Add skia-analyst and sample-scout skills with daily/weekly workflows

.github/agents/agentic-workflows.agent.md → .agents/agents/agentic-workflows.agent.md

@@ -30,7 +30,7 @@ Workflows may optionally include:
 - Workflow files: `.github/workflows/*.md` and `.github/workflows/**/*.md`
 - Workflow lock files: `.github/workflows/*.lock.yml`
 - Shared components: `.github/workflows/shared/*.md`
-- Configuration: https://github.com/github/gh-aw/blob/v0.68.3/.github/aw/github-agentic-workflows.md
+- Configuration: https://github.com/github/gh-aw/blob/v0.71.1/.github/aw/github-agentic-workflows.md
 
 ## Problems This Solves
 
@@ -52,7 +52,7 @@ When you interact with this agent, it will:
 ### Create New Workflow
 **Load when**: User wants to create a new workflow from scratch, add automation, or design a workflow that doesn't exist yet
 
-**Prompt file**: https://github.com/github/gh-aw/blob/v0.68.3/.github/aw/create-agentic-workflow.md
+**Prompt file**: https://github.com/github/gh-aw/blob/v0.71.1/.github/aw/create-agentic-workflow.md
 
 **Use cases**:
 - "Create a workflow that triages issues"
@@ -62,7 +62,7 @@ When you interact with this agent, it will:
 ### Update Existing Workflow  
 **Load when**: User wants to modify, improve, or refactor an existing workflow
 
-**Prompt file**: https://github.com/github/gh-aw/blob/v0.68.3/.github/aw/update-agentic-workflow.md
+**Prompt file**: https://github.com/github/gh-aw/blob/v0.71.1/.github/aw/update-agentic-workflow.md
 
 **Use cases**:
 - "Add web-fetch tool to the issue-classifier workflow"
@@ -72,7 +72,7 @@ When you interact with this agent, it will:
 ### Debug Workflow  
 **Load when**: User needs to investigate, audit, debug, or understand a workflow, troubleshoot issues, analyze logs, or fix errors
 
-**Prompt file**: https://github.com/github/gh-aw/blob/v0.68.3/.github/aw/debug-agentic-workflow.md
+**Prompt file**: https://github.com/github/gh-aw/blob/v0.71.1/.github/aw/debug-agentic-workflow.md
 
 **Use cases**:
 - "Why is this workflow failing?"
@@ -82,7 +82,7 @@ When you interact with this agent, it will:
 ### Upgrade Agentic Workflows
 **Load when**: User wants to upgrade workflows to a new gh-aw version or fix deprecations
 
-**Prompt file**: https://github.com/github/gh-aw/blob/v0.68.3/.github/aw/upgrade-agentic-workflows.md
+**Prompt file**: https://github.com/github/gh-aw/blob/v0.71.1/.github/aw/upgrade-agentic-workflows.md
 
 **Use cases**:
 - "Upgrade all workflows to the latest version"
@@ -92,7 +92,7 @@ When you interact with this agent, it will:
 ### Create a Report-Generating Workflow
 **Load when**: The workflow being created or updated produces reports — recurring status updates, audit summaries, analyses, or any structured output posted as a GitHub issue, discussion, or comment
 
-**Prompt file**: https://github.com/github/gh-aw/blob/v0.68.3/.github/aw/report.md
+**Prompt file**: https://github.com/github/gh-aw/blob/v0.71.1/.github/aw/report.md
 
 **Use cases**:
 - "Create a weekly CI health report"
@@ -102,7 +102,7 @@ When you interact with this agent, it will:
 ### Create Shared Agentic Workflow
 **Load when**: User wants to create a reusable workflow component or wrap an MCP server
 
-**Prompt file**: https://github.com/github/gh-aw/blob/v0.68.3/.github/aw/create-shared-agentic-workflow.md
+**Prompt file**: https://github.com/github/gh-aw/blob/v0.71.1/.github/aw/create-shared-agentic-workflow.md
 
 **Use cases**:
 - "Create a shared component for Notion integration"
@@ -112,7 +112,7 @@ When you interact with this agent, it will:
 ### Fix Dependabot PRs
 **Load when**: User needs to close or fix open Dependabot PRs that update dependencies in generated manifest files (`.github/workflows/package.json`, `.github/workflows/requirements.txt`, `.github/workflows/go.mod`)
 
