/byted-util-volcengine-cloud-detect
Volcengine Cloud Detect (云拨测) API integration for creating detection tasks, retrieving results, generating reports, and managing detection nodes. Use when the user wants to (1) create network detection/dialing tasks (拨测任务), (2) check task results or generate detection reports,
$ npx -y skills add bytedance/agentkit-samples --skill byted-util-volcengine-cloud-detect --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/byted-util-volcengine-cloud-detect
Context preview
The summary Claude sees to decide when to auto-load this skill.
Volcengine Cloud Detect (云拨测) API integration for creating detection tasks, retrieving results, generating reports, and managing detection nodes. Use when the user wants to (1) create network detection/dialing tasks (拨测任务), (2) check task results or generate detection reports,
SKILL.md
byted-util-volcengine-cloud-detect.SKILL.mdname: byted-util-volcengine-cloud-detect
description: Volcengine Cloud Detect (云拨测) API integration for creating detection tasks, retrieving results, generating reports, and managing detection nodes. Use when the user wants to (1) create network detection/dialing tasks (拨测任务), (2) check task results or generate detection reports, (3) list or search detection nodes (拨测节点), (4) manage existing tasks (list/stop/restart/delete). Triggers include natural language requests about website monitoring, network latency testing, HTTP detection, ping tests, DNS tests, node queries, or report generation for Volcengine cloud detect service.
Volcengine Cloud Detect
Interact with Volcengine Cloud Detect API (云拨测) through natural language. All API calls are handled via `scripts/volc_detect.py`. For detailed API parameters, read `references/api_docs.md`.
Prerequisites
Volcengine credentials are required:
- `VOLC_ACCESSKEY`: Access Key
- `VOLC_SECRETKEY`: Secret Key
Before executing any command, check whether both credentials exist in environment variables:
test -n "$VOLC_ACCESSKEY" && test -n "$VOLC_SECRETKEY"
If either value is missing, ask the user to provide the missing AK/SK, then write them to the current shell environment and persist them to the user's shell profile:
export VOLC_ACCESSKEY="USER_PROVIDED_ACCESS_KEY"
export VOLC_SECRETKEY="USER_PROVIDED_SECRET_KEY"
SHELL_PROFILE="${ZDOTDIR:-$HOME}/.zshrc"
grep -q '^export VOLC_ACCESSKEY=' "$SHELL_PROFILE" 2>/dev/null \
&& sed -i '' 's|^export VOLC_ACCESSKEY=.*|export VOLC_ACCESSKEY="USER_PROVIDED_ACCESS_KEY"|' "$SHELL_PROFILE" \
|| printf '\nexport VOLC_ACCESSKEY="USER_PROVIDED_ACCESS_KEY"\n' >> "$SHELL_PROFILE"
grep -q '^export VOLC_SECRETKEY=' "$SHELL_PROFILE" 2>/dev/null \
&& sed -i '' 's|^export VOLC_SECRETKEY=.*|export VOLC_SECRETKEY="USER_PROVIDED_SECRET_KEY"|' "$SHELL_PROFILE" \
|| printf 'export VOLC_SECRETKEY="USER_PROVIDED_SECRET_KEY"\n' >> "$SHELL_PROFILE"Never run `scripts/volc_detect.py` until both `VOLC_ACCESSKEY` and `VOLC_SECRETKEY` are available.
Default Parameters for CreateTask
When user creates a task without specifying all parameters, use these defaults:
| Parameter | Default Value | Notes | |-----------|--------------|-------| | ProjectName | `default` | Always use unless user specifies | | Type | `1` (HTTP(S)) | Task type | | Name | `{current_time}_claw_detect` | Format: YYYYMMDD_HHMMSS_claw_detect | | Address | **(required)** | Must ask user if not provided | | NodeCount | `5` | Samples per line | | IntervalSeconds | `60` | Detection frequency | | FinishTime | `current_time + 90 seconds` | 1.5 minutes after creation | | LineIdList | **(required)** | Must obtain from ListNodes |
**Task Type Mapping**: 1=HTTP(S), 2=DNS, 3=PING, 5=UDP, 6=TCP, 8=Upload, 9=Download, 11=PageElement
**Interval Options** (seconds): 60, 120, 180, 300, 600, 900, 1200, 1800, 3600, 7200, 10800, 21600, 43200, 86400
Workflow: Creating a Detection Task
1. **Collect required info**: Ask user for `Address` (target URL). If not provided, prompt for it. 2. **Determine node selection**: Before creating task, ask user about detection requirements to filter nodes:
- Target region? (e.g., mainland China, specific provinces/cities)
- ISP preference? (e.g., China Telecom, China Mobile, China Unicom)
- Node type? (IDC = data center, LastMile = end user)
3. **Fetch and filter nodes**: Run `list-nodes`, then fuzzy-search based on user requirements. 4. **Confirm LineIdList**: Show matched nodes to user and confirm selection. 5. **Create task**: Run `create-task` with all parameters including confirmed LineIdList. 6. **Return TaskId**: Present the created task ID to user.
Node Selection Conversation Guide
When user says "create a detection task for baidu.com", respond by: 1. Confirming the target address 2. Asking about geographic/ISP requirements 3. Running `list-nodes` to show available options 4. Using `fuzzy-search-nodes` to filter based on user's description
Example user requirements to node filters:
- "mainland China + Telecom" → `--is-mainland true` + search "电信"
- "Beijing IDC nodes" → search "北京 IDC"
- "Shanghai and Guangzhou Mobile" → search "上海 移动" and "广州 移动"
- "all over the country" → `--is-mainland true`, select diverse nodes
Workflow: Getting Results & Reports
1. **Get task results**: Run `get-result` with TaskId and time range (must be <= 1 hour). 2. **Generate report**: Run `generate-report` to produce summary statistics. 3. **Present findings**: Show key metrics in a concise format.
Report Format
Present reports using this structure:
## Detection Report for {TaskName} (ID: {TaskId})
**Time Range**: {start} ~ {end}
**Total Samples**: {N}
**Success Rate**: {X}%
### Latency Statistics (ms)
| Metric | Value |
|--------|-------|
| Avg | {avg} |
| Min | {min} |
| Max | {max} |
| P90 | {p90} |
### Status Code Distribution
| Code | Count |
|------|-------|
| ... | ... |
### Issues
- {N} failures from {region-isp} nodes
- Top error: {error_code} ({count} occurrences)Workflow: Managing Tasks
- **List tasks**: `list-tasks` with optional filters (--name, --address)
- **Stop task**: `stop-task --task-id ID`
- **Restart task**: `restart-task --task-id ID`
- **Delete task**: `delete-task --task-id ID` (confirm with user first)
- **Get task details**: `get-task --task-id ID`
Workflow: Node Discovery
- **List all nodes**: `list-nodes [--is-mainland true|false]`
- **Filter by type**: `list-nodes --line-types 1,2` (1=LastMile, 2=IDC)
- **Fuzzy search**: `fuzzy-search-nodes "search query"`
Script Commands Reference
All commands use `python scripts/volc_detect.py`:
# Create task
python scripts/volc_detect.py create-task \
--address "https://example.com" \
--name "task_name" \
--type 1 \
--node-count 5 \
--interval-seconds 60 \
--finish-time TIMESTAMP \
--line-ids 228,229,230 \
--http-method 1
# Get results
python scripts/volc_det
Read more
name: byted-util-volcengine-cloud-detect description: Volcengine Cloud Detect (云拨测) API integration for creating detection tasks, retrieving results, generating reports, and managing detection nodes. Use when the user wants to (1) create network detection/dialing tasks (拨测任务), (2) check task results or generate detection reports, (3) list or search detection nodes (拨测节点), (4) manage existing tasks (list/stop/restart/delete). Triggers include natural language requests about website monitoring, network latency testing, HTTP detection, ping tests, DNS tests, node queries, or report generation for Volcengine cloud detect service.
