decisions-design-references
Playbook for Aceternity UI, Refero MCP, Mobbin MCP, and Godly when building or polishing web UI — what each source is for and how agents should use it.
Skill by tensology
Chalk Labs
Need help deploying decisions-design-references?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tensology-decisions-design-references
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/decisions-design-references
What's inside
- Skill name
decisions-design-references- Description
- Playbook for Aceternity UI, Refero MCP, Mobbin MCP, and Godly when building or polishing web UI — what each source is for and how agents should use it.
- License
- MIT
- Instructions
- 98 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
<!-- GLOBAL_UI_UX_REFERENCE -->
## Global interface source
Before using this skill for interface work, read the current global `ui-ux-system` skill (`~/.agents/skills/ui-ux-system/SKILL.md`), especially its Paul's rules, settled taste rules, and Definition of Done - UI. Those rules are authoritative and override conflicting guidance here. Aesthetic recipes are opt-in: use them only when the brief explicitly calls for them and they earn their place. This skill adds only its specialized guidance.
# Design Reference Sources
DecisionsAI does not replace these products — it tells agents **which tool for which job** and how to wire MCPs.
## Quick pick
| Need | Use |
|------|-----|
| Paste-ready React/Tailwind/Motion components | **Aceternity UI** — ui.aceternity.com |
| Real shipped screens + DESIGN.md tokens | **Refero MCP** — refero.design/mcp (Pro) |
| Pattern library + flows (mobile/web) | **Mobbin MCP** — api.mobbin.com/mcp (Pro, OAuth) |
| Visual inspiration only | **Godly** — godly.website (manual screenshots/links) |
| ECC implementation taste | `frontend-design`, `ui-ux-system` |
**“10x”** — if someone lists five sites and the fifth is “10x”, it is usually slang or a misheard name, not a fifth MCP. Ask the user for the exact URL unless they confirm a product.
---
## Aceternity UI (no MCP)
- Site: https://ui.aceternity.com
- Stack: React, Tailwind CSS, Framer Motion
- **Workflow:** open the component page → copy the published code → adapt to project structure (paths, imports, design tokens).
- **Agent tip:** put the component URL in the prompt: “Implement the bento grid from ui.aceternity.com/components/…”
- Do not invent Aceternity APIs — only use what’s on the page.
---
## Refero (official MCP + optional skill)
- MCP docs: https://refero.design/mcp
- Library: styles.refero.design (DESIGN.md extracts)
- **Requires:** Refero Pro; browser OAuth on first MCP call.
- **MCP gives:** search over 130k+ screens and flows with structured metadata (patterns, layouts).
- **Optional skill:** `npx skills add https://github.com/referodesign/refero_skill`
- **Example prompts:**
- “Find onboarding flows from fintech apps”
- “Show how Linear handles empty states”
- “Extract typography and spacing for a dense settings page”
- Paste extracted tokens into the repo as CSS variables or tailwind theme extension.
---
## Mobbin (official HTTP MCP)
- Site: https://mobbin.com
- Endpoint: `https://api.mobbin.com/mcp`
- **Requires:** Mobbin Pro (~€10/month); OAuth via browser on first use.
- **Claude Code setup:**
```bash
claude mcp add mobbin --scope user --transport http https://api.mobbin.com/mcp
```
- **Cursor:** add to `~/.cursor/mcp.json`:
```json
{
"mcpServers": {
"mobbin": {
"url": "https://api.mobbin.com/mcp"
}
}
}
```
- Use for: navigation patterns, paywalls, onboarding, mobile-specific layouts.
- Cite which pattern you copied and why it fits the ticket.
---
## Godly (gallery only)
- Site: https://godly.website
- No API, no MCP.
- **Workflow:** user or agent picks 1–3 gallery pages → attach screenshots or URLs → describe what to borrow (typography mood, color, density).
- Do not claim Godly integration — treat as human-curated mood board.
---
## Decisions integration
- **Ideation first:** `decisions-ui-ideation`
- **Setup:** `~/.decisions/harness/mcp-setup-design.sh` and `mcp-recommendations.json`
- **Workflows:** UI steps should list this skill + `frontend-design`
- **Evidence:** in result packets, list references used (Refero query, Mobbin pattern, Aceternity URL, Godly link).