-**Prompt file**: https://github.com/github/gh-aw/blob/v0.68.3/.github/aw/dependabot.md
+**Prompt file**: https://github.com/github/gh-aw/blob/v0.71.1/.github/aw/dependabot.md
 
 **Use cases**:
 - "Fix the open Dependabot PRs for npm dependencies"
@@ -122,7 +122,7 @@ When you interact with this agent, it will:
 ### Analyze Test Coverage
 **Load when**: The workflow reads, analyzes, or reports test coverage — whether triggered by a PR, a schedule, or a slash command. Always consult this prompt before designing the coverage data strategy.
 
-**Prompt file**: https://github.com/github/gh-aw/blob/v0.68.3/.github/aw/test-coverage.md
+**Prompt file**: https://github.com/github/gh-aw/blob/v0.71.1/.github/aw/test-coverage.md
 
 **Use cases**:
 - "Create a workflow that comments coverage on PRs"
@@ -169,10 +169,10 @@ gh aw compile --validate
 
 ## Important Notes
 
-- Always reference the instructions file at https://github.com/github/gh-aw/blob/v0.68.3/.github/aw/github-agentic-workflows.md for complete documentation
+- Always reference the instructions file at https://github.com/github/gh-aw/blob/v0.71.1/.github/aw/github-agentic-workflows.md for complete documentation
 - Use the MCP tool `agentic-workflows` when running in GitHub Copilot Cloud
 - Workflows must be compiled to `.lock.yml` files before running in GitHub Actions
 - **Bash tools are enabled by default** - Don't restrict bash commands unnecessarily since workflows are sandboxed by the AWF
 - Follow security best practices: minimal permissions, explicit network access, no template injection
-- **Network configuration**: Use ecosystem identifiers (`node`, `python`, `go`, etc.) or explicit FQDNs in `network.allowed`. Bare shorthands like `npm` or `pypi` are **not** valid. See https://github.com/github/gh-aw/blob/v0.68.3/.github/aw/network.md for the full list of valid ecosystem identifiers and domain patterns.
+- **Network configuration**: Use ecosystem identifiers (`node`, `python`, `go`, etc.) or explicit FQDNs in `network.allowed`. Bare shorthands like `npm` or `pypi` are **not** valid. See https://github.com/github/gh-aw/blob/v0.71.1/.github/aw/network.md for the full list of valid ecosystem identifiers and domain patterns.
 - **Single-file output**: When creating a workflow, produce exactly **one** workflow `.md` file. Do not create separate documentation files (architecture docs, runbooks, usage guides, etc.). If documentation is needed, add a brief `## Usage` section inside the workflow file itself.

