Name: tavily
Rating: 57.599999999999994 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

tavily

Tavily integration. Manage data, records, and automate workflows. Use when the user wants to interact with Tavily data.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/tavily/SKILL.md

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete executable membrane commands and a clear connection state machine, but it does not use progressive disclosure — no reference files exist and detail (proxy options, clientAction schema) is inlined. The connection workflow includes validation checkpoints via state polling, though re-auth loops are only lightly covered.

Suggestions

Move the proxy request flag table and the clientAction schema details into a dedicated reference file (e.g. references/proxy.md) and link to it from SKILL.md to improve progressive disclosure.

Add an explicit re-auth feedback loop (poll CLIENT_ACTION_REQUIRED -> prompt user -> re-poll until READY) to make the connection workflow fully checkpointed.

Trim the opening 'Tavily is an AI-powered search engine...' overview paragraph, which explains a concept Claude already knows.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete CLI commands and a flag table; only minor over-explanation such as the introductory 'Tavily is an AI-powered search engine...' paragraph that Claude already knows.	4 / 5
Actionability	Fully executable copy-paste membrane commands for install, login, connection, action listing/running, and proxy requests, plus a complete options table covering the common cases.	5 / 5
Workflow Clarity	The connection flow has a clear sequence with explicit state checks (READY, CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR) and a polling loop; the --wait retry is present, though there is no explicit re-auth feedback loop for CLIENT_ACTION_REQUIRED beyond 'poll again'.	4 / 5
Progressive Disclosure	There is reasonable section structure but no external reference files exist; all content (including the full proxy flag table and clientAction schema details) is inlined in SKILL.md rather than split into one-level-deep references.	3 / 5
	Total	16 / 20 Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description correctly identifies the Tavily niche and includes an explicit Use-when trigger, but the listed actions ('Manage data, records, automate workflows') are generic rather than reflecting Tavily's actual capabilities (search, articles, research). It is third-person and clear, but the action vocabulary is padded fluff over a specific tool.

Suggestions

Replace the generic 'Manage data, records, and automate workflows' with Tavily-specific actions such as 'Search the web, retrieve articles, and synthesize research results'.

Expand the Use-when clause with concrete natural triggers, e.g. 'Use when the user asks to search the web, research a topic, or retrieve articles via Tavily'.

Trim the generic 'automate workflows' phrasing, which does not reflect what Tavily actually does and reads as buzzword padding.

Dimension	Reasoning	Score
Specificity	It names the Tavily domain and the actions 'Manage data, records, and automate workflows', but these actions are generic and not Tavily-specific (search, articles) — minimal concrete actions.	2 / 5
Completeness	It states the what ('Manage data, records, and automate workflows') and an explicit when clause ('Use when the user wants to interact with Tavily data'), but the when is somewhat generic rather than listing concrete trigger phrases.	4 / 5
Trigger Term Quality	'Tavily data' and 'interact with Tavily data' are relevant keywords but it misses common natural phrasings like 'search the web', 'research', 'articles' or synonyms users would actually say.	3 / 5
Distinctiveness Conflict Risk	'Tavily integration' names a clear niche with distinct triggers tied to a specific product, leaving only minor overlap risk with other data/search skills.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/tavily/SKILL.md
Commit: f484c82

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.