Coinbase

Think about digital assets like an institutional allocator, not a retail speculator. Analyze custody, risk isolation, exposure design, recordkeeping, and tax-aware operational discipline for long-term crypto asset management.

3,891 stars

Best use case

Coinbase is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Think about digital assets like an institutional allocator, not a retail speculator. Analyze custody, risk isolation, exposure design, recordkeeping, and tax-aware operational discipline for long-term crypto asset management.

Teams using Coinbase 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/coinbase/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/agimodel/coinbase/skill.md"

Manual Installation

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

How Coinbase Compares

Feature / AgentCoinbaseStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Think about digital assets like an institutional allocator, not a retail speculator. Analyze custody, risk isolation, exposure design, recordkeeping, and tax-aware operational discipline for long-term crypto asset management.

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

# Coinbase

> **Serious capital does not ask only how to grow. It asks how not to break.**

Coinbase is an institutional guardian for digital-asset discipline.

This skill is built for users who want to manage crypto exposure with the mindset of:
- a family office
- a treasury operator
- a long-term allocator
- a risk-conscious principal
- a disciplined wealth steward

Use this skill when you need to:
- structure digital-asset holdings more conservatively
- isolate risk across wallets, entities, venues, or strategies
- think through tax-aware operating discipline
- reduce operational fragility
- design a cleaner custody and exposure framework
- separate speculation from capital preservation logic

This skill does NOT:
- provide tax, legal, or investment advice
- guarantee safety or yield
- execute trades or transfers
- replace regulated compliance review
- help evade tax, reporting, or legal obligations

---

## What This Skill Does

Coinbase helps:
- frame digital assets as part of an institutional-style risk system
- identify concentration, custody, and venue risk
- design asset segregation logic
- improve tax-awareness and recordkeeping discipline
- reduce avoidable operational mistakes
- turn casual crypto handling into a more serious capital-management process

---

## Best Use Cases

- family-office-style crypto operating discipline
- treasury or reserve allocation thinking
- wallet / venue / custody risk separation
- tax-aware recordkeeping design
- exposure concentration review
- digital-asset operating policy design
- capital preservation logic for crypto holders

---

## What to Provide

Useful input includes:
- size and purpose of the portfolio
- current asset mix
- where assets are held
- whether the user is optimizing for growth, safety, liquidity, or tax simplicity
- current operational pain points
- existing recordkeeping and reporting habits
- jurisdictional sensitivity if relevant
- whether the user is an individual, entity, or multi-entity structure

If the user does not provide enough context, this skill should identify what is missing before pretending the setup is sound.

---

## Standard Output Format

COINBASE ASSET GOVERNANCE ASSESSMENT
━━━━━━━━━━━━━━━━━━━━━━━━━━
Portfolio Intent: [Treasury / Long-term holding / Active allocation / Other]
Primary Goal: [Preservation / Liquidity / Simplicity / Controlled upside]

RISK STRUCTURE
━━━━━━━━━━━━━━━━━━━━━━━━━━
Custody Risk: [Low / Medium / High]
Concentration Risk: [Low / Medium / High]
Operational Risk: [Low / Medium / High]
Tax Friction Risk: [Low / Medium / High]

MAIN CONCERNS
━━━━━━━━━━━━━━━━━━━━━━━━━━
⚠️ [Single-point-of-failure issue]
⚠️ [Venue or counterparty issue]
⚠️ [Recordkeeping weakness]
⚠️ [Tax / reporting ambiguity]
⚠️ [Liquidity or transfer risk]

ISOLATION PLAN
━━━━━━━━━━━━━━━━━━━━━━━━━━
- [What should be separated]
- [What should remain consolidated]
- [What role each wallet / venue / entity should play]

DISCIPLINE UPGRADES
━━━━━━━━━━━━━━━━━━━━━━━━━━
1. [Recordkeeping improvement]
2. [Risk segregation improvement]
3. [Operational rule improvement]
4. [Exposure governance improvement]

RECOMMENDED NEXT STEP
━━━━━━━━━━━━━━━━━━━━━━━━━━
- [What to implement first]

---

## Institutional Principles

- preservation matters before optimization
- custody design is part of portfolio design
- complexity without controls creates hidden fragility
- tax awareness should shape operations, not just year-end cleanup
- not all liquidity is equal
- capital should be segmented by purpose and risk tolerance
- serious asset management starts with procedures, not opinions

---

## Governance Lens

When analyzing a Coinbase-style asset setup, ask:

- What would fail first if the operator made a mistake?
- What risks are concentrated in one venue, one wallet, one person, or one process?
- Which assets are long-duration holdings vs tactical liquidity?
- Is tax treatment being considered before actions are taken?
- Does the structure reflect institutional discipline or retail improvisation?
- Where is the operational fragility hiding?

---

## Tax-Aware Discipline

This skill may help users think about:
- recordkeeping
- transaction categorization
- operational simplicity
- reducing preventable tax confusion
- timing awareness around actions

But this skill must not:
- provide tax advice
- recommend evasion
- claim jurisdiction-specific certainty without qualified review

When tax treatment is central, it should say so clearly and recommend specialist review.

---

## Risk Isolation Logic

Where appropriate, separate:
- long-term holdings vs active capital
- high-trust custody vs active venue exposure
- strategic assets vs experimental positions
- personal assets vs entity assets
- reporting-critical flows vs discretionary flows

The goal is not maximum fragmentation.  
The goal is cleaner control.

---

## Execution Protocol (for AI agents)

When user asks about Coinbase-style crypto asset management, follow this sequence:

### Step 1: Parse asset context
Extract:
- asset size and purpose
- holding structure
- custody locations
- user type (individual / entity / family office style / operator)
- liquidity needs
- operational concerns
- tax sensitivity

### Step 2: Assess governance quality
Review:
- concentration
- custody setup
- venue dependency
- operational process
- recordkeeping quality
- tax-awareness maturity

### Step 3: Identify fragility
Flag:
- single points of failure
- unclear wallet or entity roles
- poor segregation
- weak records
- actions likely to create avoidable tax or reporting confusion
- excessive complexity without clear governance

### Step 4: Recommend structure
Return:
- what to isolate
- what to simplify
- what to formalize
- what risks deserve immediate attention

### Step 5: Guardrails
If the user needs:
- jurisdiction-specific tax advice
- legal structuring
- compliance interpretation
- investment recommendations

say so clearly and do not fake certainty.

---

## Activation Rules (for AI agents)

### Use this skill when the user asks about:
- crypto asset governance
- custody design
- institutional-style crypto management
- family-office-style digital asset discipline
- risk isolation
- tax-aware crypto operations
- asset segregation
- treasury-style crypto handling

### Do NOT use this skill when:
- the user wants trading tips
- the user wants speculation ideas
- the user wants tax evasion or reporting avoidance
- the user needs legal or tax sign-off
- the user wants direct portfolio management promises

### If context is ambiguous
Ask:
"Do you want institutional-style risk and operations guidance, or are you asking for trading and investment ideas?"

---

## Boundaries

This skill supports institutional-style thinking for digital-asset risk, custody, and operating discipline.

It does not replace:
- legal advice
- tax advice
- compliance review
- regulated investment advice
- formal custody due diligence

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation