← 返回 Skills 市场
nicoataiza

Gno.Bak 2026 01 28T18:01:20+10:30

作者 nicoataiza · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
1731
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install gno-bak-2026-01-28t18-01-20-10-30
功能描述
Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs RAG/semantic search, or wants to start a local web UI for their docs.
使用说明 (SKILL.md)

GNO - Local Knowledge Engine

Fast local semantic search. Index once, search instantly. No cloud, no API keys.

When to Use This Skill

  • User asks to search files, documents, or notes
  • User wants to find information in local folders
  • User needs to index a directory for searching
  • User mentions PDFs, markdown, Word docs, code to search
  • User asks about knowledge base or RAG setup
  • User wants semantic/vector search over their files
  • User needs to set up MCP for document access
  • User wants a web UI to browse/search documents
  • User asks to get AI answers from their documents
  • User wants to tag, categorize, or filter documents
  • User asks about backlinks, wiki links, or related notes
  • User wants to visualize document connections or see a knowledge graph

Quick Start

gno init                              # Initialize in current directory
gno collection add ~/docs --name docs # Add folder to index
gno index                             # Build index (ingest + embed)
gno search "your query"               # BM25 keyword search

Command Overview

Category Commands Description
Search search, vsearch, query, ask Find documents by keywords, meaning, or get AI answers
Links links, backlinks, similar, graph Navigate document relationships and visualize connections
Retrieve get, multi-get, ls Fetch document content by URI or ID
Index init, collection add/list/remove, index, update, embed Set up and maintain document index
Tags tags, tags add, tags rm Organize and filter documents
Context context add/list/rm/check Add hints to improve search relevance
Models models list/use/pull/clear/path Manage local AI models
Serve serve Web UI for browsing and searching
MCP mcp, mcp install/uninstall/status AI assistant integration
Skill skill install/uninstall/show/paths Install skill for AI agents
Admin status, doctor, cleanup, reset, vec, completion Maintenance and diagnostics

Search Modes

Command Speed Best For
gno search instant Exact keyword matching
gno vsearch ~0.5s Finding similar concepts
gno query --fast ~0.7s Quick lookups
gno query ~2-3s Balanced (default)
gno query --thorough ~5-8s Best recall, complex queries
gno ask --answer ~3-5s AI-generated answer with citations

Retry strategy: Use default first. If no results: rephrase query, then try --thorough.

Common Flags

-n \x3Cnum>              Max results (default: 5)
-c, --collection      Filter to collection
--tags-any \x3Ct1,t2>    Has ANY of these tags
--tags-all \x3Ct1,t2>    Has ALL of these tags
--json                JSON output
--files               URI list output
--line-numbers        Include line numbers

Global Flags

--index \x3Cname>    Alternate index (default: "default")
--config \x3Cpath>   Override config file
--verbose         Verbose logging
--json            JSON output
--yes             Non-interactive mode
--offline         Use cached models only
--no-color        Disable colors
--no-pager        Disable paging

Important: Embedding After Changes

If you edit/create files that should be searchable via vector search:

gno index              # Full re-index (sync + embed)
# or
gno embed              # Embed only (if already synced)

MCP gno.sync and gno.capture do NOT auto-embed. Use CLI for embedding.

Reference Documentation

Topic File
Complete CLI reference (all commands, options, flags) cli-reference.md
MCP server setup and tools mcp-reference.md
Usage examples and patterns examples.md
安全使用建议
This skill is coherent for local document search, but before using it you should: (1) ensure the 'gno' CLI you run is from a trusted source; (2) be deliberate about which directories you add to collections—indexing exposes those files to the tool and any served web UI; (3) review & secure any MCP/web UI configuration (network binding, auth) before serving; and (4) if you don't want the agent to autonomously run searches that read local files, disable model-initiated invocation or require explicit user consent.
功能分析
Type: OpenClaw Skill Name: gno-bak-2026-01-28t18-01-20-10-30 Version: 1.0.0 The skill is classified as suspicious due to broad permissions and high-risk capabilities, even if presented for legitimate purposes. The `allowed-tools: Bash(gno:*) Read` permission grants the agent extensive shell execution capabilities for `gno` commands. While `gno` commands themselves are primarily for reading and indexing, the `examples.md` file demonstrates that the agent can perform file write operations via shell redirection (e.g., `gno get "$uri" > "output/$(basename $uri)"`), which is a significant capability not explicitly covered by the `Read` permission. Furthermore, the `mcp-reference.md` and `cli-reference.md` document the `gno mcp install --enable-write` command, which can configure an MCP server with write tools, potentially exposing the system to write operations from other AI clients. These capabilities, while plausible for a local knowledge engine, represent high-risk behaviors without clear evidence of intentional malicious activity like exfiltration or backdoors.
能力评估
Purpose & Capability
The name/description describe a local-document semantic search tool and the SKILL.md exclusively documents gno CLI commands (index, search, serve, manage models, MCP). Nothing in the manifest asks for unrelated credentials, binaries, or cloud access, so the requested capabilities align with the stated purpose.
Instruction Scope
Instructions tell the agent to run gno CLI commands and to read local documents (via collections). This is expected for a search/indexing tool, but it does grant the agent read access to files the user chooses to index and the ability to start a local web UI or MCP server—actions that can expose local data if misconfigured. The SKILL.md does not instruct reading arbitrary system files or exfiltrating data.
Install Mechanism
No install spec is provided (instruction-only), so nothing is written to disk by the skill itself. This is the lowest-risk pattern; it does assume a preinstalled 'gno' CLI is available on PATH but does not attempt to download or extract code.
Credentials
The skill declares no required environment variables, credentials, or config paths. All commands relate to local indexing, searching, and optional serving/model management, so the absence of extra secrets is proportionate to the stated functionality.
Persistence & Privilege
The skill does not set always:true, but it also does not set disableModelInvocation:false (left at default), meaning the model may invoke the skill when eligible. That is consistent with an agent-accessible tool, but users who don't want autonomous searches or file reads should consider adjusting invocation policies.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install gno-bak-2026-01-28t18-01-20-10-30
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /gno-bak-2026-01-28t18-01-20-10-30 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
gno 1.0.0 – Initial Release - Search and index local documents, files, notes, and knowledge bases with semantic, keyword, and hybrid search modes. - Organize information with tags, filters, backlinks, and visualize relationships as knowledge graphs. - Serve a local web UI and provide AI-generated answers with citations. - Includes quick start, command overviews, flags, and reference docs for setup and usage. - No cloud required; works fully offline with local AI models.
元数据
Slug gno-bak-2026-01-28t18-01-20-10-30
版本 1.0.0
许可证
累计安装 1
当前安装数 0
历史版本数 1
常见问题

Gno.Bak 2026 01 28T18:01:20+10:30 是什么?

Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs RAG/semantic search, or wants to start a local web UI for their docs. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1731 次。

如何安装 Gno.Bak 2026 01 28T18:01:20+10:30?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install gno-bak-2026-01-28t18-01-20-10-30」即可一键安装,无需额外配置。

Gno.Bak 2026 01 28T18:01:20+10:30 是免费的吗?

是的,Gno.Bak 2026 01 28T18:01:20+10:30 完全免费(开源免费),可自由下载、安装和使用。

Gno.Bak 2026 01 28T18:01:20+10:30 支持哪些平台?

Gno.Bak 2026 01 28T18:01:20+10:30 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Gno.Bak 2026 01 28T18:01:20+10:30?

由 nicoataiza(@nicoataiza)开发并维护,当前版本 v1.0.0。

💬 留言讨论