tavily-search

Web search via Tavily API (alternative to Brave). Use when the user asks to search the web / look up sources / find links and Brave web_search is unavailable or undesired. Returns a small set of relevant results (title, url, snippet) and can optionally include short answer summaries.

Quality

78%

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 ./configs/microservice/bff-service/configs/agent-skills/clawhub/openclaw-tavily-search/SKILL.md

Quality

Content

100%

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

The body is an efficient, fully actionable reference: executable commands, complete option/depth tables, and well-organized sections backed by a real script. As a simple single-purpose skill it meets the top anchor on every dimension with no concept padding or organizational debt.

Dimension	Reasoning	Score
Conciseness	The body is lean — Quick Start, an Options table, a Search Depth table, and Tips — with no explanation of concepts Claude already knows (what web search or Node is); every section is actionable reference material, matching 'lean and efficient; assumes Claude's competence'.	3 / 3
Actionability	Commands are fully executable and copy-paste ready (e.g. `node {baseDir}/scripts/search.mjs "query" --deep`), and the Options table gives every flag with defaults and valid values, matching 'fully executable code/commands; specific examples; copy-paste ready'.	3 / 3
Workflow Clarity	This is a simple single-purpose skill (one CLI invocation) whose single action is unambiguous, so per the simple-skills note workflow_clarity scores 3; there are no destructive or batch operations that would require validation checkpoints.	3 / 3
Progressive Disclosure	The skill is under 50 lines with one real bundle file (scripts/search.mjs, referenced via {baseDir}/scripts/search.mjs) and no nested references, organized into clearly labeled sections, matching the under-50-lines note that well-organized sections alone warrant a 3.	3 / 3
	Total	12 / 12 Passed

Description

57%

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 is clear and reasonably specific about what the skill does and which service it uses, but it lacks an explicit 'Use when...' trigger clause and offers only a thin set of natural keywords. Adding trigger guidance and more user-natural terms would raise it across completeness and trigger_term_quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to search the web, look something up online, or find recent information/news.'

Broaden natural trigger terms to include variations users actually say, such as 'look up', 'find information online', 'research', or 'news search'.

Enumerate a second distinct capability (e.g. domain-filtered or news/topic search) to move specificity from a single described action to multiple concrete actions.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Web search using Tavily's LLM-optimized API") and concrete outputs ("content snippets, scores, and metadata"), but these are facets of a single capability rather than multiple distinct actions like extract/fill/merge, so it matches the 'names domain and some actions, not comprehensive' anchor rather than the level above.	2 / 3
Completeness	It clearly answers 'what' (web search via Tavily returning snippets/scores/metadata) but has no 'Use when...' clause or equivalent trigger guidance; per the rubric guidelines a missing explicit trigger caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	"Web search" and "search" are natural terms a user would say, but coverage is thin — no common variations like "look up", "find information online", or "research" — matching 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	Naming "Tavily's LLM-optimized API" gives the skill a clear, specific niche unlikely to trigger for unrelated skills, matching the 'clear niche with distinct triggers' anchor; it is not the level below because the mechanism is explicitly scoped rather than generic.	3 / 3
	Total	9 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: UnicomAI/wanwu
Path: configs/microservice/bff-service/configs/agent-skills/clawhub/openclaw-tavily-search/SKILL.md
Commit: f618458

Reviewed: about 14 hours 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.