
Volcengine Documentation
- 21 installs
- 411 repo stars
- Updated August 4, 2026
- bytedance/agentkit-samples
volcengine-documentation is a Claude skill that searches and fetches official Volcengine product documentation.
About
volcengine-documentation is a Claude skill that searches and retrieves official Volcengine product documentation. It exposes a search operation that returns relevant docs (default 5) and a fetch operation that returns full document content for a given URL. A developer uses it to answer product, usage, billing, deployment, and troubleshooting questions with authoritative docs. Every answer must cite the clean official doc link.
- Searches and fetches official Volcengine documentation
- search returns up to 5 docs; fetch returns full doc content by URL
- Requires citing the clean official doc link on every answer
Volcengine Documentation by the numbers
- 21 all-time installs (skills.sh)
- Ranked #1,001 of 1,879 Documentation skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
volcengine-documentation capabilities & compatibility
Calls the public Volcengine docs API; no API key stated
- Capabilities
- documentation search · doc fetch
- Use cases
- documentation · research · web search
- Runs
- Runs locally
- Pricing
- Free
What volcengine-documentation says it does
火山引擎文档综合查询技能,支持**文档检索**和**内容获取**两个核心功能
所有回答末尾**必须**附上对应的官方文档链接作为参考来源
npx skills add https://github.com/bytedance/agentkit-samples --skill volcengine-documentationAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 21 |
|---|---|
| repo stars | ★ 411 |
| Last updated | August 4, 2026 |
| Repository | bytedance/agentkit-samples ↗ |
What it does
Search and fetch official Volcengine documentation to answer product, usage, and billing questions.
Who is it for?
Answering Volcengine product, usage, billing, and troubleshooting questions from official docs.
Skip if: Executing cloud operations (use volcengine-cli) or looking up API parameter specs (use volcengine-api).
When should I use this skill?
A user asks about a Volcengine product, feature, or doc and you need the official source.
What you get
You get official doc content plus the clean source link to cite.
- relevant doc list from search
- full document content from fetch
- cited clean official doc links
By the numbers
- search returns 5 documents by default
- answers show at most 3 most-relevant results with links
Files
volcengine-documentation 火山引擎文档技能
功能描述
火山引擎文档综合查询技能,支持文档检索和内容获取两个核心功能,火山引擎文档是火山最权威的官方数据,涵盖全产品使用全链路。
决策逻辑(必看)
触发判断规则
1. 用户提供文档链接:直接调用 fetch 接口获取完整内容,无需先检索。
search 和 fetch 配合规则
1. 用户提问类需求:优先调用 search 接口(默认不携带ServiceCodes参数),返回5条结果,优先使用返回的Content内容回答。 2. 二次检索优化:如果第一次搜索结果匹配度不高,可根据第一次返回结果中的ServiceCodes字段,携带对应产品编码参数执行二次检索,缩小范围获取更精准结果。 3. 需要完整文档内容:先调用 search 找到对应文档链接,再调用 fetch 获取全文内容。
功能说明
1. 文档检索 (search)
根据用户问题检索相关火山引擎官方文档,支持按产品过滤。
- 请求地址:
https://docs-api.cn-beijing.volces.com/api/v1/doc/search
请求参数
| 参数名 | 类型 | 必填 | 说明 |
|---|---|---|---|
| Query | string | 是 | 用户的具体问题描述 |
| Limit | number | 否 | 检索返回的文档数量,默认返回5篇 |
| ServiceCodes | array<string> | 否 | 产品过滤条件,指定仅查询某几个产品的文档,可通过返回结果中的ServiceCodes字段获取产品编码 |
返回参数
核心有效数据在 Result.DocList 字段中,每个文档项包含:
| 字段名 | 类型 | 说明 |
|---|---|---|
| Title | string | 官方文档标题 |
| Url | string | 文档官方访问链接 |
| Content | string | 文档完整内容 |
| ServiceCodes | array<string> | 文档所属产品编码列表 |
---
2. 内容获取 (fetch)
根据火山引擎官方文档链接,获取对应的完整文档内容,支持结构化解析文档标题、正文内容。
- 请求地址:
https://docs-api.cn-beijing.volces.com/api/v1/doc/fetch
请求参数
| 参数名 | 类型 | 必填 | 说明 |
|---|---|---|---|
| Url | string | 是 | 火山引擎官方文档链接,格式如 https://www.volcengine.com/docs/6349/162514 |
⚠️ 重要处理规则: 如果Url包含query参数(例如 https://www.volcengine.com/docs/6396/624853?lang=zh),需要在请求前去掉所有query参数,只保留 https://www.volcengine.com/docs/6396/624853 部分进行请求。
