Sample Scout

What it does

When your agent uses it

• The user asks about what samples should we build
• What demos are we missing
• Find interesting Skia GMs
• Sample gap analysis

Example prompts

• “what samples should we build”
• “what demos are we missing”
• “find interesting Skia GMs”
• “/sample-scout”

Requirements

• Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Setup
2. 2Analyze GM Files
3. 3Cross-Reference with Existing Gallery Samples
4. 4Validate and Render
5. 5Present Results

What it can do on your machine

Read from SKILL.md and the folder at commit a74f7f9. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 3 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python3
  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sample Scout loads about 1.5k tokens when it runs, and up to ~4.2k if it reads all its reference files. Until then it costs about 218 tokens; SKILL.md has 490 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~218

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~4.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from mono/SkiaSharp at commit a74f7f9, republished under its MIT licence (© mono). 490 words, ~1,535 tokens.

name

sample-scout

description

Scout Skia GM (golden master) samples in the externals/skia submodule to find demos worth porting to the SkiaSharp Gallery. Reads .cpp files directly from the checked-out submodule, analyzes what each 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.

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

git submodule update --init --depth=1 externals/skia

ls externals/skia/gm/*.cpp | xargs -n1 basename | sort > gm-files.txt
wc -l < gm-files.txt

find samples/Gallery -name "*.cs" -path "*/Samples/*" | sort

Analyze Skia GM sample files. For EACH file, read it from externals/skia/gm/FILENAME
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.

python3 .agents/skills/sample-scout/scripts/validate-sample-scout.py sample-scout-report.json

python3 .agents/skills/sample-scout/scripts/render-sample-scout.py sample-scout-report.json sample-scout-report.md

© mono, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (scripts, references) in .agents/skills/sample-scout of mono/SkiaSharp.

• SKILL.md
• evals/evals.json
• references/analysis-instructions.md
• references/sample-scout-schema.json
• references/schema-cheatsheet.md
• scripts/render-sample-scout.py
• scripts/requirements.txt
• scripts/validate-sample-scout.py

Open the folder on GitHubat commit a74f7f9