browse-research — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited browse-research (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use this skill when the user needs researched, cited answers backed by real web sources — not LLM hallucinations.
Install LastSearch MCP server:
{
"mcpServers": {
"lastsearch": {
"command": "npx",
"args": ["-y", "lastsearch"]
}
}
}Or set LASTSEARCH_API_KEY=ls_xxx for full features (sessions, sharing, knowledge export).
Use answer to get a cited, evidence-backed answer:
answer({ query: "How do mRNA vaccines work?", depth: "fast" })Use depth: "thorough" when:
The response contains:
When presenting results:
claims[].sources| Range | Meaning |
|---|---|
| 80-100% | Strong evidence, multiple corroborating sources |
| 60-79% | Good evidence, some gaps |
| 40-59% | Mixed evidence, contradictions possible |
| 0-39% | Weak evidence, few or low-quality sources |
User: "Is intermittent fasting effective for weight loss?"
answer({
query: "Is intermittent fasting effective for weight loss? What does the research say?",
depth: "thorough"
})Present the answer with inline citations, highlight any contradictions between studies, and note the confidence score.
Use clarity to get answers with reduced hallucinations — two modes:
Fast (no internet) — LLM-only answer with anti-hallucination grounding techniques:
clarity({ prompt: "Explain the causes of the 2008 financial crisis" })Verified (with internet) — LLM answer + web pipeline, fused into one answer with source-backed claims:
clarity({ prompt: "Explain the causes of the 2008 financial crisis", verify: true })The response includes: answer, claims[] (each with origin: "llm", "source", or "confirmed"), confidence, techniques, risks, and verified (whether web sources were consulted).
Use fast mode when speed matters. Use verified mode when accuracy matters.
search first if you just need URLs, not a full researched answerbrowse_harden before generating content to reduce hallucinations in the output~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.