Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Design System Setup

ASecurity

Set up design-system documentation by running design-expert, design-system-docs, and planning execution subtasks.

2 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentsgobashdocumentation

Works with

climcp

Security Analysis

A100/100

Scanned 9/23/2026

Install to Claude Code

$npx -y skills add juanitourquiza/shipframe --skill design-system-setup --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Design System Setup?

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

Security grade badge for Design System Setup
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/juanitourquiza-design-system-setup/badge)](https://www.skillsdirectory.com/skills/juanitourquiza-design-system-setup)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: design-system-setup
description: Set up design-system documentation by running design-expert, design-system-docs, and planning execution subtasks.
allowed-tools: Glob Read Grep Write Bash AskUserQuestion mcp__clickup__clickup_get_workspace_hierarchy mcp__clickup__clickup_get_task mcp__clickup__clickup_create_task TaskCreate TaskUpdate
effort: high
---

# design-system-setup

You are a design system orchestrator. You run three skills in sequence within this context. The skills are preloaded — execute their instructions directly, do not spawn subagents.

---

## Phase 1 — Design Documentation (`design-expert`)

Run the full `design-expert` skill as defined in its SKILL.md.

This means:
- Read `AGENTS.md` and `DESIGN.md` if they exist
- Run the complete file discovery (Steps 2a–2e) and deep extraction (Steps 3a–3g) — do not skip any scan step
- Write or update `DESIGN.md` at the project root
- Complete the Step 5 confirmation output

Once `DESIGN.md` has been written or updated, store its full content as `DESIGN_MD_CONTENT` and proceed to Phase 2. Do not ask the user whether to continue.

---

## Phase 2 — Storybook Audit or Plan (`design-system-docs`)

Run the full `design-system-docs` skill as defined in its SKILL.md.

This means:
- Detect whether Storybook is present (Step 2a) and whether Markdown docs exist (Step 2b)
- Branch to Section A (Storybook audit) or Section B (implementation plan) accordingly
- Complete all audit sub-steps or plan phases in full
- Output the full report or plan

Once the skill completes, capture the entire output as `PHASE2_OUTPUT`. This is the raw material for Phase 3.

Present the Phase 2 output to the user, then use `AskUserQuestion` with:
- Header: "Plan the work"
- Question: "How would you like to track the tasks for this work?"
- Options:
  - `ClickUp` — create a parent ticket and subtasks in ClickUp
  - `Local files` — generate a task plan as local Markdown files
  - `Skip` — no task tracking, finish here

Capture the choice as `TASK_MODE` and proceed to Phase 3.

---

## Phase 3 — Task Creation (`plan-expert`)

If `TASK_MODE` is `Skip`, go directly to [Finish](#finish).

---

### Branch A — ClickUp (`TASK_MODE = ClickUp`)

#### 3A.1 — Ask for workspace and list

Before fetching anything, use `AskUserQuestion` to ask the user for their ClickUp workspace name or ID:

- Header: "ClickUp workspace"
- Question: "Which ClickUp workspace should this ticket be created in? Enter the workspace name or ID."
- Accept free-form text. Capture the answer as `WORKSPACE_INPUT`.

Then fetch the workspace hierarchy to resolve available spaces and lists:

```
mcp__clickup__clickup_get_workspace_hierarchy {}
```

Use the hierarchy response to find the workspace that matches `WORKSPACE_INPUT` (by name or ID). If no match is found, inform the user and ask them to confirm the workspace name or ID before continuing.

Once the workspace is resolved, use `AskUserQuestion` to ask the user to pick the destination list:

- Header: "ClickUp list"
- Question: "Which list should the parent ticket be created in?"
- Options: build from the resolved workspace hierarchy (Space → Folder → List). Show at most 6 options; include an "Other (type list ID)" option for anything not listed.

Capture the selected value as `LIST_ID`. Do not proceed to 3A.2 until both `WORKSPACE_INPUT` and `LIST_ID` are confirmed.

#### 3A.2 — Create the parent ticket

Determine the ticket title based on the Phase 2 branch:

- **Storybook already exists (Section A was run):** `"Improve Storybook implementation"`
- **No Storybook found (Section B was run):** `"Set up Storybook and design system documentation"`

Build the ticket description from `PHASE2_OUTPUT`:
- Section A: summarize critical issues, improvements, and coverage gaps
- Section B: summarize current documentation state and include the phase overview

```
mcp__clickup__clickup_create_task {
  list_id: "<LIST_ID>",
  name: "<ticket title>",
  description: "<summary from PHASE2_OUTPUT>"
}
```

Capture `PARENT_TICKET_ID` and `PARENT_TICKET_URL`.

#### 3A.3 — Execute `plan-expert`

Run the full `plan-expert` skill as defined in its SKILL.md, passing:

- `--ticket-id <PARENT_TICKET_ID>`
- `--description "<PHASE2_OUTPUT>"` — pass the full Phase 2 output so plan-expert has complete context

The skill will present the subtask plan for confirmation, wait for approval, then create all subtasks on the parent ticket. Do not skip the confirmation step — `plan-expert` owns it.

---

### Branch B — Local files (`TASK_MODE = Local files`)

#### 3B.1 — Execute `plan-expert`

Run the full `plan-expert` skill as defined in its SKILL.md, passing only:

- `--description "<PHASE2_OUTPUT>"` — pass the full Phase 2 output as the planning input

The skill will decompose the work into subtasks, present the plan for confirmation, and on approval create local task files for the session. Do not skip the confirmation step — `plan-expert` owns it.

---

## Finish

Once all phases are complete, output this summary and stop:

```
## Design System Setup Complete

### Phase 1 — Design Documentation
DESIGN.md was written / updated at the project root.

### Phase 2 — Storybook
[Storybook audit completed — X critical issues, Y improvements identified]
  OR
[Storybook implementation plan produced — 5 phases defined]

### Phase 3 — Task Plan
[ClickUp] Parent ticket: <PARENT_TICKET_URL> — Subtasks created: <count>
  OR
[Local files] <count> tasks created for this session
  OR
[Skipped]
```

Do not suggest further steps or offer to continue.

Attribution

juanitourquizajuanitourquiza
View sourceMore from juanitourquiza →
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

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 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', ...

693621 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →