数据测试
- 作者仓库星标 1,423
- 许可证 Apache-2.0
- 作者更新于 实时读取
- 作者仓库 video-search-and-summarization
- 领域
- AI 智能
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 94 / 100 · 已通过审计
- 作者 / 版本 / 许可
- @NVIDIA-AI-Blueprints · Apache-2.0
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- 未声明（默认跨平台）
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- Shell 执行
- 允许写入 / 修改
- 网络行为
- 允许外网请求
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。
需要注意： 未限定 allowed-tools，默认拥有全部工具权限。
---
name: video-analytics
description: Query video analytics data and metrics from Elastic search via the VA-MCP server (port 9901). Th…
category: AI 智能
runtime: 无特殊运行时
---
# video-analytics 输出预览
## PART A: 任务判断
- 适用问题：提示词、Agent 工作流、模型评估或自动化推理。
- 输入要求：目标材料、限制条件、期望输出和验收方式。
- 证据边界：围绕“Deployment prerequisite / REQUIRED: Two-Step Pattern (copy this exactly) / Tool Reference”读取原文规则，不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断：确认你的需求是否属于提示词、Agent 工作流、模型评估或自动化推理，并标出输入、限制和预期结果。
- **02** 执行计划：优先按“Deployment prerequisite / REQUIRED: Two-Step Pattern (copy this exactly) / Tool Reference”拆成步骤，说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果：给出可复制的命令、文件改动、检查清单或内容草稿，并说明如何继续迭代。
- **04** 风险边界：结合 读取文件、执行终端命令、写入/修改文件、会按任务需要访问外部网络、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、执行终端命令、写入/修改文件；会按任务需要访问外部网络；通常不需要额外 API Key。
- 先小样例验证，再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。原文出现了 `/deploy` 这类斜杠命令；如果你的 Agent 支持命令触发，优先用命令开场，再补充目标和边界。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是：读取文件、执行终端命令、写入/修改文件。
先用一个小任务确认它会围绕“Deployment prerequisite / REQUIRED: Two-Step Pattern (copy this exactly) / Tool Reference”工作；涉及文件或命令时，先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作；如果输出泛泛而谈，就补充输入、边界和验收标准后重跑。
---
name: video-analytics
description: Query video analytics data and metrics from Elastic search via the VA-MCP server (port 9901). Th…
category: AI 智能
source: NVIDIA-AI-Blueprints/video-search-and-summarization
---
# video-analytics
## 什么时候使用
- 把 AI / Agent方向的常用动作沉淀成 Agent 可调用的技能 适合处理AI Agent、提示词、模型评估与自动化推理，核心价值是把输入、判断、执行、验证和交付边界固定下来，避免 Agent 泛泛回答。 把任务拆成可执行、可检查…
- 面向提示词、Agent 工作流、模型评估或自动化推理，优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Deployment prerequisite / REQUIRED: Two-Step Pattern (copy this exactly) / Tool Reference」组织步骤，不把推断写成作者事实。
- 读取文件、执行终端命令、写入/修改文件；会按任务需要访问外部网络；通常不需要额外 API Key。
- 先跑小样例，确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown，不编造命令、平台或依赖。作者原文负责流程事实；仓库文件负责来源和命令；流狐只补充适用场景、限制和质量判断。
skill "video-analytics" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Deployment prerequisite / REQUIRED: Two-Step Pattern (copy this exactly) / Tool Reference
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、执行终端命令、写入/修改文件 | 会按任务需要访问外部网络
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
}Video Analytics (VA-MCP)
Queries incidents, alerts, and metrics stored in Elasticsearch via MCP JSON-RPC at port 9901.
ALWAYS run the commands below yourself and relay results to the user. Do NOT guess or describe — actually execute and report back.