.agents/skills/sample-scout/SKILL.md

@@ -0,0 +1,157 @@
+---
+name: sample-scout
+description: >
+  Scout Google's upstream Skia GM (golden master) samples to find demos worth porting to the
+  SkiaSharp Gallery. Fetches the full gm/ directory listing from google/skia on GitHub, analyzes
+  each .cpp file to understand what it demonstrates, checks whether the required APIs exist in
+  SkiaSharp, and cross-references against existing Gallery samples to identify gaps. Produces a
+  structured JSON report and a GitHub-flavored Markdown report for filtering by interest level, API
+  availability, and sample coverage status. Use this skill whenever the user asks about "what
+  samples should we build", "what demos are we missing", "find interesting Skia GMs", "sample gap
+  analysis", "what can we port from Skia", "gallery ideas", "scout GM samples", or any request to
+  discover demo opportunities from upstream Skia. Also use proactively after adding new APIs to
+  find samples that showcase them.
+---
+
+# Sample Scout
+
+You analyze Google's upstream Skia GM (golden master) sample files to discover demos worth porting
+to the SkiaSharp Gallery. The goal is to find visually impressive, educationally valuable samples
+that showcase SkiaSharp's capabilities — and identify which ones we can build today vs. which need
+new APIs first.
+
+## Why This Matters
+
+Skia has 400+ GM samples that exercise every API and visual technique. These are a goldmine for
+the SkiaSharp Gallery — each one is a proven, tested visual that demonstrates something users would
+want to learn. But nobody can manually review 400+ C++ files to find the gems. This skill automates
+the discovery.
+
+## Key References
+
+- **[references/analysis-instructions.md](references/analysis-instructions.md)** — How to classify samples
+- **[references/sample-scout-schema.json](references/sample-scout-schema.json)** — JSON Schema for validation
+- **[references/schema-cheatsheet.md](references/schema-cheatsheet.md)** — Human-readable schema docs
+
+## Workflow
+
+```
+Phase 1: Setup (list GM files, list existing Gallery samples)
+Phase 2: Analyze GM files (parallel agents, each handles a chunk)
+Phase 3: Cross-reference with existing Gallery samples
+Phase 4: Validate and render
+Phase 5: Present results
+```
+
+### Phase 1: Setup
+
+**1a. List all GM files from upstream**
+
+Use the GitHub API to get the complete file listing from `google/skia/gm/`:
+
+```bash
+gh api repos/google/skia/contents/gm --jq '.[].name' | grep '\.cpp$' | sort > gm-files.txt
+wc -l < gm-files.txt
+```
+
+IMPORTANT: Always use upstream `google/skia`, not our fork `mono/skia`. The fork may be behind.
+
+**1b. List existing Gallery samples**
+
+```bash
+find samples/Gallery -name "*.cs" -path "*/Samples/*" | sort
+```
+
+For each sample, extract the `Title`, `Description`, and `Category` to build a coverage map.
+
+**1c. Split into chunks for parallel processing**
+
+With 400+ files, split into 5 chunks of ~80-90 files each for parallel analysis.
+
+### Phase 2: Analyze GM Files
+
+Launch **5 parallel background agents** (general-purpose), each analyzing one chunk. Each agent:
+
+1. For each `.cpp` file in its chunk, fetch from GitHub:
+   ```
+   github-mcp-server-get_file_contents owner=google repo=skia path=gm/{filename}
+   ```
+
+2. Read the file and extract:
+   - **What it demonstrates** (1-2 sentences)
+   - **Key Skia APIs used** (class::method names)
+   - **Interest level**: high / medium / low
+   - **API availability**: check if the required APIs exist in SkiaSharp by grepping `binding/SkiaSharp/`
+   - **Missing APIs**: list any APIs not available in SkiaSharp
+   - **Notes**: GPU-only, Graphite-specific, bug regression, etc.
+
+3. Save findings as JSON array to a temp file.
+
+See [references/analysis-instructions.md](references/analysis-instructions.md) for the classification
+criteria and decision guidelines.
+
+**Agent prompt template:**
+```
+Analyze Skia GM sample files from google/skia. For EACH file, fetch it using
+github-mcp-server-get_file_contents (owner=google, repo=skia, path=gm/FILENAME),
+read it, and produce a JSON entry.
+
+Files: {comma-separated list}
+
+Read .agents/skills/sample-scout/references/analysis-instructions.md for classification criteria.
+
+For each file output: file, name, description, interesting (high/medium/low),
+apis_available (true/false), missing_apis [], key_apis [], notes,
+visualGoal (what the rendered output looks like), suggestedControls [],
+category (Gallery category), skiaSharpApis [] (C# equivalents).
+
+Check API availability by grepping binding/SkiaSharp/ for the C# equivalents.
+Save as JSON array to {output_path}.
+Must produce exactly {N} entries — count at the end to confirm.
+```
+
+### Phase 3: Cross-Reference with Existing Gallery Samples
+
+After all agents complete, merge their findings and cross-reference against existing Gallery samples:
+
+For each GM entry, check if an existing Gallery sample covers the same topic:
+- **`existing`** — A Gallery sample directly covers this GM's main feature
+- **`similar`** — A Gallery sample covers a related topic (e.g., gradient GM → Gradient sample exists)
+- **`none`** — No Gallery sample covers this
+
+Tag each finding with `sampleStatus` and `matchedSample`.
+
+Save the merged findings as `sample-scout-report.json` in the working directory.
+
+### Phase 4: Validate and Render
+
+**4a. Validate**
+
+```bash
+python3 .agents/skills/sample-scout/scripts/validate-sample-scout.py sample-scout-report.json
+```
+
+**4b. Render Markdown**
+
+```bash
+python3 .agents/skills/sample-scout/scripts/render-sample-scout.py sample-scout-report.json sample-scout-report.md
+```
+
+This produces a `.md` file with `###`/`####` headers suitable for GitHub issues.
+
+### Phase 5: Present Results
+
+Show the summary with these key metrics:
+- Total samples analyzed
+- 🆕 No existing sample (opportunities)
+- 🔶 Similar sample exists (enhancement opportunities)
+- ✅ Already covered
+- 🎯 **Opportunity count** = high interest + APIs ready + no existing sample
+
+Then present the top opportunities — samples that are high-interest, have all APIs available,
+and have no existing Gallery coverage. These are the ones to build next.
+
+Offer:
+1. "Want me to build Gallery samples for the top opportunities?"
+2. "Should I focus on samples that need new APIs first?"
+3. "Want to filter by a specific category (shaders, image filters, text, etc.)?"

