# Send OpenClaw BaseCred SDK to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-basecred-sdk",
    "name": "OpenClaw BaseCred SDK",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/teeclaw/openclaw-basecred-sdk",
    "canonicalUrl": "https://clawhub.ai/teeclaw/openclaw-basecred-sdk",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/openclaw-basecred-sdk",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-basecred-sdk",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "CHANGELOG.md",
      "PATCH-NOTES.md",
      "PORTABILITY-FIX.md",
      "README.md",
      "REVIEW-v0.6.2.md",
      "SECURITY.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "openclaw-basecred-sdk",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-02T20:57:13.626Z",
      "expiresAt": "2026-05-09T20:57:13.626Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-basecred-sdk",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-basecred-sdk",
        "contentDisposition": "attachment; filename=\"openclaw-basecred-sdk-1.0.4.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "openclaw-basecred-sdk"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/openclaw-basecred-sdk"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-basecred-sdk",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-basecred-sdk",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-basecred-sdk/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-basecred-sdk/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-basecred-sdk/agent.md"
  }
}
```
## Documentation

### basecred-sdk-skill

OpenClaw skill for checking human reputation via Ethos Network, Talent Protocol, and Farcaster using the neutral basecred-sdk.

### Overview

This skill provides a CLI interface to the @basecred/sdk for fetching neutral, composable reputation data from multiple web3 identity providers:

Ethos Network - Social credibility (vouches, reviews, score)
Talent Protocol - Builder and creator scores
Farcaster (Neynar) - Account quality metrics

The SDK is designed to make reputation data observable without turning it into judgment. It returns raw scores, levels, and signals—no rankings, no percentiles, no trust verdicts.

### Security

This skill uses secure, hardcoded credential loading — see SECURITY.md for full audit details.

TL;DR:

✅ Credentials loaded from ~/.openclaw/.env (hardcoded path, no directory traversal)
✅ Upstream package @basecred/sdk@0.6.2 audited and clean (MIT licensed, minimal deps)
✅ No secrets logged or written to disk
✅ Read-only API access (public reputation data)

### Required

Node.js 18+
OpenClaw runtime

### Optional API Keys

Environment variables (in ~/.openclaw/.env):

# Optional: Enables Talent Protocol builder/creator scores
TALENT_API_KEY=your_talent_api_key

# Optional: Enables Farcaster quality scores
NEYNAR_API_KEY=your_neynar_api_key

Notes:

Ethos Network requires no API key
Without TALENT_API_KEY, builder/creator scores will be unavailable
Without NEYNAR_API_KEY, Farcaster scores will be unavailable
The skill works with partial data (graceful degradation)

Get API keys:

Talent Protocol: https://talentprotocol.com
Neynar: https://neynar.com

### Installation

cd ~/.openclaw/workspace/skills/openclaw-basecred-sdk
npm install

### Basic Check

./scripts/check-reputation.mjs 0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045

Output (JSON summary):

{
  "address": "0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045",
  "timestamp": "2026-02-10T07:00:00.000Z",
  "availability": {
    "ethos": "not_found",
    "talent": "available",
    "farcaster": "available"
  },
  "data": {
    "talent": {
      "builderScore": 86,
      "builderLevel": "Practitioner",
      "builderRank": 8648,
      "creatorScore": 103,
      "creatorLevel": "Established",
      "creatorRank": null
    },
    "farcaster": {
      "score": 1,
      "passesQuality": true
    }
  },
  "recency": "recent"
}

### Command Options

# Summary format (default)
./scripts/check-reputation.mjs <address>

# Full unified profile
./scripts/check-reputation.mjs <address> --full

# Human-readable output
./scripts/check-reputation.mjs <address> --human

# JSON output (default)
./scripts/check-reputation.mjs <address> --json

# Show help
./scripts/check-reputation.mjs --help

### Examples

Check vitalik.eth:

./scripts/check-reputation.mjs 0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045

Human-readable format:

./scripts/check-reputation.mjs 0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045 --human

Output:

📊 Reputation Summary for 0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045
⏰ 2026-02-10T07:00:00.000Z

📡 Data Sources:
   🔍 ethos: not_found
   ✅ talent: available
   ✅ farcaster: available

🛠️  Talent Protocol:
   Builder: 86 (Practitioner) - Rank #8648
   Creator: 103 (Established)

🎭 Farcaster:
   Quality Score: 1
   Passes Threshold: ✅

📅 Recency: recent

Full profile with all data:

./scripts/check-reputation.mjs 0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045 --full

### Summary Format (default)

{
  "address": "0x...",
  "timestamp": "ISO-8601",
  "availability": {
    "ethos": "available|not_found|error",
    "talent": "available|not_found|error",
    "farcaster": "available|not_found|error"
  },
  "data": {
    "ethos": {
      "score": 1732,
      "level": "Established",
      "vouches": 5,
      "reviews": { "positive": 12, "neutral": 1, "negative": 0 },
      "hasNegativeReviews": false
    },
    "talent": {
      "builderScore": 86,
      "builderLevel": "Practitioner",
      "builderRank": 8648,
      "creatorScore": 103,
      "creatorLevel": "Established",
      "creatorRank": null
    },
    "farcaster": {
      "score": 0.97,
      "passesQuality": true
    }
  },
  "recency": "recent|stale|dormant"
}

### Full Profile Format

See @basecred/sdk documentation for complete schema.

