SKILLEMALL.ai

AB tavily-search-pro-native-node

Research-grade Tavily web search for OpenClaw using native Node.js with zero dependencies. Use for deep web research, multi-URL content extraction, estimated Tavily credit tracking, response caching, usage-log review, and 429 backoff. Includes search, extract, stats, and cache subcommands. Requires TAVILY_API_KEY in the process environment. For minimal search-only use, prefer tavily-search-native-node.

ClawHub Agent Skills author: Jeremy Westburg v1.0.36 MIT-0 5 files body ≈ 4 162 tokens Open the sourceclawhub.ai analyzed 4 d ago

As a process B 66/100 · Nearly there — weak spots: running it twice

AnalyzerInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
A
99/100
safety, quality, tests
Safety 60%
100
Quality 40%
97
Run on models
none yet
Process rating
B
66/100
Nearly there
Running it twice w 4
30
When it triggers w 12
50
Failures and branches w 10
50
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • 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 · 0

    ✓ No critical or high findings

    Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "risk_class"

    Process rating: all ten parameters 66/100

    • 30Running it twice. 12 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 70Execution cost. Instruction body is 4162 tokens
    • 85Steps. 88 steps, 1 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 10 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
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 405: enough signal without eating the budget
    • +4Structure: 11 headings
    • +3Step-by-step instructions: 88 items
    • +3Output format is stated explicitly
    • +4Has examples (2 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)
    • +3All 2 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.

    External checks

    ClawHub: clean
    This skill is a disclosed Tavily web research helper with expected external API use, local caching, and local usage logging.
    LLM: benign (high) · VirusTotal: · 11 Sept 2026