Tavily research

Skill libenxier-beep/codex-custom-skills/skills/tavily-research

Use when the user needs a cited, multi-source web research report and ordinary targeted browsing is insufficient—for example, a deep comparison, market analysis, literature review, or broad investigation. Requires an authenticated Tavily CLI.From its SKILL.md

Install

npx -y skills add libenxier-beep/codex-custom-skills --skill tavily-research

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.9 KB, 377 tokens by cl100k_base, as published. Nobody here has run it

Tavily Research

Use Tavily's deep-research command for synthesis-heavy web work. For a quick fact, a small number of current claims, or a known page, use the normal web tools instead.

Preflight

Run command -v tvly.
Run tvly --status to confirm the CLI and authentication state.
If the CLI or authentication is missing, report the dependency and ask before installing software or changing credentials. Never run a remote install script automatically.

Run Research

Choose the lightest model that fits:

mini: a focused single-topic investigation
pro: a broad, multi-angle comparison or report
auto: let Tavily select based on complexity

tvly research run "competitive landscape of AI code assistants" --model mini
tvly research run "compare three approaches to durable agent memory" --model pro --json
tvly research run "fintech market trends" --stream

Use --output-schema PATH when the user needs structured fields, and -o PATH only when they requested a saved artifact or repository conventions require one.

For a long-running job:

tvly research run "topic" --no-wait --json
tvly research status REQUEST_ID --json
tvly research poll REQUEST_ID --json

Deliverable

Answer the user's question directly; do not dump raw CLI output.
Preserve source links and place citations next to the claims they support.
Separate source-backed facts from inference.
Note meaningful gaps, disagreement, or recency limitations.
Do not overstate confidence when the returned sources are weak or incomplete.

This skill is adapted from Tavily's open-source skill collection. See LICENSE.txt for its MIT license notice.

What ships with it: 2 files

1.3 KB alongside SKILL.md

agents/

openai.yaml210 B

LICENSE.txt1.1 KB

Gives 0 of the 12 instructions most research analysis skills give in 377 tokens

Counted across 1,063 of the 1,754 authors here whose files we hold, read 2026-08-07

Generate a markdown reportin 32 of 1063, across 23 files
Cite each claim's sourcein 30 of 1063, across 15 files
Define the ideal customer profilein 20 of 1063, across 2 files
Search for companies matching the criteriain 20 of 1063, across 2 files
Assign a fit score from one to tenin 20 of 1063, across 2 files
Analyze the codebase to understand the productin 19 of 1063, across 1 file
Ask clarifying questions about the value propositionin 19 of 1063, across 1 file
Look for signals of immediate needin 19 of 1063, across 1 file
Identify the target decision maker rolein 19 of 1063, across 1 file
Suggest a personalized contact strategyin 19 of 1063, across 1 file
Provide conversation starters for outreachin 19 of 1063, across 1 file
Format results in a scannable markdown templatein 19 of 1063, across 1 file

Said here and by no other author read

run command -v tvly
report the dependency if authentication is missing
ask before installing software or changing credentials
choose the lightest model that fits
use --output-schema PATH for structured fields
use -o PATH only when a saved artifact is requested

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.