Deployment prerequisite
This skill reads from the Elasticsearch/VA-MCP stack brought up by the VSS alerts profile (either verification or real-time mode). Before any query:
Probe the VA-MCP endpoint:
curl -sf --max-time 5 "http://${HOST_IP}:9901/mcp" >/dev/null 2>&1 || \ curl -sf --max-time 5 "http://${HOST_IP}:9901/" >/dev/nullIf the probe fails, ask the user:
"The VSS
alertsprofile isn't running on$HOST_IP(VA-MCP unreachable). Which mode should I deploy —verification(CV) orreal-time(VLM)?"- Answer → hand off to the
/deployskill with-p alerts -m <mode>. Return here once it succeeds. - If the user declines → stop. No incidents/alerts/metrics to query without the alerts stack up.
(If your caller has granted explicit pre-authorization to deploy autonomously — e.g. the request says "pre-authorized to deploy prerequisites", or you are running in a non-interactive evaluation harness with that permission — skip the confirmation and invoke
/deploydirectly. Default the mode toverificationunless the request specifies otherwise.)- Answer → hand off to the
If the probe passes, proceed.
REQUIRED: Two-Step Pattern (copy this exactly)
Every query requires two shell commands run in sequence:
# Step 1: initialize — get session ID from response HEADER
SESSION_ID=$(curl -si -X POST http://localhost:9901/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"cli","version":"1.0"}},"id":0}' \
| grep -i "mcp-session-id" | awk '{print $2}' | tr -d '\r')
# Step 2: call the tool using the session ID in the header
curl -s -X POST http://localhost:9901/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-H "mcp-session-id: $SESSION_ID" \
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"video_analytics__get_incidents","arguments":{"max_count":10}},"id":1}' \
| grep '^data:' | sed 's/^data: //' | jq -r '.result.content[0].text'The session ID comes from the response header
mcp-session-id, not the body. Skipping Step 1 always results inBad Request: Missing session ID.
Tool Reference
Replace the -d payload in Step 2 with any of the following.
video_analytics__get_incidents
| Parameter | Type | Description |
|---|---|---|
source |
string | Sensor ID or place name (optional) |
source_type |
string | sensor or place |
start_time |
string | ISO 8601: YYYY-MM-DDTHH:MM:SS.sssZ |
end_time |
string | ISO 8601 |
max_count |
int | Max results (default: 10) |
includes |
list | Extra fields: objectIds, info |
vlm_verdict |
string | confirmed, rejected, or unverified |
# Recent incidents (all sensors)
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"video_analytics__get_incidents","arguments":{"max_count":10}},"id":1}'
# For a specific sensor
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"video_analytics__get_incidents","arguments":{"source":"<sensor-id>","source_type":"sensor","max_count":20}},"id":1}'
# Confirmed (VLM-verified) only
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"video_analytics__get_incidents","arguments":{"vlm_verdict":"confirmed","max_count":10}},"id":1}'video_analytics__get_incident
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"video_analytics__get_incident","arguments":{"id":"<incident-id>","includes":["objectIds","info"]}},"id":1}'video_analytics__get_sensor_ids
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"video_analytics__get_sensor_ids","arguments":{}},"id":1}'video_analytics__get_places
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"video_analytics__get_places","arguments":{}},"id":1}'video_analytics__get_fov_histogram
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"video_analytics__get_fov_histogram","arguments":{"source":"<sensor-id>","source_type":"sensor","start_time":"<ISO>","end_time":"<ISO>","object_type":"Person","bucket_count":10}},"id":1}'video_analytics__analyze
analysis_type: max_min_incidents, average_speed, avg_num_people, avg_num_vehicles
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"video_analytics__analyze","arguments":{"source":"<sensor-id>","source_type":"sensor","start_time":"<ISO>","end_time":"<ISO>","analysis_type":"avg_num_people"}},"id":1}'vst_sensor_list
-d '{"jsonrpc":"2.0","method":"tools/call","params":{"name":"vst_sensor_list","arguments":{}},"id":1}'
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核