references/feedback-resolution-steps.md).
-3. **Resolve** — Use `azsdk_typespec_customized_code_update` for TypeSpec changes; delegate via `azsdk_typespec_delegate_apiview_feedback` for complex cases.
+3. **Resolve** — Use `azsdk_customized_code_update` for TypeSpec changes; delegate via `azsdk_typespec_delegate_apiview_feedback` for complex cases.
 4. **Validate** — Run validation, regenerate SDK, build and test.
 5. **Confirm** — Verify all items addressed. If delegated, follow [post-delegation follow-up](references/feedback-resolution-steps.md#post-delegation-follow-up). Request re-review.
 

.github/skills/azsdk-common-apiview-feedback-resolution/evals/eval.yaml

@@ -18,12 +18,12 @@ metrics:
     threshold: 0.7
     description: Did the skill stay within behavior limits?
 graders:
-- type: text
-  name: no_fatal_errors
-  config:
-    regex_not_match:
-    - (?i)fatal error
-    - (?i)unhandled exception
-    - '(?i)panic:'
+  - type: text
+    name: no_fatal_errors
+    config:
+      regex_not_match:
+        - (?i)fatal error
+        - (?i)unhandled exception
+        - '(?i)panic:'
 tasks:
   - "tasks/*.yaml"

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

@@ -15,15 +15,15 @@ compatibility:
 
 | Tool | Purpose |
 |------|---------|
-| `azsdk_verify_setup` | Verify environment |
-| `azsdk_package_generate_code` | Generate SDK |
-| `azsdk_package_build_code` | Build package |
-| `azsdk_package_run_check` | Validate package |
-| `azsdk_package_run_tests` | Run tests |
-| `azsdk_customized_code_update` | Apply customizations (includes regeneration and build) |
-| `azsdk_package_update_changelog_content` | Update changelog |
-| `azsdk_package_update_metadata` | Update metadata including ci.yml |
-| `azsdk_package_update_version` | Update version |
+| `azure-sdk-mcp:azsdk_verify_setup` | Verify environment |
+| `azure-sdk-mcp:azsdk_package_generate_code` | Generate SDK |
+| `azure-sdk-mcp:azsdk_package_build_code` | Build package |
+| `azure-sdk-mcp:azsdk_package_run_check` | Validate package |
+| `azure-sdk-mcp:azsdk_package_run_tests` | Run tests |
+| `azure-sdk-mcp:azsdk_customized_code_update` | Apply customizations (includes regeneration and build) |
+| `azure-sdk-mcp:azsdk_package_update_changelog_content` | Update changelog |
+| `azure-sdk-mcp:azsdk_package_update_metadata` | Update metadata including ci.yml |
+| `azure-sdk-mcp:azsdk_package_update_version` | Update version |
 
 Prerequisites: azure-sdk-mcp server must be running. Without MCP, use `npx tsp-client` CLI.
 

.github/skills/azsdk-common-generate-sdk-locally/eval.yaml

@@ -22,8 +22,7 @@ graders:
     name: no_fatal_errors
     config:
       regex_not_match:
-        - (?i)error occurred
-        - (?i)failed
-        - (?i)re-run the tool
+        - (?i)fatal error
+        - (?i)unhandled exception
 tasks:
   - "tasks/*.yaml"

.github/skills/azsdk-common-pipeline-troubleshooting/evals/eval.yaml

@@ -18,12 +18,12 @@ metrics:
     threshold: 0.7
     description: Did the skill stay within behavior limits?
 graders:
-- type: text
-  name: no_fatal_errors
-  config:
-    regex_not_match:
-    - (?i)fatal error
-    - (?i)unhandled exception
-    - '(?i)panic:'
+  - type: text
+    name: no_fatal_errors
+    config:
+      regex_not_match:
+        - (?i)fatal error
+        - (?i)unhandled exception
+        - '(?i)panic:'
 tasks:
   - "tasks/*.yaml"

.github/skills/azsdk-common-prepare-release-plan/evals/eval.yaml

@@ -18,12 +18,12 @@ metrics:
     threshold: 0.7
     description: Did the skill stay within behavior limits?
 graders:
-- type: text
-  name: no_fatal_errors
-  config:
-    regex_not_match:
-    - (?i)fatal error
-    - (?i)unhandled exception
-    - '(?i)panic:'
+  - type: text
+    name: no_fatal_errors
+    config:
+      regex_not_match:
+        - (?i)fatal error
+        - (?i)unhandled exception
+        - '(?i)panic:'
 tasks:
   - "tasks/*.yaml"

.github/skills/azsdk-common-sdk-release/evals/eval.yaml

@@ -18,12 +18,12 @@ metrics:
     threshold: 0.7
     description: Did the skill stay within behavior limits?
 graders:
-- type: text
-  name: no_fatal_errors
-  config:
-    regex_not_match:
-    - (?i)fatal error
-    - (?i)unhandled exception
-    - '(?i)panic:'
+  - type: text
+    name: no_fatal_errors
+    config:
+      regex_not_match:
+        - (?i)fatal error
+        - (?i)unhandled exception
+        - '(?i)panic:'
 tasks:
   - "tasks/*.yaml"