GoogleChrome
@GoogleChrome Organization
Public Skills
nightly-eval-investigation
by GoogleChrome
Downloads and analyzes the latest three distinct nightly evaluation runs (Claude Code, Codex CLI, and Jetski CLI) from the GCS remote dashboard to identify and flag unhealthy or low-performing tasks and guides. Use this skill whenever you need to run a bulk investigation on remote nightly runs, track agent health, or identify over-prescribed/brittle guides.
coherence-auditor
by GoogleChrome
Run a document coherence, link integrity, and git repository status audit across repository markdown files using a dedicated subagent. Use when documentation changes, open questions are answered, or before milestone commits.
modern-web-guidance
by GoogleChrome
Search tool for modern web development best practices. MANDATORY: Execute FIRST for all HTML/CSS and clientside JS tasks. Do NOT skip — web APIs evolve rapidly and training weights contain obsolete patterns. Trigger immediately for: modals/dialogs/popovers, tables, dark mode, anchor positioning, container queries, view transitions, scroll-driven animations, parallax/reveals, forms, validation, autofill, accessibility, custom selects, scrollbars, CWV (LCP, INP, CLS), content-visibility, fetch priority, image optimization, security, passkeys, HTML sanitization, web components, dates/timezones, built-in AI, WebAssembly, standard HTML/CSS/DOM in frameworks, etc. DO NOT trigger for: backend (SQL, ORMs, API routes), infra/scripts (CI/CD, Docker, Actions, Python/Go, Git), or tooling/trivial (Vite, tsconfig, ESLint, tests, copy/renames, 3P docs), etc.
investigating-eval-results
by GoogleChrome
Analyzes Guidance evaluation results to identify patterns and causes of low pass rates. Use when investigating low guided pass rates, checking trajectories, or debugging eval grader failures.
grader-replay
by GoogleChrome
Validates changes to graders, grading fixtures, and CSS/DOM/AST helpers by replaying saved agent solutions from historical eval suites and triaging before/after diffs. Use when modifying grader.ts, test-fixture.ts, run-grader.ts, or parser helpers used by graders. Don't use for debugging low guided pass rates in live evals (use eval-investigation), flagging nightly suites (nightly-eval-investigation), or validating gd dev prompt generation (dev-prompt-canary).
project-evals
by GoogleChrome
Best practices for creating and reviewing expectations.md, targets/<app>/task.md, and targets/<app>/grader.ts files to evaluate guidance quality. Use this skill any time you're writing or reviewing an expectations.md, task.md, or grader.ts file.
project-guides
by GoogleChrome
Best practices for authoring and reviewing guidance. Use this skill any time you're writing or reviewing guide.md, expectations.md, or demo.html files.
project-use-cases
by GoogleChrome
Best practices for creating use cases for a given feature. This is the first step in creating a new guide. Use this skill any time you're writing or reviewing a use case under the guides/ directory.
project-features
by GoogleChrome
Criteria and best practices for filing and triaging new-feature issues. Use this skill any time you file a new-feature issue, triage one, fix its web-feature ID, or decide whether a browser launch needs guidance at all.
dev-prompt-canary
by GoogleChrome
Empirically validates changes to gd dev authoring and grading prompts (src/authoring/dev-prompts.ts, src/authoring/dev.ts, src/grading/generate-grader.ts, src/grading/template.grader.ts) by running fast incremental task.md and grader.ts canary regenerations and a held-out 4th solution stress test in an isolated worktree. Use whenever modifying prompts or generation logic in the gd dev pipeline.
project-guide-validation
by GoogleChrome
Protocol for validating the technical accuracy, framework nuances, and evaluation readiness of web guidance. Use this skill when assigned to validate or review a guide, demo, or expectations file.
project-coding-standards
by GoogleChrome
Coding style, architectural conventions, and PR review standards for the modern-web-guidance-src (guidance) repository. Use when authoring new code, refactoring features, writing CLI tools, adding server endpoints, or preparing PRs for review.
project-maintenance
by GoogleChrome
"Routine maintenance notes: checking vendored deps, web-features/compat dataset updates, and doc coherence."
chrome-extensions
by GoogleChrome
Build and publish Chrome Extensions using Manifest V3 best practices. Use this skill whenever the user asks to create, modify, debug, or understand Chrome browser extensions, add-ons, or anything involving the Chrome Extensions API. Trigger on mentions of: 'Chrome extension', 'browser extension', 'manifest.json', 'content script', 'service worker' (in browser context), 'popup' (in browser extension context), 'side panel', 'chrome.* API', 'declarativeNetRequest', 'omnibox', 'context menu' (in extension context), 'userScripts', 'user script', 'script manager', or any request to build functionality that integrates with the Chrome browser UI. Also trigger for publishing to the Chrome Web Store: 'publish extension', preparing an extension for publishing, responding to a review rejection, writing permission justifications, or drafting a privacy policy.
project-discipline-guides
by GoogleChrome
Workflow for refactoring discipline-level guides (e.g., JavaScript, CSS) to remove "Common Knowledge" by generating and comparing against model-specific "Knowledge Mirrors".
baseline-status
by GoogleChrome
Use this skill to check the browser support and Baseline status of web features.