Volcengine Cloud Detect
Interact with Volcengine Cloud Detect API (云拨测) through natural language. All API calls are handled via `scripts/volc_detect.py`. For detailed API parameters, read `references/api_docs.md`.
Prerequisites
Volcengine credentials are required:
- `VOLC_ACCESSKEY`: Access Key
- `VOLC_SECRETKEY`: Secret Key
Before executing any command, check whether both credentials exist in environment variables:
test -n "$VOLC_ACCESSKEY" && test -n "$VOLC_SECRETKEY"
If either value is missing, ask the user to provide the missing AK/SK, then write them to the current shell environment and persist them to the user's shell profile:
export VOLC_ACCESSKEY="USER_PROVIDED_ACCESS_KEY"
export VOLC_SECRETKEY="USER_PROVIDED_SECRET_KEY"
SHELL_PROFILE="${ZDOTDIR:-$HOME}/.zshrc"
grep -q '^export VOLC_ACCESSKEY=' "$SHELL_PROFILE" 2>/dev/null \
&& sed -i '' 's|^export VOLC_ACCESSKEY=.*|export VOLC_ACCESSKEY="USER_PROVIDED_ACCESS_KEY"|' "$SHELL_PROFILE" \
|| printf '\nexport VOLC_ACCESSKEY="USER_PROVIDED_ACCESS_KEY"\n' >> "$SHELL_PROFILE"
grep -q '^export VOLC_SECRETKEY=' "$SHELL_PROFILE" 2>/dev/null \
&& sed -i '' 's|^export VOLC_SECRETKEY=.*|export VOLC_SECRETKEY="USER_PROVIDED_SECRET_KEY"|' "$SHELL_PROFILE" \
|| printf 'export VOLC_SECRETKEY="USER_PROVIDED_SECRET_KEY"\n' >> "$SHELL_PROFILE"Never run `scripts/volc_detect.py` until both `VOLC_ACCESSKEY` and `VOLC_SECRETKEY` are available.
Default Parameters for CreateTask
When user creates a task without specifying all parameters, use these defaults:
| Parameter | Default Value | Notes | |-----------|--------------|-------| | ProjectName | `default` | Always use unless user specifies | | Type | `1` (HTTP(S)) | Task type | | Name | `{current_time}_claw_detect` | Format: YYYYMMDD_HHMMSS_claw_detect | | Address | **(required)** | Must ask user if not provided | | NodeCount | `5` | Samples per line | | IntervalSeconds | `60` | Detection frequency | | FinishTime | `current_time + 90 seconds` | 1.5 minutes after creation | | LineIdList | **(required)** | Must obtain from ListNodes |
**Task Type Mapping**: 1=HTTP(S), 2=DNS, 3=PING, 5=UDP, 6=TCP, 8=Upload, 9=Download, 11=PageElement
**Interval Options** (seconds): 60, 120, 180, 300, 600, 900, 1200, 1800, 3600, 7200, 10800, 21600, 43200, 86400
Workflow: Creating a Detection Task
1. **Collect required info**: Ask user for `Address` (target URL). If not provided, prompt for it. 2. **Determine node selection**: Before creating task, ask user about detection requirements to filter nodes:
- Target region? (e.g., mainland China, specific provinces/cities)
- ISP preference? (e.g., China Telecom, China Mobile, China Unicom)
- Node type? (IDC = data center, LastMile = end user)
3. **Fetch and filter nodes**: Run `list-nodes`, then fuzzy-search based on user requirements. 4. **Confirm LineIdList**: Show matched nodes to user and confirm selection. 5. **Create task**: Run `create-task` with all parameters including confirmed LineIdList. 6. **Return TaskId**: Present the created task ID to user.