---
## When MCP is unavailable
1. Use repo existing UI as primary reference.
2. Aceternity component URLs for concrete components.
3. Godly links/screenshots for direction.
4. State in `Blockers:` or `Summary:` that Refero/Mobbin need Pro + MCP setup — do not fake live search results.From tensology/decisionsai, MIT.
More from tensology/decisionsai
- 0.646score
domain-modeling
tensology
Use when a project needs shared terminology, glossary updates, ADRs, clearer domain language, or when user language conflicts with existing code, ticket…
SkillAFreshness: A★ 17Claude Code +9 - 0.646score
architecture-deepening-review
tensology
Use when reviewing a codebase for architectural friction, shallow modules, poor test seams, scattered behavior, duplicated orchestration, or opportunities to…
SkillAFreshness: A★ 17Claude Code +9 - 0.646score
impeccable
tensology
Explicit-command design reviewer.
SkillAFreshness: A★ 17Claude Code +9 - 0.643score
visual-plan
tensology
Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype review when useful.
SkillAFreshness: A★ 17Claude Code +9 - 0.641score
quick-recap
tensology
Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md…
SkillAFreshness: A★ 17Claude Code +9 - 0.641score
stay-within-limits
tensology
Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming…
SkillAFreshness: A★ 17Claude Code +9 - 0.641score
plow-ahead
tensology
Use when the user explicitly wants autonomous progress without routine clarification stops: "plow ahead", "do not stop", "use your best judgment", "keep going…
SkillAFreshness: A★ 17Claude Code +9 - 0.641score
codebase-design
tensology
Use when designing or improving a module interface, choosing a seam, reducing shallow modules, making code easier to test, or reviewing architecture for…
SkillAFreshness: A★ 17Claude Code +9 - 0.641score
read-the-damn-docs
tensology
Use when implementing, integrating, upgrading, debugging, or answering anything involving third-party APIs, libraries, frameworks, CLIs, cloud services…
SkillAFreshness: A★ 17Claude Code +9 - 0.641score
plan-arbiter
tensology
Use when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two…
SkillAFreshness: A★ 17Claude Code +9 - 0.640score
ln-721-frontend-restructure
tensology
Frontend structure worker: SCAFFOLD new React project or RESTRUCTURE existing monolith to component-based architecture
SkillAFreshness: A★ 17Claude Code +9 - 0.638score
decisions-design-aesthetics
tensology
Pick a design aesthetic from awesome-design-skills — bundled minimal/professional/enterprise/shadcn/bento; full catalog in reference for on-demand load.
SkillAFreshness: A★ 17Claude Code +9
Signals
- Stars
- 17
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- Oct 24, 2026 (7 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/tensology/decisionsai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from tensology
- 0.646score
impeccable
tensology
Explicit-command design reviewer.
SkillAFreshness: A★ 17Claude Code +9 - 0.646score
domain-modeling
tensology
Use when a project needs shared terminology, glossary updates, ADRs, clearer domain language, or when user language conflicts with existing code, ticket…
SkillAFreshness: A★ 17Claude Code +9 - 0.646score
architecture-deepening-review
tensology
Use when reviewing a codebase for architectural friction, shallow modules, poor test seams, scattered behavior, duplicated orchestration, or opportunities to…
SkillAFreshness: A★ 17Claude Code +9 - 0.643score
visual-plan
tensology
Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype review when useful.
SkillAFreshness: A★ 17Claude Code +9 - 0.641score
quick-recap
tensology
Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md…
SkillAFreshness: A★ 17Claude Code +9 - 0.641score
read-the-damn-docs
tensology
Use when implementing, integrating, upgrading, debugging, or answering anything involving third-party APIs, libraries, frameworks, CLIs, cloud services…
SkillAFreshness: A★ 17Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get decisions-design-references running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
decisions-design-references skill. Agent Mart. https://agentmart.dev/skills/tensology-decisions-design-references (last updated 2026-10-24)