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 agentmods add skills/volcengine/volcengine-skills/volcengine-knowledge-searchnpx skills add volcengine/volcengine-skills --skill volcengine-knowledge-searchgit clone --depth 1 https://github.com/volcengine/volcengine-skillsWrote 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/volcengine/volcengine-skills/volcengine-knowledge-search)<a href="https://agentmods.dev/skills/volcengine/volcengine-skills/volcengine-knowledge-search"><img src="https://agentmods.dev/badge/skills/volcengine/volcengine-skills/volcengine-knowledge-search.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00121 | $0.03392 |
| Opus 5 | $0.00060 | $0.01696 |
| Sonnet 5 | $0.00024 | $0.00678 |
| Haiku 4.5 | $0.00012 | $0.00339 |
Grade A, and why
volcengine-knowledge-search scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
火山引擎官方文档综合查询技能，提供 **search（检索）** 与 **fetch（全文获取）** 两个能力。火山引擎文档是火山最权威的官方数据，覆盖全产品使用全链路。接口为公开文档服务，**无需 AK/SK 鉴权**，脚本用 **Python3 标准库**实现（仅依赖 `python3`，无需 curl/jq）。 How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
volcengine-knowledge-search 火山引擎文档检索技能
火山引擎官方文档综合查询技能，提供 search（检索） 与 fetch（全文获取） 两个能力。火山引擎文档是火山最权威的官方数据，覆盖全产品使用全链路。接口为公开文档服务，无需 AK/SK 鉴权，脚本用 Python3 标准库实现（仅依赖 python3，无需 curl/jq）。
脚本会在本地把上游响应 解析 + 裁剪 + 清洗成干净 markdown 文本再输出（search 每条只回摘要、fetch 按页返回），避免把「整篇正文 × N、单行几十~上百 KB」的原始 JSON 灌进上下文。所以脚本输出可直接阅读/引用，不需要你再解析 JSON。
什么时候用
- 用户咨询火山引擎产品的概念、用法、计费规则、部署步骤、最佳实践、服务条款/协议等可在官方文档中找到解释的问题
- 用户给出一条火山引擎官方文档链接（
https://www.volcengine.com/docs/...），需要取该文档全文 - 用户消息里出现「火山」「火山引擎」「volcengine」且属于查官方文档 / 读文档全文的场景
命令速查
脚本位于 scripts/volcengine_docs.py，命令均相对本 skill 目录根执行。
| 子命令 | 用途 | 形式 |
|---|---|---|
search |
关键词检索文档 | search "<关键词>" [返回数量] [产品编码1,产品编码2...] |
fetch |
取单篇文档全文(分页) | fetch "<火山引擎文档链接>" [start_index] [max_length] |
search
python3 scripts/volcengine_docs.py search "tos 怎么计费" 3
参数：
| 参数 | 必填 | 说明 |
|---|---|---|
| 查询关键词 | 是 | 完整的自然语言问题/描述,贴近文档正式表述;不是关键词堆砌或英文缩写(见下方「如何写好 query」) |
| 返回数量 | 否 | 检索返回文档数，默认 10 |
| 产品编码 | 否 | 逗号分隔，限定仅查某几个产品；编码取自上一次返回的 ServiceCodes |
输出：已整理好的 markdown 文本，每条命中一段：
## 1. <标题>
<纯净URL>
ServiceCodes: <产品编码,逗号分隔>
<正文摘要，默认前 600 字，已清掉 HTML 标签>
---
直接阅读/引用即可，无需再解析 JSON。摘要字数可用环境变量 VOLC_SEARCH_SNIPPET 调整。ServiceCodes 行用于二次精搜（见示例 4）。
如何写好 query —— 这是「向量语义检索」,不是关键词精确匹配
本接口底层是向量库语义检索（embedding 召回）,而非倒排索引的关键词精确匹配。query 写得好不好,直接决定召回质量。把握一个核心:让 query 在语义上尽量贴近目标文档里的正式表述。
写 query 的要点:
- 用完整的自然语言描述,而非孤立短词。 例如查产品订阅价格,写「火山方舟 Coding Plan AI 编程订阅套餐 价格 计费」,而不是只写「Coding Plan」。短词/单个英文缩写语义太稀疏,极易召回跑偏(实测只搜「Coding Plan」会召回 DataFinder、RTC 等完全无关文档)。
- 补全产品全称与上下文。 用户常用简称、营销名、口语词(如「方舟」「豆包编程」「code plan」);先在 query 里补上官方全称 + 所属产品 + 具体方向(如「火山方舟大模型服务 模型推理 计费规则」),让向量更聚焦。
- 优先用「问题 / 描述」句式,而非命令式。 向量更亲近文档正文的陈述语气,「TOS 跨区域复制如何配置」优于「配 TOS 复制」。
- 首搜跑偏就换语义等价的说法重写,而不是重试同一句。 同一概念可能有多种表述,换近义描述(中英、全称/简称、功能动词)往往能召回到正确文档。
- 专有新名词(新产品、新功能、营销活动名)召回差时,把它「翻译」成它实际属于的产品 + 能力描述再搜,定位到正确产品后,可用返回的
ServiceCodes带产品编码二次精搜(见示例 4)。
真实对比(实测):用户问「火山引擎 Coding Plan 什么价格、如何接入」。
What ships with it
1 file 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.
- 3d ago First seen · 183 lines · 121 tokens per session scan A d72f4690d920
volcengine-knowledge-search is a skill published in the GitHub repository volcengine/volcengine-skills (18 stars, last pushed 2d ago), licensed MIT. It adds 121 tokens to every session and 3,392 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
application-design-center-design-deploy
Processes GCP infrastructure design and deployment workflows within Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".