← 返回 Skills 市场
BlackClaw
作者
bilalmotiwala
· GitHub ↗
· v1.0.0
1825
总下载
5
收藏
7
当前安装
1
版本数
在 OpenClaw 中安装
/install blackswan
功能描述
Real-time crypto risk intelligence; before and as things break. Two tools: Flare (15-min precursor detection, immediate alarms) and Core (60-min state synthesis, context assessment). Free access to the last analysis. No API key required. Upgrade to x402 for custom analysis.
使用说明 (SKILL.md)
BlackSwan Risk Intelligence
BlackSwan monitors crypto markets 24/7 and produces two risk assessments:
- Flare — Precursor detection from a 15-minute signal window. Use for immediate, alarm-bell risk checks. Before the news breaks.
- Core — State synthesis from a 60-minute signal window. Use for market context and risk assessment. As the news breaks.
When to use each tool
| Question | Tool |
|---|---|
| "Is something happening right now?" | Flare |
| "What's the overall market risk environment?" | Core |
| "Should I be worried about sudden moves?" | Flare |
| "Give me a full risk briefing" | Both (Flare first, then Core) |
Base URL
https://mcp.blackswan.wtf
Endpoints
GET /api/flare
Returns the latest Flare precursor detection assessment.
curl -s https://mcp.blackswan.wtf/api/flare
Response fields:
| Field | Description |
|---|---|
agent |
Always "flare" |
data_age |
Human-readable age of the data (e.g. "12 minutes ago") |
status |
"clear" or "alert" |
severity |
"none", "low", "medium", "high", or "critical" |
checked_at |
ISO 8601 timestamp of the assessment |
assessment |
Natural language risk assessment |
signals |
Array of detected signals, each with type, source, and detail |
GET /api/core
Returns the latest Core state synthesis assessment.
curl -s https://mcp.blackswan.wtf/api/core
Response fields:
| Field | Description |
|---|---|
agent |
Always "core" |
data_age |
Human-readable age of the data (e.g. "1 hour ago") |
timestamp |
ISO 8601 timestamp of the assessment |
environment |
"stable", "elevated", "stressed", or "crisis" |
assessment |
Natural language risk assessment |
key_factors |
Array of strings describing the main risk factors |
sources_used |
Array of data source names used in the assessment |
data_freshness |
Description of how fresh the underlying data is |
Interpreting severity levels (Flare)
| Severity | Meaning |
|---|---|
none |
No precursors detected, markets quiet |
low |
Minor signals, worth noting but not actionable |
medium |
Notable signals, warrants attention |
high |
Strong precursors detected, elevated risk of sudden moves |
critical |
Extreme signals, immediate risk of major market event |
Interpreting environment levels (Core)
| Environment | Meaning |
|---|---|
stable |
Normal market conditions, low systemic risk |
elevated |
Above-normal risk, some stress indicators present |
stressed |
Significant stress across multiple indicators |
crisis |
Severe market stress, active dislocation or contagion |
Error handling
| HTTP Status | Meaning |
|---|---|
200 |
Success, response contains full assessment |
502 |
Agent output failed validation — format may have changed |
503 |
No recent agent runs — system may be starting up |
500 |
Unexpected server error |
On non-200 responses, the body is {"error": "..."} with a human-readable message.
Complete risk check pattern
To get a full picture, call both endpoints:
curl -s https://mcp.blackswan.wtf/api/flare
curl -s https://mcp.blackswan.wtf/api/core
Present Flare results first (immediate risks), then Core (broader context).
安全使用建议
This skill appears to be a simple client for the BlackSwan risk API and does not request secrets, but there are a few red flags to check before installing: 1) Confirm the correct project name — the registry lists 'BlackClaw' while the SKILL.md and homepage reference 'BlackSwan' (possible packaging mistake or copy/paste). 2) Verify the external endpoint (https://mcp.blackswan.wtf) and the GitHub repo (https://github.com/blackswanwtf/blackswan-mcp) yourself — ensure the service is reputable and you’re comfortable the agent calling it. 3) Ensure curl is available or acceptable to be used at runtime (SKILL.md notes it as a required binary). If you need stronger assurance, ask the publisher for the canonical repository link and a brief explanation of the naming mismatch, or run the skill in an isolated environment/network before granting it access to sensitive workflows.
功能分析
Type: OpenClaw Skill
Name: blackswan
Version: 1.0.0
The skill bundle is benign. It provides instructions for an AI agent to fetch crypto risk intelligence data from `https://mcp.blackswan.wtf` using `curl`. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts against the agent. The `SKILL.md` clearly defines the purpose and the `curl` commands are standard GET requests to a specific, stated endpoint, without any high-risk flags.
能力评估
Purpose & Capability
The SKILL.md describes a simple network client for a crypto risk API (Flare/Core), which is coherent with the stated purpose. However, the packaged skill name in the registry is 'BlackClaw' while the SKILL.md and homepage reference 'BlackSwan' (blackswan-mcp). Also the SKILL.md metadata requires the 'curl' binary but the registry metadata lists no required binaries. These inconsistencies suggest sloppy packaging or a copy/paste error and should be clarified before trusting the skill.
Instruction Scope
Runtime instructions are narrowly scoped: they direct the agent to call two public HTTP endpoints on https://mcp.blackswan.wtf and present results. The instructions do not ask the agent to read local files, access environment variables, or contact other external endpoints. The main risk is that the agent will send requests to an external, non-mainstream domain — expected for this type of skill but worth verifying the service's trustworthiness.
Install Mechanism
There is no install spec and no code files (instruction-only), which limits on-disk risk. This is the lowest-risk install pattern. Note: SKILL.md lists a runtime dependency on curl (metadata: requires bins: ["curl"]) whereas the registry metadata earlier said no required binaries — an internal inconsistency to confirm.
Credentials
The skill requests no environment variables, no credentials, and no config paths. That is proportionate for a read-only public API client and reduces risk of secret exfiltration.
Persistence & Privilege
The skill is not marked always:true and is user-invocable (normal). It does not request persistent privileges or system-wide configuration changes.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install blackswan - 安装完成后，直接呼叫该 Skill 的名称或使用
/blackswan触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of BlackSwan (now blackclaw) skill for real-time crypto risk intelligence.
- Provides two main tools: Flare (15-min precursor detection) and Core (60-min market context analysis).
- No API key is required for the latest analysis; upgrade available for custom requests.
- Detailed API endpoints with sample commands and response formats.
- Clear documentation on interpreting risk levels and error handling.
元数据
常见问题
BlackClaw 是什么？
Real-time crypto risk intelligence; before and as things break. Two tools: Flare (15-min precursor detection, immediate alarms) and Core (60-min state synthesis, context assessment). Free access to the last analysis. No API key required. Upgrade to x402 for custom analysis. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1825 次。
如何安装 BlackClaw？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install blackswan」即可一键安装，无需额外配置。
BlackClaw 是免费的吗？
是的，BlackClaw 完全免费（开源免费），可自由下载、安装和使用。
BlackClaw 支持哪些平台？
BlackClaw 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 BlackClaw？
由 bilalmotiwala（@bilalmotiwala）开发并维护，当前版本 v1.0.0。
推荐 Skills