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-volcengine-flinkgit 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-volcengine-flink)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-volcengine-flink"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-volcengine-flink.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 86 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
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 | $0.00093 | $0.01046 |
| Opus 5 | $0.00046 | $0.00523 |
| Sonnet 5 | $0.00019 | $0.00209 |
| Haiku 4.5 | $0.00009 | $0.00105 |
Grade A, and why
byted-volcengine-flink scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Byted Volcengine Flink
火山引擎 Flink 聚合技能入口,用于统一处理 Flink 相关需求,并按意图转发到对应子技能文档。
前置环境
在安装并使用本技能前,需要先完成 flink-mcp 前置准备。
1) 安装并验证 mcporter
flink-dev.md、flink-resource.md、flink-sre.md 中的运维/诊断指令依赖 mcporter。
可按你的 Python 环境选择任一方式安装:
npm install -g mcporter
安装后验证:
mcporter --help
2) 配置必需环境变量
flink-mcp 启动依赖以下环境变量(缺一不可):
VOLCENGINE_ACCESS_KEYVOLCENGINE_SECRET_KEYVOLCENGINE_REGIONVOLCENGINE_PROJECT_NAME
示例:
export VOLCENGINE_ACCESS_KEY="your-access-key"
export VOLCENGINE_SECRET_KEY="your-secret-key"
export VOLCENGINE_REGION="cn-beijing"
export VOLCENGINE_PROJECT_NAME="your-flink-project"
3) 在本地 MCP 配置文件中注册 flink-mcp(推荐)
将 flink-mcp 加入本地 MCP Client 使用的配置文件(通常为 mcp.json 或等效配置文件)。
说明:MCP Client 会根据这段配置拉起 flink-mcp,因此这是默认主路径。
先确保本地已安装 uv / uvx,然后写入如下配置:
{
"mcpServers": {
"mcp-server-flink": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/volcengine/mcp-server#subdirectory=server/mcp_server_flink",
"mcp-server-flink",
"-t",
"streamable-http"
],
"env": {
"VOLCENGINE_ACCESS_KEY": "${VOLCENGINE_ACCESS_KEY}",
"VOLCENGINE_SECRET_KEY": "${VOLCENGINE_SECRET_KEY}",
"VOLCENGINE_REGION": "${VOLCENGINE_REGION}",
"VOLCENGINE_PROJECT_NAME": "${VOLCENGINE_PROJECT_NAME}",
"UV_INDEX_URL": "https://mirrors.ivolces.com/pypi/simple/"
}
}
}
}
4) 可选:手动启动 flink-mcp(仅用于联调/排障)
当需要独立验证服务是否可启动时,可在终端手动执行:
uvx --from git+https://github.com/volcengine/mcp-server#subdirectory=server/mcp_server_flink mcp-server-flink -t streamable-http
子技能引用与路由
根据用户需求,将任务路由到以下子技能:
- 开发/部署 Flink SQL:
flink-dev.md - 只读诊断(禁止变更操作):
flink-diagnosis.md - 资源与故障分析:
flink-resource.md - SRE 运维变更(启停/重启/扩缩容/参数修改):
flink-sre.md
路由规则
- 用户表达“创建 SQL / 开发 SQL / 部署 SQL / 调试 SQL”时,优先使用
flink-dev.md。 - 用户明确要求“只读排查、不做任何变更”时,必须使用
flink-diagnosis.md。 - 用户询问故障根因、OOM、Checkpoint、性能问题、连接问题时,优先使用
flink-resource.md。 - 用户要求执行运维动作(启动、停止、重启、扩容、缩容、改配置)时,必须使用
flink-sre.md,且先做风险确认。
What ships with it
5 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.
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.
- 4d ago First seen · 110 lines · 93 tokens per session scan A 8a1f7ddc3738
byted-volcengine-flink is a skill published in the GitHub repository bytedance/agentkit-samples (449 stars, last pushed 3d ago), licensed Apache-2.0. It adds 93 tokens to every session and 1,046 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
llm-redteam-overview
LLM red team category — full AATMF v3 tactic coverage (T01–T15). Routing skill: read this first to identify which tactic applies, then load the matching sub-skill. Maps to MITRE ATLAS where overlap exists.
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.
vector-and-embedding-weaknesses
Hunt vector / embedding weaknesses (OWASP LLM08:2025) — adversarial inputs against the RAG / similarity layer that cause cross-tenant leak, embedding-inversion privacy loss, semantic confusion, and retriever-driven prompt injection.
shap
Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…
cellxgene-census
Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.