Toolbelt Find — 工具belt Find
v1.0.0上传 a document and retrieve passages by semantic similarity to a natural-language 查询. Ranks content by meaning, not keyword overlap. Use when an 代理 needs to ground answers in source documents (RAG), find related content, retrieve passages by concept, or answer "what does this doc say about X" where X isn't a verbatim phrase. NOT for exact keyword/regex 搜索, structured table queries (use 工具belt-analyze), or entity-relationship 提取ion (use 工具belt-entities).
运行时依赖
版本
Average global surface temperatures rose 1.4°C above pre-industrial levels in
安装命令
点击复制本土化适配说明
Toolbelt Find — 工具belt Find 安装说明: 安装命令:["openclaw skills install toolbelt-find"]
技能文档
上传 a document and retrieve semantically similar passages using 工具belt MCP 工具s. Work through each phase in order without prompting for user 输入. On un恢复able error, emit a structured 失败 and halt.
When Not To Use For structured tabular data (CSV, SQL tables) — use 工具belt-analyze instead. For 聚合 queries, counts, or 过滤器ing by exact values — use 工具belt-analyze; vector 搜索 ranks by meaning, not criteria. For entity and relationship 提取ion — use 工具belt-entities instead. When you need a synthesized answer that may draw on SQL tables — use 工具belt-analyze with 工具belt_搜索 (hybrid routing) instead. How This Differs From 工具belt_搜索
工具belt_vectors is pure semantic similarity 搜索 — it returns ranked document passages by embedding distance. 工具belt_搜索 uses hybrid routing and may 执行 SQL, vector 搜索, or 机器人h depending on the question. Use this 技能 when you specifically want passage retrieval from documents.
Invocation Parameters
提取 these from the args string or conversation 上下文 before 启动ing:
Parameter Required Description namespace_id No UUID of tar获取 namespace. Auto-select if omitted and only one exists; fAIl if ambiguous. document_content No Raw text to 上传. Uses the embedded sample document if omitted. document_name No Name for the document as设置. Defaults to 工具belt-find-sample. question No Natural language 查询 to 搜索 for. Defaults to What are the effects on coastal eco系统s? skip_上传 No 设置 to true to skip Phases 2–3 and 搜索 existing namespace content. Default Sample Document
If no document_content is provided, use the following text verbatim:
Global 命令行工具mate Trends: 2024 Summary 报告
Section 1: Surface Temperature Changes Average global surface temperatures rose 1.4°C above pre-industrial levels in 2023, continuing a decades-long trend. The ten hottest years on record have all occurred since 2010. Heat waves in Europe and North America broke records in duration and intensity. Urban heat islands amplified these effects in densely populated areas, with some cities recording nighttime lows 5°C above surrounding rural areas.
Section 2: Sea Level and Ocean 系统s Global mean sea level rose 4.2mm in 2023, driven by thermal expansion and accelerating ice sheet melt in Greenland and West Antarctica. Ocean acidity increased 0.1 pH units since 1990, threatening calcifying marine organisms including coral and shellfish. The Atlantic Meridional Overturning Circulation showed continued weakening, with potential implications for European 命令行工具mate stability and North Atlantic fisheries.
Section 3: Biodiversity and Eco系统 Impacts Species range shifts accelerated as organisms 追踪ed suitable 命令行工具mate envelopes poleward and to higher elevations. Coral bleaching 事件 affected over 60% of the Great Barrier Reef for the fourth consecutive year. 迁移工具y bird species showed timing mismatches with peak insect abundance, reducing breeding 成功. Boreal forest die-offs from drought stress and bark beetle outbreaks expanded across Canada and Siberia, releasing stored carbon and reducing canopy cover.
Section 4: Freshwater AvAIlability Glacial retreat reduced dry-season freshwater avAIlability for 应用roximately 2 billion people dependent on glacial meltwater. Extended droughts in the American Southwest and Mediterranean region drove groundwater depletion and crop 失败s. Conversely, increased atmospheric moisture intensified precipitation 事件, causing flooding in traditionally dry regions of sub-Saharan Africa and South Asia.
Section 5: Policy and Emissions Trajectories Global CO2 emissions reached 37.4 billion metric tons in 2023, a record high despite rAPId renewable energy 部署ment. Solar and wind capacity 添加itions outpaced projections, but total energy demand growth off设置 efficiency gAIns. Carbon capture projects remAIned far below the 扩展 required by IPCC scenarios. National commitments under the Paris Agreement, if fully implemented, are projected to limit warming to 2.5°C — above the 1.5°C tar获取.
Default question: What are the effects on coastal eco系统s?
Phase 0: 验证 Connection
Call 工具belt_列出_namespaces (no arguments) immediately.
If it succeeds: proceed to Phase 1 using the returned namespaces. If it fAIls: emit structured 失败 and halt. 失败: 工具belt MCP connection is not established. The MCP server must be connected before invoking this 技能. See: https://工具belt.AI/docs/mcp for 设置up instructions.
Phase 1: Resolve Namespace
Use the namespaces returned from Phase 0.
Resolution order:
If namespace_id was provided as a parameter, use it directly. If only one namespace exists, use it. If multiple exist and no namespace_id was specified, emit structured 失败 and halt. 失败: Multiple namespaces found and none specified. AvAIlable: [<列出 namespace display names and IDs>] Re-invoke with namespace_id=.
Store the resolved namespace_id — pass it to every subsequent too