.agents/skills/sample-scout/evals/evals.json

@@ -0,0 +1,35 @@
+{
+  "skill_name": "sample-scout",
+  "evals": [
+    {
+      "id": 1,
+      "prompt": "Scout the upstream Skia GM samples and find interesting demos we should port to the SkiaSharp Gallery. Do a full scan.",
+      "expected_output": "Full scan of 400+ GM files from google/skia/gm/. Should categorize each by interest level, check API availability, and cross-reference with existing Gallery samples. Should identify top opportunities.",
+      "files": [],
+      "expectations": [
+        "Produces a JSON file that passes validate-sample-scout.py with exit code 0",
+        "Produces a Markdown report via render-sample-scout.py",
+        "JSON meta.source is 'google/skia/gm/'",
+        "JSON findings array has at least 300 entries",
+        "JSON summary.totalFindings equals actual findings count",
+        "At least 50 findings have interesting='high'",
+        "At least one finding references mesh.cpp with apis_available=false",
+        "At least one finding references runtimeshader.cpp with apis_available=true",
+        "sampleStatus field is present on findings",
+        "summary.opportunities count matches actual high+available+none count"
+      ]
+    },
+    {
+      "id": 2,
+      "prompt": "What Skia GM samples can we build today with existing SkiaSharp APIs? I want to find demos we're missing.",
+      "expected_output": "Should filter to samples where apis_available=true and sampleStatus='none'. Focus on the actionable opportunities.",
+      "files": [],
+      "expectations": [
+        "Produces a valid JSON report",
+        "Identifies samples with sampleStatus 'none' that have apis_available true",
+        "Presents a focused list of buildable opportunities",
+        "Each opportunity has a clear description of what it demonstrates"
+      ]
+    }
+  ]
+}

