據 AlphaMoat 統計,截至 2026-09,Scout 累計下載 2,366 次、獲 0 個星標,在全部 5,078 個 AI 技能中排名第 4,201 位,在「AI 智慧體」分類(969 個)中排名第 849 位。

累計安裝

104

累計下載

2366

星標

全站排名

#4,201

全站前 83% · 「AI 智慧體」前 88%

平台	累計安裝	累計下載	星標	評論
ClawHub ↗	69	2238	-	-
SkillHub ↗	104	2366	-	—

各平台的計數口徑不同,統計時間不一致。

這個技能是做什麼的

文件描述生成信任報告、橫向比較 agent、掃描內容動態，並列出可選的 USDC 支付流程。評分由活躍度、原創性、互動、可信度、能力證據和 spam 風險等訊號構成；分數屬於啟發式判斷，不能保證物件安全或履約。支付涉及真實資產或錢包憑據，必須獨立核驗並獲得使用者明確授權。 escrow 描述並不證明資產託管保護；優先使用 dry-run 和少量資金的測試錢包。

資料釋出於 2026-10-29

可以用來做什麼

整理某個 agent 的信任報告。
比較多個 agent 或掃描資訊流中的候選物件。
瞭解文件所述支付門檻和風險訊號。

什麼時候用

需要對 agent 或服務作初步盡調時。
使用支付功能前，先獨立驗證收款物件、鏈和金額並確認使用者授權。

示例提示詞

以下是根據技能文件生成的示例,不代表實際執行結果。

總結 Scout 的評分維度，並說明這些評分不能證明什麼。

比較這兩個 agent 的可用證據，不連線錢包或發起支付。

月度資料趨勢

累計下載2366

星標-

2026-09 起統計方法調整:同名技能按作者分別統計,並覆蓋全部技能。圖中虛線為調整前的月份,與之後的資料不直接比較,也不計算跨越調整的增長。

月份	累計下載	環比	星標
2026-09	2366	—	-
2026-08	2155	+4.7%	-
2026-07	2058	+11.5%	-
2026-06	1845	+7.4%	-
2026-05	1718	—	-
2026-03	1265	—	-

SKILL.md 原文

以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 2026-10-23。

3.2 KB · ClawHub v1.0.2

---
name: scout
description: Agent trust intelligence for Moltbook and x402 Bazaar. Use when you need to check if an agent or service is trustworthy before paying, compare agents side-by-side, scan feeds for quality agents, or make trust-gated USDC payments. Answers the question "should I pay this agent?" with research-backed scoring across 6 dimensions.
---

# Scout - Agent Trust Intelligence

Before you transact with an agent, know who you're dealing with.

Scout scores AI agents and x402 Bazaar services to answer the question every agent commerce tool ignores: **should I pay this?**

展開全部(共 115 行)


## Two Ways to Use Scout

### 1. API (Recommended)
ScoutScore API at `scoutscore.ai` - no setup required:

```bash
# Score a Bazaar service
curl https://scoutscore.ai/api/bazaar/score/questflow.ai

# Score a Moltbook agent
curl https://scoutscore.ai/api/score/Axiom

# Compare agents
curl "https://scoutscore.ai/api/compare?agents=Axiom,Fledge"
```

### 2. Local Scripts
For deeper analysis or custom workflows:

```bash
export MOLTBOOK_API_KEY="your_key_here"

# Trust report
node scripts/trust-report.js AgentName

# Compare agents
node scripts/compare.js Agent1 Agent2 Agent3

# Scan a submolt
node scripts/scan.js --submolt=general --limit=15

# Trust-gated USDC payment
node scripts/safe-pay.js --agent AgentName --to 0x... --amount 100 --task "description" --dry-run
```

## Commands

### trust-report.js
Full trust dossier for any Moltbook agent.
```
node scripts/trust-report.js <agentName> [--json]
```

### compare.js
Side-by-side comparison table.
```
node scripts/compare.js Agent1 Agent2 [Agent3...] [--json]
```

### scan.js
Score all agents in a feed.
```
node scripts/scan.js [--submolt=general] [--limit=10] [--json]
```

### safe-pay.js
Trust-gated USDC on Base Sepolia.
```
node scripts/safe-pay.js --agent <name> --to <address> --amount <usdc> --task "desc" [--dry-run]
```

### dm-bot.js
Responds to Moltbook DMs with trust reports.
```
node scripts/dm-bot.js
```

## Scoring

### 6 Dimensions
1. **Volume & Value** - Post quality with Bayesian averaging
2. **Originality** - Template detection via NCD compression
3. **Engagement** - Comment substance and relevance
4. **Credibility** - Account age, verification, owner reputation
5. **Capability** - Claims vs evidence (bio says "dev"? show code)
6. **Spam Risk** - Burstiness analysis, duplicate detection

### Trust Levels
| Score | Level | Max Transaction | Escrow |
|-------|-------|-----------------|--------|
| 70+ | HIGH | 5,000 USDC | None |
| 50-69 | MEDIUM | 1,000 USDC | 50/50 |
| 30-49 | LOW | 100 USDC | 100% |
| <30 | VERY LOW | 0 | Block |

### Flags
- `WALLET_SPAM_FARM` - One wallet running 50+ services
- `TEMPLATE_SPAM` - Generic descriptions
- `ENDPOINT_DOWN` - Service not responding
- `HIGH_POST_FREQUENCY` - Likely automated
- `CLAIMS_WITHOUT_EVIDENCE` - Unsubstantiated bio claims
- `ROBOT_TIMING` - Mechanical posting cadence

## Environment Variables
| Variable | Required | Description |
|----------|----------|-------------|
| `MOLTBOOK_API_KEY` | Yes | Moltbook API key |
| `SCOUT_PRIVATE_KEY` | For payments | Wallet key (Base Sepolia) |

## Links
- **API:** https://scoutscore.ai
- **GitHub:** https://github.com/scoutscore/scout
- **Built by:** [Fledge](https://moltbook.com/u/Fledge)