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-viking-search-knowledgebasegit 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-viking-search-knowledgebase)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-viking-search-knowledgebase"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-viking-search-knowledgebase.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.04166 |
| Opus 5 | $0.00034 | $0.02083 |
| Sonnet 5 | $0.00014 | $0.00833 |
| Haiku 4.5 | $0.00007 | $0.00417 |
Grade A, and why
byted-viking-search-knowledgebase 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 5d 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 — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Byted Viking Search Knowledgebase
该 Skill 用于通过 APIG 网关调用火山引擎 Viking 知识库的 API：
/api/knowledge/collection/info：查看知识库详情，获取collection_name和description。仅在路由/连接检查场景使用，不是知识问答的默认入口。/api/knowledge/collection/search_knowledge：语义检索，根据 query 从知识库中获取相关切片，返回切片列表、相关度分数、文档信息等。
版本整合说明：byted-viking-search-knowledgebase.tar.gz 曾包含 legacy 根目录 byted-viking-knowledgebase（scripts/search.py、VIKING_KBSVR_*）；该目录与仓库中的旧 skill 保持兼容，不作为本 skill 的更新目标。当前统一使用本目录的 APIG 鉴权、DATABASE_VIKING_* 配置和 scripts/viking_search.py。
输入前提（必读）
你接收到的不是用户原话，而是上级 Agent 分配给你的任务描述。这类描述通常具有以下特征，必须在拆分阶段处理掉，不能整段塞进 --query：
- 篇幅长（动辄数十到上百字）
- 分点（"1、…2、…3、…" 或 "首先…其次…最后…"）
- 多子意图叠加（同一段话里夹了"原因 + 步骤 + 流程 + 案例"等多个独立检索目标）
- 含大量过渡词、修饰语、上下文铺垫
直接把任务原文当 query 必然召回失配（向量被多个语义稀释，分数全部偏低）。正确做法是：先拆，再并行检索。
默认策略（最重要）
对于"基于知识库回答问题"类需求，默认走 auto 多库并行检索，且 query 必须经过【拆分 + 关键词化】处理。
不要在没有充分理由的情况下走 info → 推理 → search 的两步路由。
只有在以下少数场景才偏离默认策略：
| 场景 | 选择 |
|---|---|
| 知识问答（绝大多数） | auto，按"Query 构造规则"拆分多个独立 query 并行检索 |
任务已指定具体 resource_id 或 name |
search |
| 配置中知识库数 ≤ 2 且任务是路由决策 | 可选 info 辅助 |
| 任务意图是"连接检查"/"看看这个库通了没"/"调用下这个知识库"/"列一下我有哪些库" | info |
| 任务描述完全无主题关键词（如"帮我查点东西"） | 先 info 列表，再回报上级 Agent 请求澄清 |
经验法则：当你不确定走哪个动作时，默认选
auto。它本身就是为"未知目标 + 有具体语义"设计的。
Query 构造规则（拆分 + 关键词化 + 并行）
search / auto 的 --query 是语义检索向量入口。面对上级 Agent 的长任务描述，必须执行三步处理：
第 1 步：拆分子意图
逐句通读任务描述，识别其中独立的检索目标。每个分点、每个"和/与/以及/同时"连接的并列项，通常都是一个独立子意图。
示例：上级任务 = "排查网络连接失败的问题，需要：1、常见故障原因分类；2、对应的排查解决步骤；3、从易到难的标准化处理流程" → 识别出 3 个子意图：① 故障原因分类 ② 排查解决步骤 ③ 标准化处理流程
第 2 步：每个子意图压缩为关键词 query
对每个子意图，提炼成由 2~5 个核心关键词 构成的短 query，剔除连接词、修饰语、铺垫语。
形态要求：
- 长度：每个 query 控制在 5~15 个汉字 / 10~30 个英文词以内
- 由名词性关键词为主，允许少量动词，避免完整句式和疑问语气
- 保留专有名词、术语、产品名、错误码原文
示例（接上文）：
- query₁ = "网络连接失败 故障原因 分类"
- query₂ = "网络故障 排查步骤 解决方法"
- query₃ = "网络故障 标准化处理流程"
第 3 步：并行检索（关键约束）
将拆出的多个 query 分别独立调用 auto，禁止拼接成一个长 query。多次调用应在同一轮内并行发起。
多个 query 之间必须满足：
| 约束 | 说明 | 反例 |
|---|---|---|
| 互相独立 | 每个 query 表达一个完整可检索的子意图 | "故障原因"（太空泛，必须带主题词"网络故障 原因"） |
| 无重叠 | 关键词集合之间交集尽量小，不要让多个 query 检索同一片切片 | query₁="网络故障 原因 分类"、query₂="网络故障 原因 类型" ← 重叠过高 |
| 高区分度 | 每个 query 应能命中知识库的不同切片群 | 三个 query 都包含"网络故障 步骤" ← 区分度低 |
| 数量适中 | 通常 2~4 个 query；超过 5 个说明子意图拆得太碎，需合并 | — |
What ships with it
6 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.
- 5d ago First seen · 317 lines · 68 tokens per session scan A c4c2d725e13a
byted-viking-search-knowledgebase is a skill published in the GitHub repository bytedance/agentkit-samples (450 stars, last pushed 4d ago), licensed Apache-2.0. It adds 68 tokens to every session and 4,166 once invoked, about $0.0003 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
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.
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…
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.
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.
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.
aeon
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard…