ERC-8004 Register
Register AI agents on-chain, update metadata, validate registrations, and auto-fix broken profiles via the ERC-8004 Identity Registry. Supports Base, Ethereum, Polygon, Monad, BNB.
Best use case
ERC-8004 Register is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Register AI agents on-chain, update metadata, validate registrations, and auto-fix broken profiles via the ERC-8004 Identity Registry. Supports Base, Ethereum, Polygon, Monad, BNB.
Teams using ERC-8004 Register 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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/erc8004-register/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ERC-8004 Register Compares
| Feature / Agent | ERC-8004 Register | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Register AI agents on-chain, update metadata, validate registrations, and auto-fix broken profiles via the ERC-8004 Identity Registry. Supports Base, Ethereum, Polygon, Monad, BNB.
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
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# ERC-8004 Registration Skill
Register, update, validate, and fix agents on-chain via the ERC-8004 Identity Registry.
## Use This When...
- "Register my agent on-chain"
- "I need to create a new ERC-8004 agent"
- "Update my agent's metadata"
- "Check if my agent registration is valid"
- "Fix my agent's registration issues"
- "Show my agent's on-chain info"
- "What agents do I own?"
- "Health check my agents"
## Commands
### register
Register a new agent on-chain.
```bash
python scripts/register.py register --name "AgentName" --description "Description" [--image URL] [--chain base]
```
**Options:**
- `--name` (required): Agent name
- `--description` (required): Agent description
- `--image`: Image URL (must be https://)
- `--chain`: Blockchain (base, ethereum, polygon, monad, bnb). Default: base
### update
Update an existing agent's metadata.
```bash
python scripts/register.py update <agentId> [--name NAME] [--description DESC] [--image URL] [--add-service name=X,endpoint=Y] [--remove-service NAME] [--chain base]
```
### info
Display agent information.
```bash
python scripts/register.py info <agentId> [--chain base]
```
### validate
Check registration for common issues.
```bash
python scripts/register.py validate <agentId> [--chain base]
```
**Checks:**
- Missing `type` field
- Local-path images (/home/..., ./, file://)
- Empty name/description
- Missing registrations array
- Unreachable image URLs
### fix
Auto-fix common registration issues.
```bash
python scripts/register.py fix <agentId> [--chain base] [--dry-run]
```
**Auto-fixes:**
- Missing `type` field
- Missing `registrations` array
- Local-path images (removes them)
Use `--dry-run` to preview changes without applying.
### self-check
Check all agents owned by your wallet.
```bash
python scripts/register.py self-check
```
Queries Agentscan for your agents, validates each, and prints a health report.
## Cross-Skill Workflows
### Post-Registration Flow
```bash
# 1. Register new agent
python scripts/register.py register --name "MyBot" --description "Trading assistant"
# 2. Validate the registration
python scripts/register.py validate 42 --chain base
# 3. Check initial reputation (from erc8004-reputation skill)
python scripts/reputation.py lookup 42 --chain base
# 4. Monitor for discovery (from erc8004-discover skill)
python scripts/discover.py info 42
```
### Periodic Health Check
```bash
# Run self-check to validate all your agents
python scripts/register.py self-check
# Fix any issues found
python scripts/register.py fix 42 --chain base
```
## Heartbeat Integration
For automated monitoring, run self-check periodically:
```bash
# Cron: check health every hour
0 * * * * cd /path/to/skill && python scripts/register.py self-check >> /var/log/agent-health.log 2>&1
# Or in a script:
#!/bin/bash
python scripts/register.py self-check
if [ $? -ne 0 ]; then
echo "Agent health check failed!" | notify-send
fi
```
## Wallet Configuration
Set one of these environment variables:
```bash
export ERC8004_MNEMONIC="your twelve word mnemonic phrase here"
# OR
export ERC8004_PRIVATE_KEY="0x..."
```
## Contract
Identity Registry: `0x8004A169FB4a3325136EB29fA0ceB6D2e539a432` (same on all chains)
## Supported Chains
| Chain | ID | Explorer |
|----------|------|----------------------|
| Base | 8453 | basescan.org |
| Ethereum | 1 | etherscan.io |
| Polygon | 137 | polygonscan.com |
| Monad | 143 | explorer.monad.xyz |
| BNB | 56 | bscscan.com |
## Dependencies
```bash
pip install web3 eth-account
```
## Related Skills
- **erc8004-discover**: Find and monitor agents
- **erc8004-reputation**: Rate agents and check trust scoresRelated Skills
doppel-erc-8004
Register your agent onchain with ERC-8004. Set up a wallet, fund it, register on the Identity Registry, and link your onchain identity back to the Doppel hub for verifiable reputation and token allocation.
agentconnex-register
Auto-register OpenClaw agents on AgentConnex (agentconnex.com) — the professional network for AI agents. Zero-config auto-boot registration requires no API key. Use when deploying a new agent, updating agent capabilities, or syncing agent profiles to AgentConnex. Triggers on "register on agentconnex", "sync agent profile", "update agentconnex", or when an agent boots.
ERC-8004 Reputation
On-chain reputation for AI agents. Give feedback, check scores, view leaderboards, and build trust via the ERC-8004 Reputation Registry. Supports Base, Ethereum, Polygon, Monad, BNB.
ERC-8004 Agent Discovery
Search and discover 43k+ AI agents registered via ERC-8004. Find agents by skill, chain, or reputation. View leaderboards, ecosystem stats, and monitor metadata changes.
qwen-auto-register
自动注册 Qwen 账号并获取 token。支持预测性自动切换,避免 API 额度超限。需要安装 auto-register 包。
---
name: article-factory-wechat
humanizer
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.
find-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.
tavily-search
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.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
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.