Tavily Research

What it does

The current instruction is a research process rather than a hosted-report API recipe. It divides a question into non-overlapping subtopics, carries scope limits into each and fills evidence gaps before writing. It describes both a delegated workflow and a single-agent path, and asks later research to build on an existing report rather than repeating it.

Best for

Comparisons and investigations that need several kinds of evidence weighed together instead of one factual lookup.

Tradeoffs and requirements

Its source-suggested delegation and file layout do not override host rules or authorize additional agents. Retrieval still depends on the available tools and service access, and an apparently well-cited synthesis can misread sources. The companion researcher and writer references are outside this main-file assessment.

Unknown; inspect source requirements and supporting scripts.

Install from the source

First time installing a skill? Follow the walkthrough →

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/00a131a8033e565829a21f49745925801213ea97/skills/tasks/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.

No configured text patterns matched. Unmatched or concealed behavior can still exist.

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

Suggested workflow

Define the question, boundaries and useful output. Split distinct evidence needs, inspect authoritative pages for each and reconcile contradictions before writing. Select a delegated path only when permitted; otherwise keep the work in the existing agent and use the allowed tools.

How to judge the result

Check consequential citations against their actual claims and dates. Explain which conclusions follow directly from sources and which are inferences, keep unresolved gaps visible and avoid presenting a polished narrative as proof that every relevant alternative was investigated.