Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Greyboxing

ASecurity

Greybox a site's pages — layout, UX, motion on placeholder content — from an existing DESIGN.md. Use when the user wants to greybox, lay out, or build the pages of a site whose design system exists, or when the frontend-design pipeline reaches phase 2.

3 stars
0 votes
0 copies
1 views
Added 9/23/2026
ai-agentsfrontend

Works with

cli

Security Analysis

A100/100

Pro scans all 5 files and shows the line behind each finding

Scanned 9/23/2026

$npx -y skills add Firzus/agent-skills --skill greyboxing --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Greyboxing?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Greyboxing
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/firzus-greyboxing/badge)](https://www.skillsdirectory.com/skills/firzus-greyboxing)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: greyboxing
description: >-
  Greybox a site's pages — layout, UX, motion on placeholder content — from
  an existing DESIGN.md. Use when the user wants to greybox, lay out, or
  build the pages of a site whose design system exists, or when the
  frontend-design pipeline reaches phase 2.
---

# Greyboxing

Build every page's structure, style, and motion on placeholder content — real content lands later, into a frame that already works.

Inputs, read at the start of every session: `DESIGN.md` (identity — never edited here) and `PAGES.md` (pipeline state — owned and updated here). The surface's dials (`DESIGN_VARIANCE`, `MOTION_INTENSITY`, `VISUAL_DENSITY`) gate every layout and motion decision.

Everything is **responsive, designed mobile-first**: build the narrow layout first, then widen through the breakpoints. Sole exception: features inherently bound to one platform. Shared chrome (header, footer, nav) has a **single source** — a component, custom element, or include consumed by every page, never duplicated per page.

## Prerequisites

| Tool / skill     | For                                                                    |
| ---------------- | ---------------------------------------------------------------------- |
| `prototype`      | switchable UI variants of signature-tier pages                         |
| `agent-browser` (or `playwright-cli`) | the visual protocol in [review.md](./review.md); when neither is available, the review degrades to code-level checks and the review report must say so |
| `grilling`       | the site-pass grill                                                    |

## Per-page loop

One page per fresh session, in `PAGES.md` order:

1. **Plan** — pull the page's key sections and tier from `PAGES.md`. Name the page's **signature element** (the one thing it will be remembered by — spend the boldness there, keep everything around it quiet; check `PAGES.md` that no other page already spends it). Write its **motion thesis** ([motion.md](./motion.md)). Declare the page's demoable **states** (empty, error, loading) and the query params that show them. Reach into [vocabulary.md](./vocabulary.md) for named patterns, and [3d-vfx.md](./3d-vfx.md) when the brief or dials call for 3D, video, scroll effects, or shaders.
2. **Variants** — *signature tier only*: invoke the `prototype` skill (UI branch) to generate several throwaway layout variants on the page's route, all consuming the theme source. The user picks the winner — a mix of variants is a valid pick. Utility tier skips this step.
3. **Build** — turn the plan (or winning variant) into the real page: layout, navigation, UX, and motion per the thesis; every style and motion value drawn from the theme source; every declared state reachable; placeholder content everywhere, passing the **Jane Doe test**.
4. **Review** — run the page through [review.md](./review.md): generic-default test, mechanical checklist, visual protocol, fix order. Fix before moving on. No tier skips this step.
5. **Record** — update the page's row in `PAGES.md`: status, signature element, motion thesis, state query params.

**Jane Doe test** — nothing smells fake: credible names, messy numbers like 47.2 %, plausible brand names, seeded real photos — so the review judges true proportions.

## Site pass

Once every page has passed, in its own session: run review.md's **site pass** across the whole set, then invoke the `grilling` skill on the cross-page result (signature spread, chrome, shared patterns). Record the outcome in `PAGES.md`.

**Done when:** every page in `PAGES.md` has passed the review, and the site pass — including its grill — has passed.

Attribution

FirzusFirzus
View sourceSee grades on GitHubMore from Firzus →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →