Skia Analyst

What it does

When your agent uses it

• The user asks to write release notes
• Generate changelog
• What changed between versions
• What are we missing

Example prompts

• “write release notes”
• “generate changelog”
• “what changed between versions”
• “/skia-analyst”

Requirements

• Python 3

Workflow steps

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

1. 1Setup
2. 2Launch Independent Agents
3. 3Synthesize
4. 4Generate Outputs
5. 5Present Results

What it can do on your machine

Read from SKILL.md and the folder at commit cb51ed5. 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:

  • gh
  • python3

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

• Network

  No URLs in SKILL.md. Its commands use gh, 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

Skia Analyst loads about 1.6k tokens when it runs, and up to ~6.5k if it reads all its reference files. Until then it costs about 231 tokens; SKILL.md has 578 words of instructions outside code blocks.

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

~231

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

~1.6k

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

~6.5k

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 cb51ed5, republished under its MIT licence (© mono). 578 words, ~1,629 tokens.

name

skia-analyst

description

Analyze Skia features for SkiaSharp - produces a unified analysis of what shipped (upstream engine benefits, PR links, migration guides) and what's missing (impact/priority/effort scoring, hidden APIs). Given any combination of git refs, milestones, or no input at all, it scans upstream Skia release notes, diffs bindings, and checks C++ headers to produce a unified report. Use whenever the user asks to "write release notes", "generate changelog", "what changed between versions", "what are we missing", "feature gap analysis", "what should we bind next", "what's new in Skia", "scout features", "diff two tags", "what shipped in this release", "summarize changes since v3.x", "prepare release announcement", or any request to analyze SkiaSharp versions or Skia features. Also use proactively when the user mentions a Skia milestone bump, finishes a release cycle, or asks what went into a specific version.

Phase 1: Setup (determine scan range, prepare sources)
Phase 2: Launch independent GPT-5.6 Sol and Terra agents in parallel
Phase 3: Synthesize — merge findings, dedupe, both lenses
Phase 4: Generate outputs (JSON → validate → Markdown)
Phase 5: Present results

cat externals/skia/include/core/SkMilestone.h

gh api repos/google/skia/contents/RELEASE_NOTES.md -H "Accept: application/vnd.github.raw" > skia-release-notes.md

github-mcp-server-get_file_contents owner=google repo=skia path=include/core/SkImage.h

task agent_type=general-purpose mode=background model=gpt-5.6-sol name=analyst-sol:
task agent_type=general-purpose mode=background model=gpt-5.6-terra name=analyst-terra:

python3 .agents/skills/skia-analyst/scripts/validate-skia-analyst.py skia-analyst-report.json

python3 .agents/skills/skia-analyst/scripts/render-skia-analyst.py skia-analyst-report.json skia-analyst-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/skia-analyst of mono/SkiaSharp.

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

Open the folder on GitHubat commit cb51ed5