crm-antdesign-admin-spec

Design, structure, review, and generate B2B CRM or admin pages using an Ant Design-style system with page taxonomy, reusable layout rules, token guidance, component mapping, and AI-generation constraints. Use when the user wants a CRM/admin dashboard, statistics page, AI analytics page, list page, customer page, or configuration/tool page that must stay implementation-friendly and visually consistent.

3,891 stars

Best use case

crm-antdesign-admin-spec is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Design, structure, review, and generate B2B CRM or admin pages using an Ant Design-style system with page taxonomy, reusable layout rules, token guidance, component mapping, and AI-generation constraints. Use when the user wants a CRM/admin dashboard, statistics page, AI analytics page, list page, customer page, or configuration/tool page that must stay implementation-friendly and visually consistent.

Teams using crm-antdesign-admin-spec should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/crm-antdesign-admin-spec/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/benisonli/crm-antdesign-admin-spec/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/crm-antdesign-admin-spec/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How crm-antdesign-admin-spec Compares

Feature / Agentcrm-antdesign-admin-specStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Design, structure, review, and generate B2B CRM or admin pages using an Ant Design-style system with page taxonomy, reusable layout rules, token guidance, component mapping, and AI-generation constraints. Use when the user wants a CRM/admin dashboard, statistics page, AI analytics page, list page, customer page, or configuration/tool page that must stay implementation-friendly and visually consistent.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# CRM Ant Design Admin Spec

## What this skill is for

Use this skill when the user needs help with:
- designing a B2B CRM / admin page
- generating a page spec before UI or frontend work starts
- reviewing whether a page matches Ant Design-style admin semantics
- keeping dashboard, list, and config pages from drifting into inconsistent styles
- creating prompts for UIUXProMax or similar AI page-generation workflows

This skill is especially useful when:
- the page belongs to a CRM, SaaS admin, analytics, or operations system
- the output needs strong structure and good information density
- the page should feel realistic to implement with Ant Design
- the user wants a reusable design system instead of one-off pretty mockups

## What this skill is NOT for

Do **not** use this as the main skill for:
- marketing websites
- landing pages
- mobile-app-first interfaces
- expressive visual branding projects
- illustration-heavy storytelling pages
- highly experimental visual design where implementation realism is secondary

## Default design direction

Prefer:
- Ant Design-style admin UI
- strong hierarchy and structure
- realistic implementation paths
- compact but readable information organization
- reusable page skeletons
- light AI-enhanced visual language only when the page truly needs it

Avoid:
- marketing-site aesthetics
- heavy glassmorphism
- cyberpunk / glow-heavy visuals
- mobile-first interaction patterns for desktop admin tasks
- decorative gradients across the entire page

## Core operating rule

First classify the page type, then apply the matching structure and constraints.

Do **not** treat every page like a dashboard.

## Page type decision

Choose one of these before designing:

1. **Statistics page**
   - KPI cards
   - charts
   - time filters
   - org tree / left filter panel
   - management overview

2. **AI analytics page**
   - analytics dashboard
   - insights / risks / recommendations
   - KPI + charts + AI summary blocks
   - slightly enhanced visual tone allowed

3. **List page**
   - customer lists
   - operational tables
   - search / filters / pagination
   - CRUD-oriented workflow

4. **Configuration / tool page**
   - parameter setup
   - upload areas
   - forms + tables
   - left functional menu + right config content

If uncertain, default to the simplest page type that matches the task.

## How to use this skill

### For design tasks
- identify the page type first
- outline the page skeleton
- specify major regions: header, filters, actions, KPI, charts, table, side nav, config form, empty state
- keep the result implementation-friendly

### For review tasks
Check for:
- wrong page type choice
- inconsistent spacing / radius / color hierarchy
- non-Ant-Design-like controls
- excessive decoration
- weak information density
- weak admin usability
- dashboard thinking forced onto list/config pages

### For AI generation tasks
Use prompt patterns from `references/prompt-templates.md`.

### For design-system alignment
Use `references/token-and-components.md`.

### For page skeleton and visual rules
Use `references/admin-guidelines.md`.

### For concrete examples
Use `references/examples.md`.

## Recommended output pattern

When generating a page spec or design direction:

1. Identify the page type
2. Pick the matching skeleton
3. Apply token / color / radius / typography rules
4. Map to likely Ant Design components
5. Add AI-specific enhancement only if the page truly needs it
6. State what should *not* be done for this page type

## Deliverable styles this skill can support

This skill can guide outputs such as:
- page strategy notes
- page information architecture
- UI section breakdowns
- component recommendations
- prompt templates for AI design/build tools
- design review comments
- implementation-friendly HTML / React / admin page planning prompts

## References

- Read `references/admin-guidelines.md` for visual system, page taxonomy, and page skeletons.
- Read `references/token-and-components.md` for token mapping and Ant Design component mapping.
- Read `references/prompt-templates.md` when creating prompts for UIUXProMax or other AI page generators.
- Read `references/examples.md` for example page interpretations and output patterns.

Related Skills

Home Inspection Business Operations

3891
from openclaw/skills

Run a profitable home inspection business with real numbers, compliance checklists, and growth playbooks.

Benefits Administration Agent

3891
from openclaw/skills

You are an employee benefits administration specialist. Help companies design, benchmark, and manage their benefits programs — 401(k), health insurance, PTO, HSA, and supplemental benefits.

HR & Benefits Management

project-retrospective

3891
from openclaw/skills

自动项目复盘机制。当完成复杂项目后,自动提取最优路径生成skill,并记录踩坑经验到memory。

trendyol-admin

3891
from openclaw/skills

Comprehensive management of Trendyol marketplace via API v2.0. Includes product lifecycle (create, update, delete, archive), stock/price management, order processing (status updates, shipping), returns, and customer questions. Use this skill as a knowledge base to construct correct API requests.

prompt-inspector

3891
from openclaw/skills

Detect prompt injection attacks and adversarial inputs in user text before passing it to your LLM. Use when you need to validate or screen user-provided text for jailbreak attempts, instruction overrides, role-play escapes, or other prompt manipulation techniques. Returns a safety verdict, risk score (0–1), and threat categories. Ideal for guarding AI pipelines, chatbots, and any application that feeds user input into a language model.

spec-kit

3891
from openclaw/skills

Use GitHub Spec Kit for Spec-Driven Development. Initialize projects, create specifications, and build software using the /speckit.* slash commands. Supports Claude Code, GitHub Copilot, Gemini CLI, and Codebuddy.

openclaw-admin

3891
from openclaw/skills

Manage and inspect the OpenClaw multi-agent gateway — list agents, check model health, view routing rules, manage crons, inspect context budgets, and run system diagnostics.

discord-admin-elite

3891
from openclaw/skills

Build, harden, and scale elite Discord servers with a practical admin playbook: security baseline, role/permission architecture, onboarding, moderation ops, engagement systems, and analytics-driven iteration. Use when designing a new server, auditing an existing one, fixing chaos, or preparing for growth.

tls-inspect

3891
from openclaw/skills

Inspect TLS certificate (expiry, SANs, chain, cipher)

harvey-specter-writing-style

3891
from openclaw/skills

Rewrite or draft text in a Harvey Specter (Suits)-inspired writing style: confident, concise, sharp-witted, leverage-focused, and decisive. Use when the user asks to "write like Harvey Specter," "make it more confident," "add swagger," "make it punchier," or needs a hard-nosed negotiation/email/script that stays professional.

risk-management-specialist

3891
from openclaw/skills

Medical device risk management specialist implementing ISO 14971 throughout product lifecycle. Provides risk analysis, risk evaluation, risk control, and post-production information analysis. Use when user mentions risk management, ISO 14971, risk analysis, FMEA, fault tree analysis, hazard identification, risk control, risk matrix, benefit-risk analysis, residual risk, risk acceptability, or post-market risk.

mdr-745-specialist

3891
from openclaw/skills

EU MDR 2017/745 compliance specialist for medical device classification, technical documentation, clinical evidence, and post-market surveillance. Covers Annex VIII classification rules, Annex II/III technical files, Annex XIV clinical evaluation, and EUDAMED integration.