Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Perplexity AI Search — measured AI agent skill | DecimalAI

vibeeval/perplexity-search

SkillScore78Maintained

AI-powered web search, research, and reasoning via Perplexity

by vibeeval

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Research pack

decimalai skills pull vibeeval-perplexity-search

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/vibeeval-perplexity-search/SKILL.md

Raw file: /s/vibeeval-perplexity-search/SKILL.md ↗ · machine-readable summary at /s/vibeeval-perplexity-search.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 6d ago

—+4% tokens0% turns78% of whole cases pass with skill (18/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	251%	0%
case-04	✗→✓	▲ Improved	178%	0%
case-05	✗→✓	▲ Improved	402%	0%
case-06	✗→✓	▲ Improved	200%	0%
case-07	✗→✓	▲ Improved	21%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

vibeeval / vibecosystem

skills/perplexity-search/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Perplexity AI Search

Web search with AI-powered answers, deep research, and chain-of-thought reasoning.

When to Use

Direct web search for ranked results (no AI synthesis)
AI-synthesized research with citations
Chain-of-thought reasoning for complex decisions
Deep comprehensive research on topics

Models (2025)

| Model | Purpose | |-------|---------| | sonar | Lightweight search with grounding | | sonar-pro | Advanced search for complex queries | | sonar-reasoning-pro | Chain of thought reasoning | | sonar-deep-research | Expert-level exhaustive research |

Usage

Quick question (AI answer)

bash
uv run python scripts/mcp/perplexity_search.py \
    --ask "What is the latest version of Python?"

Direct web search (ranked results, no AI)

bash
uv run python scripts/mcp/perplexity_search.py \
    --search "SQLite graph database patterns" \
    --max-results 5 \
    --recency week

AI-synthesized research

bash
uv run python scripts/mcp/perplexity_search.py \
    --research "compare FastAPI vs Django for microservices"

Chain-of-thought reasoning

bash
uv run python scripts/mcp/perplexity_search.py \
    --reason "should I use Neo4j or SQLite for small graph under 10k nodes?"

Deep comprehensive research

bash
uv run python scripts/mcp/perplexity_search.py \
    --deep "state of AI agent observability 2025"

Parameters

| Parameter | Description | |-----------|-------------| | --ask | Quick question with AI answer (sonar) | | --search | Direct web search - ranked results without AI synthesis | | --research | AI-synthesized research (sonar-pro) | | --reason | Chain-of-thought reasoning (sonar-reasoning-pro) | | --deep | Deep comprehensive research (sonar-deep-research) |

Search-specific options

| Parameter | Description | |-----------|-------------| | --max-results N | Number of results (1-20, default: 10) | | --recency | Filter: day, week, month, year | | --domains | Limit to specific domains |

Mode Selection Guide

| Need | Use | Why | |------|-----|-----| | Quick fact | --ask | Fast, lightweight | | Find sources | --search | Raw results, no AI overhead | | Synthesized answer | --research | AI combines multiple sources | | Complex decision | --reason | Chain-of-thought analysis | | Comprehensive report | --deep | Exhaustive multi-source research |

Examples

bash
# Find recent sources on a topic
uv run python scripts/mcp/perplexity_search.py \
    --search "OpenTelemetry AI agent tracing" \
    --recency month --max-results 5

# Get AI synthesis
uv run python scripts/mcp/perplexity_search.py \
    --research "best practices for AI agent logging 2025"

# Make a decision
uv run python scripts/mcp/perplexity_search.py \
    --reason "microservices vs monolith for startup MVP"

# Deep dive
uv run python scripts/mcp/perplexity_search.py \
    --deep "comprehensive guide to building feedback loops for autonomous agents"

API Key Required

Requires PERPLEXITY_API_KEY in environment or ~/.claude/.env.

Want to see if vibeeval/perplexity-search would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.