AB tavily-search-native-node
Minimal Tavily web search for OpenClaw - native Node.js, zero dependencies, small audit surface. Use when the user asks to search the web, look up current information, find news, research a topic, check recent events, compare options, or get current or recent web information. Returns Tavily's synthesized answer plus source URLs/snippets for verification. Requires TAVILY_API_KEY in the process environment. NOT for scraping individual URLs; use the platform URL-fetch/read tool when available. For caching, raw content, extract endpoint, and usage stats, use a separately reviewed Pro Tavily skill/package when available.
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
low Secrets in code
secret-high-entropy-tokentests.mjs:104High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)const sentinel = 'tavi…345';
fixturequoted -
low Secrets in code
secret-high-entropy-tokentests.mjs:113High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)const sentinel = 'tavi…890';
fixturequoted
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "risk_class"
Process rating: all ten parameters 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 12 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4192 tokens
- 100Steps. 74 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 623: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 74 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.