.agents/skills/sample-scout/references/analysis-instructions.md

@@ -0,0 +1,93 @@
+# Sample Scout — Analysis Instructions
+
+Read this file before analyzing any GM samples. It contains the classification criteria,
+interest level guidelines, and API availability checking methodology.
+
+## Classification Criteria
+
+### Interest Level
+
+| Level | Criteria | Examples |
+|-------|----------|---------|
+| **high** | Visually impressive, demonstrates a useful technique, showcases a powerful API that users would want to learn. Would make a great Gallery demo. | Runtime shaders, shadow utils, path effects showcase, gradient interpolation, mesh drawing, image filter chains, text effects |
+| **medium** | Educational or useful reference but not visually exciting on its own. Could be combined with other samples. | Bitmap copy, color matrix, simple clip operations, tile modes, basic shapes |
+| **low** | Internal test, bug regression, GPU-backend-specific test, stress test, or not relevant to SkiaSharp users. | crbug_* files, skbug_* files, Graphite-only tests, GrFragmentProcessor tests, Vulkan/Dawn internals, benchmark GMs |
+
+### Quick Classification Rules
+
+- Files starting with `crbug_` or `skbug` → **low** (bug regression tests)
+- Files mentioning `Graphite`, `Dawn`, `GrFragmentProcessor`, `GrGeometryProcessor` → **low** (GPU internals)
+- Files testing a single specific visual feature with nice output → **high**
+- Files testing edge cases of an already-covered feature → **medium**
+- Files showing off compositing, effects chains, or creative techniques → **high**
+
+### API Availability Check
+
+For each key Skia API used in a GM sample, check if SkiaSharp has a C# equivalent:
+
+| Skia C++ | SkiaSharp C# | Where to check |
+|----------|-------------|----------------|
+| `SkCanvas::drawRect` | `SKCanvas.DrawRect` | `binding/SkiaSharp/SKCanvas.cs` |
+| `SkPaint` properties | `SKPaint` properties | `binding/SkiaSharp/SKPaint.cs` |
+| `SkShader` factories | `SKShader.Create*` | `binding/SkiaSharp/SKShader.cs` |
+| `SkImageFilter` factories | `SKImageFilter.Create*` | `binding/SkiaSharp/SKImageFilter.cs` |
+| `SkPathEffect` factories | `SKPathEffect.Create*` | `binding/SkiaSharp/SKPathEffect.cs` |
+| `SkColorFilter` factories | `SKColorFilter.Create*` | `binding/SkiaSharp/SKColorFilter.cs` |
+| `SkRuntimeEffect` | `SKRuntimeEffect` | `binding/SkiaSharp/SKRuntimeEffect.cs` |
+| `SkMesh` | ❌ Not available | — |
+| `SkShadowUtils` | ❌ Not available | — |
+| `SkImageFilters::RuntimeShader` | ❌ Not available | — |
+| `SkColorFilters::HSLAMatrix` | ❌ Not available | — |
+| GPU-specific (GrDirectContext, GrBackendTexture) | ❌ Not relevant | Internal GPU plumbing |
+| `experimental_DrawEdgeAAQuad` | ❌ Not available | Experimental API |
+
+To verify, grep the binding directory:
+```bash
+grep -ril "MethodName\|method_name" binding/SkiaSharp/
+```
+
+### What Makes a Good Gallery Sample
+
+A good SkiaSharp Gallery sample:
+1. **Looks impressive** — visual output that makes people say "wow, SkiaSharp can do that?"
+2. **Teaches something** — demonstrates an API or technique users would want to learn
+3. **Is self-contained** — doesn't need external resources (or uses bundled assets)
+4. **Has controls** — interactive parameters users can tweak to understand the API
+5. **Works on all platforms** — no GPU-specific or platform-specific requirements
+
+### Notes Field
+
+Use the notes field to capture important context:
+- "GPU-only" — requires GPU backend, won't work on CPU raster
+- "Graphite-specific" — only relevant to Graphite backend (not SkiaSharp)
+- "Bug regression test" — tests a specific fixed bug, not a feature demo
+- "Stress test" — performance/edge case test, not visual
+- "Requires test fonts" — needs specific font files
+- "Animated" — has frame-based animation
+- "Combines well with X" — could be merged with another GM for a richer sample
+
+## Output Schema
+
+Each finding must have these fields:
+
+```json
+{
+  "file": "mesh.cpp",
+  "name": "Custom Vertex Mesh Drawing",
+  "description": "Draws custom vertex meshes with SkSL vertex/fragment programs and per-vertex attributes.",
+  "interesting": "high",
+  "apis_available": false,
+  "missing_apis": ["SkMesh", "SkMeshSpecification", "SkCanvas::drawMesh"],
+  "key_apis": ["SkMesh::Make", "SkMeshSpecification::Make", "SkCanvas::drawMesh"],
+  "notes": "Requires SkMesh API which is not yet exposed in SkiaSharp",
+  "visualGoal": "A colorful warped grid of triangles with per-vertex colors, demonstrating programmable vertex displacement and custom fragment shading.",
+  "suggestedControls": ["Grid density slider (4–32)", "Warp amplitude slider (0–50)", "Color mode toggle (rainbow/grayscale)"],
+  "category": "Shaders",
+  "skiaSharpApis": ["SKCanvas.DrawVertices", "SKRuntimeEffect", "SKVertices"]
+}
+```
+
+### Required fields
+`file`, `name`, `description`, `interesting`, `apis_available`, `missing_apis`, `key_apis`, `visualGoal`, `suggestedControls`, `category`, `skiaSharpApis`
+
+All fields are required on every finding. `missing_apis` and `suggestedControls` should be empty arrays `[]` when not applicable.