bytedance/agentkit-samples is a collection of examples and tutorials for Volcengine AgentKit, an AI-agent development platform for building, deploying, and operating agent applications. Developers use the samples to learn agent creation, multi-agent collaboration, memory, retrieval, MCP integrations, media generation, customer service, and other workflows. The catalogue skills provide agent workflows based on these examples.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add bytedance/agentkit-samples --skill byted-emr-skillsgit clone --depth 1 https://github.com/bytedance/agentkit-samplesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bytedance/agentkit-samples/byted-emr-skills)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-emr-skills"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-emr-skills/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-emr-skills"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-emr-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00183 | $0.04918 |
| Opus 5 | $0.00092 | $0.02459 |
| Sonnet 5 | $0.00037 | $0.00984 |
| Haiku 4.5 | $0.00018 | $0.00492 |
Grade A, and why
byted-emr-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EMR Skills
- 何时使用(触发短语)
- 当用户提出以下任何类似需求时,立即调用该技能:
“查询EMR集群的服务列表” “重启Spark服务” “获取 EMR 作业日志” “查看EMR serverless队列列表” “查看EMR serverless队列详情” “使用 EMR Serverless 运行任务” “在 EMR 上提交一个 Spark 作业” “帮我诊断一下失败的 Spark 作业” “分析一下EMR作业失败的原因” - 任何涉及 EMR Serverless 作业/队列/计算组/监控/日志/诊断 的操作询问
功能清单
- EMR Serverless
- 队列:开通公共队列、队列列表查询、队列详情查询、队列下计算组列表查询
- 队列权限:查询队列授权主体、为用户授予/修改队列权限
- 计算组:创建/修改/启动/停止/删除、查询可选规格与镜像、外部元数据连通性测试
- 作业模板:创建/更新/查询详情/列表查询/运行
- 作业实例:提交(SparkSQL/PrestoSQL/SparkJar/PySpark/RayJob)、查询状态与详情、取消、列表查询、重跑、结果分批拉取
- EMR Agent
- 交互式诊断与知识问答
- 会话与报告管理
- EMR on ECS
- 集群:查看集群详情、集群列表、更新集群属性
- 节点组:列出节点组、更新节点组属性、节点列表、扩容节点组磁盘、更新节点组ECS规格
- 服务:列出应用、组件列表、组件实例列表、执行应用操作
- 服务配置:配置文件列表、配置文件详情、配置项列表、配置项修改历史列表、修改配置项
- 操作审计:操作列表查询
- 用户:创建集群用户、修改已创建用户信息、获取集群用户列表、获取用户详情、更新集群用户密码
- 用户组:获取集群用户组列表、集群用户组详情、创建集群用户组、更新集群用户组
- EMR on VKE
- 集群:查看集群列表、集群详情
- 服务(应用):查看服务列表、服务组件实例、重启服务或组件实例、查看服务配置参数、修改服务配置参数
- 操作日志:查看操作日志列表、操作日志详情
Initial Setup
环境变量配置
方式一:使用ARK_SKILL_API环境变量(推荐)
如果已配置以下环境变量,则无需配置火山引擎API凭证:
export ARK_SKILL_API_BASE="your-api-base-url"
export ARK_SKILL_API_KEY="your-api-key"
方式二:使用火山引擎API凭证
如果未配置ARK_SKILL_API环境变量,且需要使用serverless sdk能力或出现sdk报错,则需要配置火山引擎API凭证:
export VOLCENGINE_AK="your-access-key"
export VOLCENGINE_SK="your-secret-key"
export VOLCENGINE_REGION="cn-beijing"
- 安装emr serverless sdk,调用scripts/bin/install_serverless_sdk.sh安装
How to manage EMR
1. EMR on Serverless管理
- 针对全托管的 Serverless 形态,主要面向作业提交和资源队列管理。
- OpenAPI 推荐使用命令行工具:
python ./scripts/on_serverless/emr_serverless_cli.py --action <Action> --method <GET|POST> --query '<json>' --body '<json>'- Region 默认从环境变量
VOLCENGINE_REGION读取(默认 cn-beijing) - Service/Version 会根据 Action 自动推断(需要时也可显式传
--service/--version) - 自定义 endpoint(如 LAS)可额外传
--endpoint las.cn-beijing.volcengineapi.com
- Region 默认从环境变量
- 作业提交推荐使用命令行工具:
python ./scripts/on_serverless/emr_serverless_submit_cli.py <sql|jar|pyspark|ray> ...
如何管理资源队列
- 支持的功能列表
- 队列列表:查看所有资源队列及其配置(如最大资源、当前使用量), 必须使用OpenAPI
ListTagQueue查询队列列表。 - 队列详情:获取队列的详细信息,包括绑定的网络、存储等, 必须使用OpenAPI
GetQueue查询队列详情。 - 创建队列:一键创建公共队列, 必须使用OpenAPI
CreateQueueSilently或CreateOrderInOneStep创建队列。 - 队列计算组列表:获取指定队列下的计算组(Queue Component)列表与详情,必须使用OpenAPI
ListQueueComponent查询队列计算组列表。
- 队列列表:查看所有资源队列及其配置(如最大资源、当前使用量), 必须使用OpenAPI
- 所有的队列功能操作详情,请严格按照
references/emr_serverless/queue/emr_serverless_queue_guide.md中的说明进行操作。
What ships with it
37 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/libs/python_serverless-1.0.3.4.1-py3-none-any.whl 34 KB
- LICENSE 9.9 KB
- references/emr_agent/emr_agent_guide.md 6.1 KB
- references/emr_on_ecs/application_config/emr_on_ecs_application_config_guide.md 21 KB
- references/emr_on_ecs/application/emr_on_ecs_application_guide.md 15 KB
- references/emr_on_ecs/cluster_group/emr_on_ecs_cluster_group_guide.md 17 KB
- references/emr_on_ecs/cluster/emr_on_ecs_cluster_guide.md 12 KB
- references/emr_on_ecs/operation/emr_on_ecs_operation_guide.md 4.8 KB
- references/emr_on_ecs/user_group/emr_on_ecs_user_group_guide.md 7.9 KB
- references/emr_on_ecs/user/emr_on_ecs_user_guide.md 11 KB
- references/emr_on_vke/emr_on_vke_guide.md 7.8 KB
- references/emr_serverless/compute/emr_serverless_compute_guide.md 17 KB
- references/emr_serverless/job_instance/emr_serverless_job_instance_guide.md 11 KB
- references/emr_serverless/job/emr_serverless_job_guide.md 23 KB
- references/emr_serverless/operation_audit/emr_serverless_operation_audit_guide.md 6.0 KB
- references/emr_serverless/privilege/emr_serverless_privilege_guide.md 11 KB
- references/emr_serverless/queue/emr_serverless_queue_guide.md 19 KB
- scripts/__init__.py 0 B runs code
- scripts/bin/install_serverless_sdk.sh 183 B runs code
- scripts/client/__init__.py 0 B runs code
- scripts/client/skill_proxy_client.py 3.1 KB runs code
- scripts/client/tmp_file_manager.py 1.6 KB runs code
- scripts/client/volc_open_api_client.py 6.4 KB runs code
- scripts/config/__init__.py 426 B runs code
- scripts/config/config.py 9.1 KB runs code
- scripts/emr_agent/__init__.py 0 B runs code
- scripts/emr_agent/emr_agent_manager.py 2.6 KB runs code
- scripts/emr_agent/expert.py 7.6 KB runs code
- scripts/on_ecs/__init__.py 0 B runs code
- scripts/on_ecs/emr_on_ecs_cli.py 2.5 KB runs code
- scripts/on_ecs/emr_on_ecs_manager.py 2.1 KB runs code
- scripts/on_serverless/__init__.py 0 B runs code
- scripts/on_serverless/emr_serverless_cli.py 2.4 KB runs code
- scripts/on_serverless/emr_serverless_manager.py 5.5 KB runs code
- scripts/on_serverless/emr_serverless_submit_cli.py 11 KB runs code
- scripts/on_vke/__init__.py 0 B runs code
- scripts/on_vke/emr_on_vke_manager.py 2.8 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 215 lines · 183 tokens per session scan A 01638374b7b0
byted-emr-skills is a skill published in the GitHub repository bytedance/agentkit-samples (453 stars, last pushed 2d ago), licensed Apache-2.0. It adds 183 tokens to every session and 4,918 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
latchbio-integration
Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.
claw-admin
Claw system administration: service management, IM connections, logs, cron, and workspace diagnostics. Use when the user asks to manage claw services, connect/disconnect IM platforms, view logs, or perform system-wide operations.
x-nets
Enhanced netstat module with cached data and structured output. View network connections, routing tables, and interface statistics in interactive or TSV/CSV formats. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
x-theme
Change terminal command line prompt theme. Globally manage the display style of all x-cmd interactive components. Supports multiple theme vendors: theme, starship, ohmyposh. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
x-arp
Display ARP cache table with MAC vendor lookup and suspicious entry detection. Supports CSV, TSV, and TUI output. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
x-lsof
Enhanced lsof (List Open Files) with interactive UI and structured output. View open files, network connections, and processes. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.