Tavily Research

What it does

When your agent uses it

• Tasks that involve Web search
• Tasks that involve Deep research

Example prompts

• “/tavily-research”

Requirements

• A Bash shell
• A credential in TAVILY_API_KEY

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1Call tavily_research with your query — returns immediately with a request_id
2. 2Inform the user that research is in progress and may take 30-300 seconds
3. 3Call tavily_research_poll with the request_id — this tool waits internally until the research completes (up to ~5 minutes), so you only…
4. 4When the poll returns, include the full report text in your response — do not summarize or truncate it. Responses over 8000 characters are…

What it can do on your machine

Read from SKILL.md and the folder at commit 3c608d8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 2 files in scripts/ (Shell), which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • tavily.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • TAVILY_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tavily Research loads about 1.1k tokens when it runs. Until then it costs about 17 tokens; SKILL.md has 440 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~17

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from initializ/forge at commit 3c608d8, republished under its Apache-2.0 licence (© initializ). 440 words, ~1,099 tokens.

name

tavily-research

description

Deep multi-source research using Tavily Research API

icon

🔬

category

research

tags

research, web-search, tavily, analysis

# Submit research request
./scripts/tavily-research.sh '{"input": "impact of quantum computing on cryptography"}'
# Returns: {"status": "pending", "request_id": "..."}

# Poll for results
./scripts/tavily-research-poll.sh '{"request_id": "72d4a81c-..."}'
# Returns: {"status": "completed", "summary": "...", "report": "...", ...}

{
  "status": "completed",
  "summary": "Brief summary of key findings",
  "topic": "your research topic",
  "report": "Full multi-source research report (1000-3000 words)...",
  "sources": [
    {
      "title": "Source Title",
      "url": "https://example.com",
      "content": "Relevant excerpt..."
    }
  ],
  "research_time": 45.2
}

© initializ, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts) in forge-skills/local/embedded/tavily-research of initializ/forge.

• SKILL.md
• scripts/tavily-research-poll.sh
• scripts/tavily-research.sh

Open the folder on GitHubat commit 3c608d8