Token导航 LogoToken导航TokenDH.com
开发external-serviceclawhub未标认证来源可访问clear审计通过

sql-sparql-graphql-skillSQL sparql GraphQL 技能

Agent Skill

用于辅助 API 设计、接口文档、请求响应结构和服务集成说明。它适合让 Agent 梳理 endpoint、生成 OpenAPI 草稿、检查字段命名、整理错误码或辅助前后端联调。使用时需要确认真实业务语义、鉴权方式、分页和错误处理规则;涉及生成接口文档时,应避免凭空补字段,最好从现有代码、schema 或接口样例中提取事实。

总安装

6,336

周安装

264

GitHub Stars

公开资料未说明

下载量

2,112
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:sql-sparql-graphql-skill(SQL sparql GraphQL 技能)
来源仓库:https://github.com/kidehen/sql-sparql-graphql-skill
安装命令:
openclaw skills install sql-sparql-graphql-skill
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install sql-sparql-graphql-skill

简介

通过 OpenLink Web 服务执行 SQL、SPARQL 和 GraphQL 查询。

  • 支持实时数据空间和知识图谱访问。sql-sparql-graphql-skill 属于开发类 Skill,可作为该场景下的辅助能力补充。
  • 提供 SPASQL 和 SPARQL-FED 联合查询能力。
  • 适用于语义网和关联数据应用场景。
  • 需配置 API 端点和认证信息方可使用。

SKILL.md

name
data-twingler
description
Execute SQL, SPARQL, SPASQL, SPARQL-FED, and GraphQL queries against live data spaces and knowledge graphs via OpenLink's OpenAPI-compliant web services. Use this skill whenever the user wants to query a database, RDF store, or SPARQL endpoint; explore a knowledge graph or data space; asks "How to ...", "Define the term ...", or poses a question against a known article or graph context; or mentions linkeddata.uriburner.com, Virtuoso, OPAL, or OpenLink services. Full query templates are in references/query-templates.md — load that file before constructing any predefined query.
license
See LICENSE.txt

OpenLink Data Twingler (v2.0.83)

Enhances LLM responses with RAG by routing user intent to the right query language and live endpoint. Covers SQL, SPARQL, SPASQL, SPARQL-FED, and GraphQL — all driven by natural language, no imperative programming required.


Defaults & Settings

ParameterValue
SPARQL Default Endpointhttps://linkeddata.uriburner.com/sparql
SPARQL Result Formattext/x-html+tr
SPARQL / SQL Timeout30 seconds
SPARQL Max Results20 (unless overridden)
GraphQL Default Endpointhttps://linkeddata.uriburner.com/graphql
GraphQL Query Depth Limit10
SQL DefaultSELECT TOP 20 * FROM Demo.Demo.Customers
Cache TTL3600 seconds
Parallel ExecutionEnabled
Tabulate All ResultsYes (all query types)

Query Language Routing

Execution Routing

Default execution order for query execution:

  1. Direct native endpoint calls with curl or the query protocol's simplest direct mechanism
  2. URIBurner REST functions such as sparqlRemoteQuery, sparqlQuery, graphqlEndpointQuery, graphqlQuery, execute_spasql_query, and execute_sql_query
  3. MCP via https://linkeddata.uriburner.com/chat/mcp/messages or https://linkeddata.uriburner.com/chat/mcp/sse
  4. Authenticated LLM-mediated execution via https://linkeddata.uriburner.com/chat/functions/chatPromptComplete
  5. OPAL Agent routing using recognizable OPAL function names

If the user's prompt expresses a protocol preference such as curl, REST, OpenAI, MCP, SSE, streamable HTTP, or OPAL, follow that preference instead of the default order.

Read references/protocol-routing.md when you need exact routing guidance.

SQL

Default: SELECT TOP 20 * FROM Demo.Demo.Customers Apply TOP 20 unless a row limit is specified. Tabulate results.

SPARQL

Use default endpoint. Format text/x-html+tr. Max 20 rows. Tabulate results.

SPARQL-FED

Trigger: User explicitly names a SPARQL endpoint URL in the prompt.

  • Named endpoint → SERVICE block (remote); default endpoint → outer processor.
  • SERVICE block must contain a SELECT with an inner LIMIT.

SPASQL

Wraps SPARQL inside SQL: FROM (SPARQL ... WHERE ...) AS <alias>

GraphQL

Endpoint: https://linkeddata.uriburner.com/graphql. Depth: 10. Introspection on.


Predefined Prompt Templates

Always load references/query-templates.md and match the user's intent to a template before falling back to general LLM knowledge. Substitute {placeholders}, run the index query first (where applicable), similarity-match ?name, then execute the final query.

#TriggerTemplate in references/
1"Explore this Data Space"T1 — Entire data space
2"Explore knowledge graph {G}"T2 — Specific KG
3"Explore {G} with reasoning & inference"T3 — KG + inference
4"Using endpoint {E}, explore graph {G}"T4 — SPARQL-FED
5"How to {X}"T5 — HowTo (2-step)
6"{Question}" with article/graph contextT6 — Q&A UNION (2-step)
7"Define the term {X}"T7 — DefinedTerm (2-step)

Functions (External Web Services)

FunctionSignatureUse Case
UB.DBA.sparqlQuery(query, format)SPARQL
Demo.demo.execute_spasql_query(sql, maxrows, timeout)SPASQL
UB.DBA.sparqlQuery(sql, url)SQL
DB.DBA.graphqlQuery(query)GraphQL

Call directly, or as fallback when predefined templates yield no match.

Canonical OPAL-recognizable function names from the Smart Agent definition are:

  • UB.DBA.sparqlQuery with signature (query, format) for SPARQL
  • Demo.demo.execute_spasql_query with signature (sql, maxrows, timeout) for SPASQL
  • UB.DBA.sparqlQuery with signature (sql, url) for SQL as documented in the canonical configuration
  • DB.DBA.graphqlQuery with signature (query) for GraphQL

Treat OPAL as an agent routing layer over these named functions, not merely another transport.


Entity Denotation in Results

Hyperlink all entity identifiers using:

http://linkeddata.uriburner.com/describe/?uri={url_encoded_id}
  • All URLs must be percent-encoded.
  • Include a citation section with hyperlinked source entity IDs.
  • Log all hyperlink formatting errors with detailed feedback.

Fallback Strategies

  1. Retry without @en language tags on ?name.
  2. Prompt for missing values: {G}, {Article Title}, ?authorName, etc.
  3. Iterate through additional input values to progressively refine results.
  4. If no protocol preference was stated, fall through in this order: direct native execution -> REST function execution -> MCP -> authenticated chatPromptComplete -> OPAL Agent routing.

Commands

CommandSyntax
Update a setting/update_settings [name] [value]
Show all settings/show_settings
Run a test query/test_query [type] [content]

Rules (Non-Negotiable)

  1. Use predefined templates before general LLM knowledge.
  2. Optimize every query for performance and accuracy.
  3. Validate setting changes with test queries where possible.
  4. Handle errors gracefully with detailed, actionable feedback.
  5. Leverage caching (TTL 3600s) and parallel execution.
  6. Tabulate all query results by default.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

94.93%
按下载量换算2,005

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills