Skip to skills
AI Craft Pad
Home/Skills/Productivity & planning/tavily-research
First-party source

Tavily Research

A Tavily hosted-research workflow for multi-source synthesis with retained citations.

Editorial review checked 2026-10-29 against this instruction snapshot. Supporting scripts and runtime behavior remain outside this editorial review.

What it does

The source describes a longer research operation with model selection, streaming, structured output and saved reports. It positions this after simpler retrieval options when the task needs synthesis rather than a quick fact. The resulting report is an input to review, not a substitute for reviewing evidence.

Best for

A bounded comparison or background investigation where multiple sources and a traceable written synthesis are useful.

Tradeoffs and requirements

This operation requires authentication and hosted processing may incur costs. A report with citations can still misstate what sources say or omit relevant counterevidence. Sensitive questions or documents need an explicit decision before sending them to an external service.

Unknown; inspect source requirements and supporting scripts.

Install from the source

Inspect the pinned source snapshot and its supporting files first. The command selects this skill through the open-source skills CLI. Node.js and agent-specific setup may be required. Installation can download code. Catalog ingestion never executes skill instructions or install scripts.

npx skills add https://github.com/tavily-ai/skills/tree/778122e5f9c680f541eeceda5a5b36405eb7980c/skills/tavily-research --skill tavily-research

Review pinned skill folder ↗ · CLI documentation ↗

After source review, use npx skills check and npx skills update to inspect and apply upstream updates. Re-check changed instructions before running them.

Safety & review signals

Static review only. This is not a security audit or a guarantee of safety.

SKILL.md text only; scripts, dependencies and runtime behavior not audited.

  • Shell Or Package Install — review the source context.

Allowed tools declaration: Bash(tvly *). Runtime permissions and network behavior: Unknown.

AI Craft Pad Skill Score

85/100 · Metadata coverage 100% · Model 1.0

Scores summarize observable discovery signals. Popularity and repository activity apply to the whole repository. Unknown runtime safety earns no certification.

Documentation
100/100
100
Maintenance
100/100
100
License Clarity
100/100
100
Repository Health
100/100
100
Compatibility Evidence
80/100
80
Popularity
48/100
48
Originality
80/100
80
Static Safety
60/100
60
Read the formula and limits →

Suggested workflow

Define the question, required evidence and output shape, then choose a suitable research scope. Preserve the returned report and citations so that conclusions can be checked independently.

How to judge the result

Open the most consequential cited sources, compare their claims and dates, and flag unresolved disagreements. Verify structured output against its schema and distinguish source-supported conclusions from synthesis or inference introduced by the research service.

Similar skills to compare

Related by category; compare scope and dependencies before choosing an alternative.

Productivity & planning88/100

dispatching parallel agents

obra/superpowers

Explore dispatching parallel agents as a productivity & planning workflow from obra/superpowers. Compare its source, maintenance and review signals before choosing it for your agent.

Community sourceMIT
308,765 repo stars0 text flagsReview ↗
Productivity & planning88/100

executing plans

obra/superpowers

Explore executing plans as a productivity & planning workflow from obra/superpowers. Compare its source, maintenance and review signals before choosing it for your agent.

Community sourceMIT
308,765 repo stars0 text flagsReview ↗
Productivity & planning88/100

finishing a development branch

obra/superpowers

Explore finishing a development branch as a productivity & planning workflow from obra/superpowers. Compare its source, maintenance and review signals before choosing it for your agent.

Community sourceMIT
308,765 repo stars1 text flagReview ↗

More from this source

Development85/100

tavily best practices

tavily-ai/skills

A Tavily SDK integration guide that separates search, extraction, discovery, crawling and research.

First-party sourceMITEditorial review
491 repo stars2 text flagsReview ↗
Automation & agents85/100

tavily crawl

tavily-ai/skills

A bounded Tavily crawling workflow for collecting several pages from a defined website section.

First-party sourceMITEditorial review
491 repo stars2 text flagsReview ↗
Automation & agents85/100

tavily dynamic search

tavily-ai/skills

A Tavily workflow for filtering large retrieval payloads before they enter an agent’s working context.

First-party sourceMITEditorial review
491 repo stars2 text flagsReview ↗