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.

3,891 stars

Best use case

ERC-8004 Reputation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

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.

Teams using ERC-8004 Reputation 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/erc8004-reputation/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/aetherstacey/erc8004-reputation/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/erc8004-reputation/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How ERC-8004 Reputation Compares

Feature / AgentERC-8004 ReputationStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

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.

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

# ERC-8004 Reputation Skill

Interact with the ERC-8004 Reputation Registry — the decentralized reputation layer for AI agents.

## Use This When...

- "Check an agent's reputation"
- "Rate this agent"
- "Give feedback to agent X"
- "What's my agent's reputation?"
- "Who gave feedback to my agent?"
- "Show me the reputation leaderboard"
- "Top agents by reputation"
- "Revoke my feedback"

## Commands

### lookup
Look up an agent's reputation summary.

```bash
python scripts/reputation.py lookup <agentId> [--chain CHAIN]
```

Shows: reviewer count, feedback count, summary value, individual feedback.

### give
Give feedback to an agent.

```bash
python scripts/reputation.py give <agentId> <value> [--decimals N] [--tag1 TAG] [--tag2 TAG] [--chain CHAIN]
```

**Examples:**
```bash
# Simple score (0-100)
python scripts/reputation.py give 16700 85 --tag1 reliable

# Percentage with decimals (99.77%)
python scripts/reputation.py give 16700 9977 --decimals 2 --tag1 uptime
```

### my-rep
Check your agent's reputation across all chains.

```bash
python scripts/reputation.py my-rep <agentId> [--chains base,ethereum,polygon]
```

### clients
List all addresses that gave feedback.

```bash
python scripts/reputation.py clients <agentId> [--chain CHAIN]
```

### feedback
Read a specific feedback entry.

```bash
python scripts/reputation.py feedback <agentId> <clientAddress> <feedbackIndex> [--chain CHAIN]
```

### revoke
Revoke feedback you previously gave.

```bash
python scripts/reputation.py revoke <agentId> <feedbackIndex> [--chain CHAIN]
```

### leaderboard
Show top agents by reputation score.

```bash
python scripts/reputation.py leaderboard [--chain CHAIN] [--limit 20]
```

Fetches from Agentscan API and displays top agents with scores and star ratings.

## Cross-Skill Workflows

### Post-Registration Reputation Building
```bash
# 1. Register your agent (from erc8004-register skill)
python scripts/register.py register --name "MyBot" --description "..."

# 2. Validate the registration
python scripts/register.py validate 42

# 3. Check initial reputation (should be empty)
python scripts/reputation.py lookup 42

# 4. After interacting with clients, check reputation growth
python scripts/reputation.py my-rep 42
```

### Before Interacting with an Agent
```bash
# 1. Find the agent (from erc8004-discover skill)
python scripts/discover.py search "oracle"

# 2. Get detailed info
python scripts/discover.py info 0x1234...

# 3. Check their reputation
python scripts/reputation.py lookup 42 --chain base

# 4. If satisfied, interact and then give feedback
python scripts/reputation.py give 42 85 --tag1 reliable --tag2 accurate
```

### Reputation Monitoring
```bash
# Check your reputation regularly
python scripts/reputation.py my-rep 42

# See who's giving feedback
python scripts/reputation.py clients 42 --chain base

# Read specific feedback
python scripts/reputation.py feedback 42 0xABC... 1 --chain base
```

## Heartbeat Integration

Monitor reputation changes in automated pipelines:

```bash
# Cron: check reputation daily
0 9 * * * python scripts/reputation.py my-rep 42 >> /var/log/rep-monitor.log 2>&1

# In a monitoring script:
#!/bin/bash
# Get current feedback count
count=$(python scripts/reputation.py lookup 42 2>&1 | grep "Feedback count:" | awk '{print $3}')
last_count=$(cat /tmp/rep-count-42.txt 2>/dev/null || echo 0)
if [ "$count" != "$last_count" ]; then
    echo "New feedback received! Count: $count" | notify-send
    echo "$count" > /tmp/rep-count-42.txt
fi
```

## Configuration

### Wallet (required for write operations)

```bash
export ERC8004_MNEMONIC="your twelve word mnemonic phrase here"
# OR
export ERC8004_PRIVATE_KEY="0xabc123..."
```

Read operations (lookup, my-rep, clients, feedback, leaderboard) don't need a wallet.

### Supported Chains

| Chain    | ID   | Default | Gas Cost |
|----------|------|---------|----------|
| Base     | 8453 | Yes     | ~$0.001  |
| Ethereum | 1    |         | ~$1-10   |
| Polygon  | 137  |         | ~$0.01   |
| Monad    | 143  |         | ~$0.001  |
| BNB      | 56   |         | ~$0.05   |

Base is recommended — cheapest gas by far.

## Contract Addresses

Same on all chains:
- **Identity Registry**: `0x8004A169FB4a3325136EB29fA0ceB6D2e539a432`
- **Reputation Registry**: `0x8004BAa17C55a88189AE136b182e5fdA19dE9b63`

## Dependencies

```bash
pip install web3 eth-account
```

## Related Skills

- **erc8004-register**: Register and manage agents on-chain
- **erc8004-discover**: Find and monitor agents

Related Skills

doppel-erc-8004

3891
from openclaw/skills

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.

Web3 & Blockchain

ERC-8004 Register

3891
from openclaw/skills

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.

ERC-8004 Agent Discovery

3891
from openclaw/skills

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.

---

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