Install the "project-coding-standards" agent skill from https://github.com/GoogleChrome/modern-web-guidance-src/tree/main/.agents/skills/project-coding-standards into .claude/skills/project-coding-standards/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-coding-standards", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add GoogleChrome/modern-web-guidance-src --skill project-coding-standards -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "project-coding-standards" agent skill from https://github.com/GoogleChrome/modern-web-guidance-src/tree/main/.agents/skills/project-coding-standards into .agents/skills/project-coding-standards/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-coding-standards", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add GoogleChrome/modern-web-guidance-src --skill project-coding-standards -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "project-coding-standards" agent skill from https://github.com/GoogleChrome/modern-web-guidance-src/tree/main/.agents/skills/project-coding-standards into .cursor/skills/project-coding-standards/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-coding-standards", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add GoogleChrome/modern-web-guidance-src --skill project-coding-standards -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "project-coding-standards" agent skill from https://github.com/GoogleChrome/modern-web-guidance-src/tree/main/.agents/skills/project-coding-standards into .gemini/skills/project-coding-standards/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-coding-standards", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add GoogleChrome/modern-web-guidance-src --skill project-coding-standards -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "project-coding-standards" agent skill from https://github.com/GoogleChrome/modern-web-guidance-src/tree/main/.agents/skills/project-coding-standards into .github/skills/project-coding-standards/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-coding-standards", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add GoogleChrome/modern-web-guidance-src --skill project-coding-standards -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "project-coding-standards" agent skill from https://github.com/GoogleChrome/modern-web-guidance-src/tree/main/.agents/skills/project-coding-standards into .opencode/skills/project-coding-standards/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "project-coding-standards", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
project-coding-standards
GitHub stars
1.1k
Token cost
~2k tokens
SKILL.md length
909 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
Apache-2.0
At a glance
Coding style, architectural conventions, and PR review standards for the modern-web-guidance-src (guidance) repository.
Works in 3 steps: Data layer / core libraries (parsing,… → CLI workflows and execution commands → UI / visualization components and…
Authoring new code
SKILL.md covers Overview, PR Scope and Modularity, Architectural Principles and File, Git, & Config Integrity, plus 3 more sections
Calls pnpm and git
What it does
Project Coding Standards is an agent skill from GoogleChrome/modern-web-guidance-src. 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.
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Code quality, Pull requests and Refactoring. The licence is Apache-2.0.
When your agent uses it
Authoring new code
Refactoring features
Writing CLI tools
Adding server endpoints
Example prompts
“/project-coding-standards”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
3UI / visualization components and dashboard views
What it can do on your machine
Read from SKILL.md and the folder at commit c312847. 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
Shell commands in SKILL.md call:
pnpm
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pnpm and 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
Project Coding Standards loads about 2k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 909 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~67
When it runs· the whole SKILL.md, loaded when a task matches
~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
Auto-check passed
The automated check found no risky patterns in SKILL.md.
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); files beside SKILL.md are not scanned.
Download SKILL.mdSave it as .claude/skills/project-coding-standards/SKILL.md (or your agent's skills folder).
name
project-coding-standards
description
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.
This skill defines the architectural principles, coding conventions, and PR review standards for the modern-web-guidance-src repository.
Follow these guidelines whenever authoring TypeScript, JavaScript, CLI commands, harness utilities, server endpoints, or dashboard code.
PR Scope and Modularity
Keep PRs Focused and Single-Purpose
Split multi-component features: Do not combine backend data models, CLI tools, and frontend UI changes into a single monolithic PR.
Logical progression: Structure larger features into small, stacked, or sequential PRs:
Data layer / core libraries (parsing, normalization, abstractions)
CLI workflows and execution commands
UI / visualization components and dashboard views
Smaller, well-scoped PRs are easier to review, test, and safely revert if regressions occur.
Architectural Principles
Use Existing Abstractions & CLI Runners
Reuse repository tooling: When interacting with LLMs or executing agent workflows, use the shared repository abstractions in config.environment (such as config.environment.antigravityCliBin or config.environment.jetskiCliBin) instead of writing custom REST API clients, bespoke fetch loops, or ad-hoc token validators.
Environment and flag handling: Respect standard environment toggles (such as GD_DEV_USE_JETSKI === '1') and omit non-essential flags (e.g., omit --yolo for non-interactive or diagnostics tasks).
Single Source of Truth & Canonical Enums
Never hardcode string constants for agents:
Use centralized enums like Agents from harness/config.ts (Agents.ANTIGRAVITY_CLI, Agents.JETSKI_CLI, Agents.CLAUDE_CODE, Agents.CODEX_CLI).
Extract metadata from source-of-truth files:
Never infer properties (such as targetFile or agent) using fragile path heuristics or regexes if canonical metadata files (e.g., evals.json) exist in the parent hierarchy. Extract canonical properties directly from evals.json.
Modular Prompt & Template Management
Separate prompts from execution logic: Do not embed long prompt templates, system instructions, or markdown synthesizer templates inside runtime runner files.
Place prompts and instructions into dedicated modules (e.g., *-prompts.ts) to maintain clean separation of concerns.
File, Git, & Config Integrity
Never Weaken Shared Tooling or tsconfig
Strict type safety is non-negotiable: Never modify shared root configurations (tsconfig.json, .oxlintignore, package.json) to bypass typecheck or lint failures.
Fix types properly with TypeScript interfaces and types, or use targeted JSDoc annotations in .js files.
Targeted Remote I/O & Robust Caching
Scope remote storage operations: When downloading from remote stores (such as Cloud Storage/GCS buckets), scope queries and downloads strictly to the specific prefixes and subdirectories needed for the task. Never fetch entire buckets or unrelated directories.
Local caching first: Always check whether required assets or result files already exist locally before initiating remote downloads, avoiding redundant network traffic.
Keep Repository Clean of Generated Artifacts
Ignore transient outputs: Never commit test outputs, debug files, local caches, or working directories.
Store temporary data in standard output locations (e.g., harness/results/) and ensure .gitignore excludes transient files.
Frontend & Dashboard Guidelines
Dual-Environment Compatibility (Static vs. Local Server)
Graceful degradation: The evaluation dashboard operates in both static hosted mode (e.g., GitHub Pages) and local server mode (gd dashboard). Features, actions, or API endpoints requiring a local Node server must detect static mode and gracefully hide or disable themselves.
Explicit data sourcing: When requesting data from local server endpoints, pass the data source context (such as ?source=local) so the server can distinguish local file operations from remote streaming.
Disambiguate Multi-Run and Temporal Data
Handle multiple runs gracefully: Do not assume only a single run exists per day or per task. Distinguish runs using explicit run indices and timestamps to prevent datasets from overwriting or collapsing together.
Robust query parameter handling: Ensure URL query parameters are safely parsed with proper fallbacks, preserving dashboard state across navigations.
Show full SKILL.md (366 more words)Show less
Safe URL & Path Construction
Avoid protocol-relative URL bugs: When constructing URLs from path variables, sanitize slashes to avoid accidental leading double slashes (//...), which browsers interpret as protocol-relative hostnames.
UI Precision & Alignment
Mathematical centering: Ensure chart markers, badges, indicators, and tooltips are centered horizontally and vertically over their target elements so visual associations are unmistakable.
Verification & Testing Gates
Tiered Preflight Gates
All changes must pass linting, typechecking, and tests before PR submission:
Fast dev check (lint & typecheck):bash
pnpm typecheck && pnpm lint
Full preflight gate (all PRs): Bundles build, typecheck, lint, and parallel unit tests across all workspaces:bash
pnpm run preflight
Browser E2E gate (eval-view / dashboard / UI changes): Playwright browser tests are not included in pnpm run preflight and must be executed when touching frontend visualizers, dashboard code, or server endpoints in eval-view/:bash
pnpm --filter eval-view run test:e2e
(Run pnpm run setup:playwright first if browser binaries are not installed).
Domain-Specific Validation
Serving & Skills: When modifying skills packaging, verify with pnpm --filter serving run publish-skills --dry-run.
Guides & Graders: When authoring or updating evaluation capsules, verify grader calibration via gd dev <guide> --test-grader.
Clean Git Tree: The build must produce zero uncommitted side effects or untracked artifacts (git status must remain clean).
Code Hygiene
Safe data parsing: Never use eval() to parse data or JSON; use JSON.parse() or dedicated parsers.
Clean regular expressions: Avoid raw or unescaped control characters in regular expressions; use explicit Unicode escapes (e.g., [\u001b\u009b]).
Quick Reference Checklist Before Submitting PRs
PR Scope: Focused on a single feature, library, or UI component (no monolithic multi-component PRs).
Abstractions: Reuses repository CLI runners (config.environment) and avoids custom API clients.
Enums: Uses the Agents enum from harness/config.ts rather than raw string constants.
Metadata: Reads properties from canonical metadata files (evals.json) instead of path heuristics.
Prompts: Extracted into dedicated *-prompts.ts or constants modules.
Configs: Root tsconfig.json, package.json, and .oxlintignore are untouched unless explicitly intended.
Remote I/O & Git: Remote fetches are strictly scoped and cached; no transient debug artifacts committed.
Dashboard/UI: Handles static vs. local server modes; URL parameters safely parsed and sanitized.
Verification:pnpm run preflight (and pnpm --filter eval-view run test:e2e for eval-view/ changes) passes with 0 errors.
Project Coding Standards next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
Project Coding Standards compared with similar skills
Skill
Stars
Used in
Tokens
Auto-check
Licence
Repo updated
Project Coding Standards this skillGoogleChrome/modern-web-guidance-src
Runs a smell-first audit on a user-chosen path set: measures structure metrics, applies a named size profile, and reports code smells and test smells with evidence strength.
Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.
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…
Workflow for refactoring discipline-level guides (e.g., JavaScript, CSS) to remove "Common Knowledge" by generating and comparing against model-specific "Knowledge Mirrors".
Coding style, architectural conventions, and PR review standards for the modern-web-guidance-src (guidance) repository. Project Coding Standards is an agent skill from GoogleChrome/modern-web-guidance-src. Coding style, architectural conventions, and PR review standards for the modern-web-guidance-src (guidance) repository.
When should I use Project Coding Standards?
Project Coding Standards fits situations like: authoring new code; refactoring features; writing CLI tools; adding server endpoints.
How do I install Project Coding Standards in Claude Code?
Run `npx skills add GoogleChrome/modern-web-guidance-src --skill project-coding-standards -a claude-code`. Or copy the skill folder (.agents/skills/project-coding-standards in GoogleChrome/modern-web-guidance-src) into .claude/skills/project-coding-standards in your project. Claude Code loads it when a task matches its description.
How do I install Project Coding Standards in Codex?
Run `npx skills add GoogleChrome/modern-web-guidance-src --skill project-coding-standards -a codex`. Or copy the skill folder (.agents/skills/project-coding-standards in GoogleChrome/modern-web-guidance-src) into .agents/skills/project-coding-standards in your project. Codex loads it when a task matches its description.
Can I use Project Coding Standards in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GoogleChrome/modern-web-guidance-src --skill project-coding-standards -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/project-coding-standards, .gemini/skills/project-coding-standards, .github/skills/project-coding-standards and .opencode/skills/project-coding-standards in your project.
What does Project Coding Standards need to run?
Going by SKILL.md and its folder, Project Coding Standards needs the command-line tools its instructions call (pnpm and git).
Does Project Coding Standards access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Project Coding Standards safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Project Coding Standards use?
Project Coding Standards is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Project Coding Standards use?
About 2k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Project Coding Standards?
Skills that share tags, products or a category with Project Coding Standards: Smell Check (Zhen-Bo/smell-check, 239 stars), Code Reviewer (Yikai-Liao/symusic, 189 stars), Clean Code (jd-solanki/slidev-theme-dracula, 161 stars) and Code Reviewer (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Project Coding Standards?
GoogleChrome (a GitHub organization) maintains it in GoogleChrome/modern-web-guidance-src, which has 1,134 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 7, 2026.