Node Selection Conversation Guide
When user says "create a detection task for baidu.com", respond by: 1. Confirming the target address 2. Asking about geographic/ISP requirements 3. Running `list-nodes` to show available options 4. Using `fuzzy-search-nodes` to filter based on user's description
Example user requirements to node filters:
- "mainland China + Telecom" → `--is-mainland true` + search "电信"
- "Beijing IDC nodes" → search "北京 IDC"
- "Shanghai and Guangzhou Mobile" → search "上海 移动" and "广州 移动"
- "all over the country" → `--is-mainland true`, select diverse nodes
Workflow: Getting Results & Reports
1. **Get task results**: Run `get-result` with TaskId and time range (must be <= 1 hour). 2. **Generate report**: Run `generate-report` to produce summary statistics. 3. **Present findings**: Show key metrics in a concise format.
Report Format
Present reports using this structure:
## Detection Report for {TaskName} (ID: {TaskId})
**Time Range**: {start} ~ {end}
**Total Samples**: {N}
**Success Rate**: {X}%
### Latency Statistics (ms)
| Metric | Value |
|--------|-------|
| Avg | {avg} |
| Min | {min} |
| Max | {max} |
| P90 | {p90} |
### Status Code Distribution
| Code | Count |
|------|-------|
| ... | ... |
### Issues
- {N} failures from {region-isp} nodes
- Top error: {error_code} ({count} occurrences)Workflow: Managing Tasks
- **List tasks**: `list-tasks` with optional filters (--name, --address)
- **Stop task**: `stop-task --task-id ID`
- **Restart task**: `restart-task --task-id ID`
- **Delete task**: `delete-task --task-id ID` (confirm with user first)
- **Get task details**: `get-task --task-id ID`
Workflow: Node Discovery
- **List all nodes**: `list-nodes [--is-mainland true|false]`
- **Filter by type**: `list-nodes --line-types 1,2` (1=LastMile, 2=IDC)
- **Fuzzy search**: `fuzzy-search-nodes "search query"`
Script Commands Reference
All commands use `python scripts/volc_detect.py`:
# Create task python scripts/volc_detect.py create-task \ --address "https://example.com" \ --name "task_name" \ --type 1 \ --node-count 5 \ --interval-seconds 60 \ --finish-time TIMESTAMP \ --line-ids 228,229,230 \ --http-method 1 # Get results python scripts/volc_det
欢迎来到 AgentKit 代码工坊(Samples)仓库! AgentKit 是火山引擎推出的企业级 AI Agent 开发平台,为开发者提供完整的 Agent 构建、部署和运维解决方案。平台通过标准化的开发工具链和云原生基础设施,显著降低复杂智能体应用的开发部署门槛。 本代码库包含了一系列示例和教程,帮助您理解、实现和集成 AgentKit 的各项功能到您的应用中。
Other skills on agentkit-samples.
- /code-optimization
Optimize code performance through iterative improvements (max 2 rounds). Benchmark execution time and memory usage, compare against baseline implementations, and generate detailed optimization reports. Supports C++, Python, Java, Rust, and other languages.
Open skill - /image-video-gen
根据文字描述生成视频,一个生成图片和视频的工作流技能。依赖 skills: byted-web-search, image-generate, video-generate。注意:此 workflow 没有执行脚本,只是一个描述性的文档。
Open skill - /skills-management
Manage AgentKit skills, SkillHub/skillhub, skill centers, and skill spaces. Use this skill whenever the user has a management intent for AgentKit skills, skill中心, skill 空间, skill space, or skill hub, including listing, inspecting, downloading, fetching, uploading, publishing,
Open skill - /tos-file-access
Upload files or directories to TOS-compatible object storage for Volcano Engine or BytePlus and download files from URLs. Use this skill when (1) Upload Agent-generated files or directories for sharing, (2) Download files from URLs before Agent processing.
Open skill - /veadk-go-skills
根据用户的功能需求,完成与 VeADK-Go 相关的功能; 包括:直接根据需求生成 Agent;将Enio Agent转换为VeADK-Go Agent。
Open skill - /veadk-skills
根据用户的功能需求,完成与 VeADK 相关的功能。
Open skill

