Route ordinary public-web information tasks to the correct Tavily CLI operation. Use when the task concerns publicly accessible webpages and needs web discovery, clean extraction, URL mapping, same-site crawling, or public-web-only research, but the exact Tavily operation is not yet clear or several operations must be sequenced. Prefer the specific leaf skill when intent is clear: tavily-search for discovery without a URL, tavily-extract for known URLs, tavily-map for URL/site-structure discovery, tavily-crawl for content from many pages on one site, tavily-research for cited multi-source synthesis, and tavily-dynamic-search for programmatic filtering with context isolation. Do not use for named social/community/media/career/code platforms, login or cookie-dependent content, platform-native discussions, or cross-platform collection; use Agent Reach there. Do not use for local files, Git operations, deployments, or ordinary code editing.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Web search, content extraction, site crawling, URL discovery, and deep research. Returns JSON optimized for LLM consumption.
Route by source and access method:
When a Tavily operation is already clear, load the corresponding leaf skill instead of keeping this router as the only instruction source.
Run tvly --help or tvly <command> --help for full option details.
Must be installed and authenticated. Check with tvly --status.
tavily v0.1.0
> Authenticated via OAuth (tvly login)
If not ready:
curl -fsSL https://cli.tavily.com/install.sh | bash
Or manually: uv tool install tavily-cli / pip install tavily-cli
Then authenticate:
tvly login --api-key tvly-YOUR_KEY
# or: export TAVILY_API_KEY=tvly-YOUR_KEY
# or: tvly login (opens browser for OAuth)
Follow this escalation pattern — start simple, escalate when needed:
| Need | Command | When |
|---|---|---|
| Find pages on a topic | tvly search | No specific URL yet |
| Get a page's content | tvly extract | Have a URL |
| Find URLs within a site | tvly map | Need to locate a specific subpage |
| Bulk extract a site section | tvly crawl | Need many pages (e.g., all /docs/) |
| Deep research with citations | tvly research | Need multi-source synthesis |
For detailed command reference, use the individual skill for each command (e.g., tavily-search, tavily-crawl) or run tvly <command> --help.
All commands support --json for structured, machine-readable output and -o to save to a file.
tvly search "react hooks" --json -o results.json
tvly extract "https://example.com/docs" -o docs.md
tvly crawl "https://docs.example.com" --output-dir ./docs/
? and & as special characters.--json for agentic workflows — every command supports it.- — echo "query" | tvly search -还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
使用 AACT (Aggregate Analysis of ClinicalTrials.gov) PostgreSQL 数据库进行大批量临床试验历史分析与数据挖掘。触发场景包括：AACT 查询、临床试验批量分析、PostgreSQL 试验数据、全量 NCT 检索、试验数据挖掘、clinical trials data warehouse、疾病领域全景分析、设计相似试验匹配、跨年度试验趋势聚合。本 skill 通过 SQL 接口处理百万级试验记录，支持云端公共 PostgreSQL 服务（aact-db.ctti-clinicaltrials.org）和每日 dump 本地还原两种连接方式，自动检测并优先使用本地高性能模式。
中文简介正在准备中。当前显示原文说明。
使用 AACT (Aggregate Analysis of ClinicalTrials.gov) PostgreSQL 数据仓库进行批量、历史、聚合性临床试验数据挖掘。Use this skill when the user requests bulk SQL analysis over the full clinical trials data warehouse — historical trial trends, disease landscapes, similar-design matching, or multi-year aggregations across hundreds of thousands of NCT records. 触发场景包括：AACT 查询、临床试验批量分析、PostgreSQL 试验数据、全量 NCT 检索、试验数据挖掘、历史试验分析、clinical trials data warehouse、SQL trials、bulk trial analysis、disease landscape、试验设计相似性匹配、跨年度聚合、sponsor/phase/country 多维统计。**与 clinical-trials-v2 差异**：本 skill 走批量 SQL · 离线大数据（PostgreSQL）；v2 走实时 API · 单查询。两者互补：单条 NCT 实时状态用 v2，百万级历史挖掘用本 skill。支持云端公共 PostgreSQL（aact-db.ctti-clinicaltrials.org · 零部署）和每日 dump 本地还原（高性能 · 离线）两种连接方式，自动检测优先用本地。跨平台（macOS/Linux/Windows）参数化 SQL 防注入，read-only 强制保护。
中文简介正在准备中。当前显示原文说明。
Use when work produces a deliverable, factual claim, dataset, code change, decision, publication, deployment, automation, or irreversible action whose failure would matter; when the user asks for a quality gate, acceptance criteria, QA, completeness, validation, audit, evidence, preflight, release readiness, or a definition of done; or before claiming completion on medium- or high-risk work. Automatically decide whether a formal gate is warranted, derive task-specific pass/fail criteria, gather evidence, and block unsupported completion. Make sure to use this skill even when the user does not say "quality gate" if consequential work needs acceptance criteria or completion evidence. Skip formal gating for trivial, reversible, low-impact requests.
中文简介正在准备中。当前显示原文说明。
Create a changeset file in .changeset/ that describes a user-facing change for the release notes
中文简介正在准备中。当前显示原文说明。
Add a new competitor to the AI Visibility Tool Directory — researches the tool, generates data, takes a screenshot, and inserts into the codebase
中文简介正在准备中。当前显示原文说明。
Add tree-sitter language support to codegraph end-to-end — wire the grammar + extractor, write tests, then benchmark extraction quality and retrieval value on 3 popular real-world repos. Use when the user runs /add-lang <language> or asks to add/support a new language (e.g. Lua, Elixir, Zig, OCaml) in codegraph.
中文简介正在准备中。当前显示原文说明。