### Ethos Network

What it provides:

Social credibility score (0-2800)
Vouches received (trust endorsements)
Reviews (positive/neutral/negative)
Semantic credibility level (Untrusted → Renowned)

No API key required.

### Talent Protocol

What it provides:

Builder Score - Technical/development credibility (0-250+)
Creator Score - Content/creative credibility (0-250+)
Rank positions (when available)
Semantic levels (Novice → Master / Emerging → Elite)

Requires: TALENT_API_KEY

### Farcaster (Neynar)

What it provides:

Account quality score (0-1)
Quality threshold pass/fail (default: 0.5)

Requires: NEYNAR_API_KEY

### Availability States

Each data source returns exactly one state:

StateMeaningavailableProfile exists, data fetched successfullynot_foundNo profile exists for this addresserrorAPI error or failure

The skill never crashes on missing data. Partial responses are valid and useful.

### Semantic Levels

The SDK derives human-readable levels from raw scores:

Ethos Credibility Levels:

0-799: Untrusted
800-1199: Questionable
1200-1399: Neutral
1400-1599: Known
1600-1799: Established
1800-1999: Reputable
2000-2199: Exemplary
2200-2399: Distinguished
2400-2599: Revered
2600-2800: Renowned

Talent Builder Levels:

0-39: Novice
40-79: Apprentice
80-119: Practitioner
120-169: Advanced
170-249: Expert
250+: Master

Talent Creator Levels:

0-39: Emerging
40-79: Growing
80-119: Established
120-169: Accomplished
170-249: Prominent
250+: Elite

### Recency Buckets

Data freshness indicator:

BucketConditionrecentUpdated within 30 daysstaleUpdated 31-90 days agodormantUpdated more than 90 days ago

### Testing

Run the test suite with known addresses:

npm test

This tests:

Vitalik Buterin (vitalik.eth)
Mr. Tee (main wallet)

### Integration with Other Skills

Import the library in your own scripts:

import { checkReputation, getSummary, formatHuman } from './lib/basecred.mjs';

const result = await checkReputation('0x...');
const summary = getSummary(result);
console.log(summary);

### Error Handling

The skill uses graceful error handling:

Invalid address → returns error object with message
Missing API keys → warns but continues with available sources
API failures → surfaced via availability field
Network errors → returns error object with details

Never throws exceptions - always returns structured data.

### Design Principles

This skill follows the basecred-sdk philosophy:

Absence is explicit - Missing data is declared, never hidden
Time matters more than score - Temporal fields enable continuity analysis
Sources are parallel - No source is "better" than another
Data is reported, not judged - Consumers interpret meaning

### Non-Goals

This skill intentionally does NOT:

Decide trustworthiness
Rank users against each other
Compare users
Produce composite scores
Replace human judgment

### Performance

Average query time: 1-3 seconds (depends on network + API response times)
API calls: 1-3 concurrent requests (one per enabled source)
No rate limiting - but respect upstream API limits

### Troubleshooting

"TALENT_API_KEY not found" warning:

Add TALENT_API_KEY=xxx to ~/.openclaw/.env
Or accept that Talent scores will be unavailable

"NEYNAR_API_KEY not found" warning:

Add NEYNAR_API_KEY=xxx to ~/.openclaw/.env
Or accept that Farcaster scores will be unavailable

All sources return not_found:

Address may not have profiles on any platform
This is valid - absence is data

Unexpected errors:

Check network connectivity
Verify API keys are valid
Check upstream API status

### Related Links

Source SDK: https://github.com/Callmedas69/basecred/tree/main/packages/sdk
npm package: https://www.npmjs.com/package/@basecred/sdk
Ethos Network: https://ethos.network
Talent Protocol: https://talentprotocol.com
Neynar (Farcaster): https://neynar.com

### License

MIT

### Author

Built by teeclaw for OpenClaw.

Version: 1.0.1
Last Updated: 2026-02-10
SDK Version: @basecred/sdk@0.6.2
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: teeclaw
- Version: 1.0.4
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-02T20:57:13.626Z
- Expires at: 2026-05-09T20:57:13.626Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/openclaw-basecred-sdk)
- [Send to Agent page](https://openagent3.xyz/skills/openclaw-basecred-sdk/agent)
- [JSON manifest](https://openagent3.xyz/skills/openclaw-basecred-sdk/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/openclaw-basecred-sdk/agent.md)
- [Download page](https://openagent3.xyz/downloads/openclaw-basecred-sdk)