Skill 与 AgentSKILLS & AGENTS· MCP-SERVER
getnao/nao
nao 是开源数据分析代理,让数据分析师用聊天方式向数据库提问。An open-source chat interface for your data warehouse that answers everyday questions in plain language.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
启动聊天界面直接提问数据
连上数据库自动整理背景资料
用测试题检验回答准确率
把Tableau报表迁移成nao图表
Ask questions about your data in plain language.
Connect to BigQuery, Snowflake, Postgres, or Databricks.
Sync context from databases and code repositories.
Test natural-language-to-SQL quality with built-in tests.
Migrate dashboards from Metabase or Tableau.
上手GET STARTED
pip install nao-core选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01执行 Shell 命令Runs shell commands.claude/skills/code-review/SKILL.md
allowed-tools: Bash(gh
02执行 Shell 命令Runs shell commands.claude/skills/code-review/SKILL.md
allowed-tools: Bash(gh
静态扫描发现允许执行Shell命令(Bash工具),属于中等风险,使用前需确认该工具的配置与权限范围。Static scan flagged two medium-risk shell-command executions, both from an allowed-tools entry that includes Bash. Review that setting before running nao.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+18.0%+18.0%
1.7k → 2.0k stars · 50 个快照1.7k → 2.0k stars · 50 snapshots
讨论DISCUSSION
1 SOURCES1 SOURCES
1 条外部提及1 external mentions
状态STATUS
持续活跃Active
质量 AQuality A
近 7 天有 61 次提交,仓库还在频繁迭代,适合现在尝鲜并观察方向。1962 GitHub stars and 61 commits in the past week
HN_STORY · 5 points · 0 comments
依赖:Dependencies:@boxlite-ai/boxlite, @emnapi/core, @emnapi/runtime, @streamdown/code, depd
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude/"
}
],
"apiKey": "s://app.getnao.io --api-key \"$NAO_API_KEY\" ``` - **Self-hosted**: run the Do",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 1,
"dev-tools": 3,
"indie-web": 0,
"skill-agent": 0,
"productivity": 4
},
"primary": "skill-agent",
"secondary": "mcp-server"
},
"localRuntime": "mini | mistral | openrouter | ollama | vertex api_key: ${{ env('AN",
"skillMdTotal": 10,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 8,
"agent": 6,
"media": 0,
"design": 2,
"browser": 0,
"devtool": 1,
"security": 1,
"marketing": 0,
"productivity": 4
},
"classification": [
{
"signal": "9 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 12 markdown files",
"weight": 0.75
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
}
],
"scannedSources": [
"readme",
".claude/skills/code-review/SKILL.md",
"skills/add-semantic-layer/SKILL.md",
"skills/audit-context/SKILL.md",
"skills/build-custom-charts/SKILL.md",
"skills/create-context-tests/SKILL.md",
"skills/deploy-context/SKILL.md",
"skills/migrate-metabase/SKILL.md",
"skills/migrate-tableau-workbook/SKILL.md",
"skills/setup-context/SKILL.md",
"skills/write-context-rules/SKILL.md"
],
"skillMdFetched": 10
}