返回参数
核心有效数据在 Result 字段中:
| 字段名 | 类型 | 说明 |
|---|---|---|
| Title | string | 文档的完整标题 |
| Content | string | 文档的完整正文内容,结构化解析后的文本 |
结果处理规则
通用强制规则
1. 所有回答末尾必须附上对应的官方文档链接作为参考来源,使用 [文档标题](纯净URL) 格式,每条结果都要标注来源地址 2. 如果返回多个结果,按相关性排序展示,最多展示3条最相关的结果,每条结果都附带对应的文档链接 3. 链接必须使用脚本返回的CleanUrl(已剥离所有query参数),禁止使用带?lang=zh等参数的URL
检索结果处理
1. 优先使用返回的Content内容回答用户问题,信息更准确 2. 接口直接返回文档完整内容,无需做额外摘要提炼
内容获取结果处理
1. 接口直接返回文档完整内容,可直接使用无需额外处理
工具使用方法
检索文档
python {skill_dir}/scripts/volcengine_docs.py search "查询关键词" [返回数量] [产品编码1,产品编码2...]示例:
python {skill_dir}/scripts/volcengine_docs.py search "tos是什么" 1 tos获取文档完整内容
python {skill_dir}/scripts/volcengine_docs.py fetch "火山引擎文档链接"示例:
python {skill_dir}/scripts/volcengine_docs.py fetch "https://www.volcengine.com/docs/6349/162514?lang=zh"#!/usr/bin/env python3
import sys
import json
import requests
from urllib.parse import urlparse
API_BASE = "https://docs-api.cn-beijing.volces.com/api/v1/doc"
REQUEST_TIMEOUT = 15 # 超时时间15秒,防止永久阻塞
# 已取消负向关键词判断逻辑,所有查询默认放行
def search(query, limit=10, service_codes=None):
"""检索火山引擎文档"""
url = f"{API_BASE}/search"
payload = {
"Query": query,
"Limit": limit
}
if service_codes:
payload["ServiceCodes"] = service_codes
headers = {
"Content-Type": "application/json"
}
try:
response = requests.post(url, headers=headers, json=payload, timeout=REQUEST_TIMEOUT)
response.raise_for_status()
return response.json()
except Exception as e:
return {"error": f"检索请求失败: {str(e)}"}
def fetch(doc_url):
"""获取文档完整内容,自动处理URL中的query参数"""
parsed = urlparse(doc_url)
# 完全剥离query参数和fragment参数,确保URL纯净
clean_url = f"{parsed.scheme}://{parsed.netloc}{parsed.path}"
url = f"{API_BASE}/fetch"
payload = {
"Url": clean_url
}
headers = {
"Content-Type": "application/json"
}
try:
response = requests.post(url, headers=headers, json=payload, timeout=REQUEST_TIMEOUT)
response.raise_for_status()
result = response.json()
# 始终返回纯净URL
if "Result" in result:
result["Result"]["CleanUrl"] = clean_url
return result
except Exception as e:
return {"error": f"内容获取请求失败: {str(e)}"}
def print_help():
help_info = {
"name": "volcengine-docs 火山引擎文档查询工具",
"usage": [
{
"action": "search",
"desc": "检索火山引擎文档",
"params": "<查询关键词> [返回数量] [产品编码1,产品编码2...]",
"example": 'python volcengine_docs.py search "tos是什么" 1 tos'
},
{
"action": "fetch",
"desc": "获取文档完整内容",
"params": "<火山引擎文档链接>",
"example": 'python volcengine_docs.py fetch "https://www.volcengine.com/docs/6349/162514?lang=zh"'
}
]
}
print(json.dumps(help_info, ensure_ascii=False, indent=2))
if __name__ == "__main__":
if len(sys.argv) < 2:
print_help()
sys.exit(1)
action = sys.argv[1]
result = {}
if action == "search":
if len(sys.argv) < 3:
result = {"error": "缺少查询关键词", "help": "用法: python volcengine_docs.py search <查询关键词> [返回数量] [产品编码1,产品编码2...]"}
else:
query = sys.argv[2]
limit = 10
service_codes = None
if len(sys.argv) >=4:
try:
limit = int(sys.argv[3])
except ValueError:
result = {"error": "返回数量必须是数字"}
if len(sys.argv) >=5:
service_codes = sys.argv[4].split(",")
if "error" not in result:
result = search(query, limit, service_codes)
elif action == "fetch":
if len(sys.argv) < 3:
result = {"error": "缺少文档URL", "help": "用法: python volcengine_docs.py fetch <火山引擎文档链接>"}
else:
doc_url = sys.argv[2]
result = fetch(doc_url)
else:
result = {"error": f"未知操作 {action}", "help": "支持的操作: search, fetch"}
print(json.dumps(result, ensure_ascii=False, indent=2))
if "error" in result:
sys.exit(1)
Related skills
FAQ
What two operations does it provide?
A search operation that finds relevant docs (default 5 results) and a fetch operation that returns the full content of a given doc URL.
Does it cite sources?
Yes, every answer must append the official doc link using the clean URL with all query parameters stripped.