Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Use Perplexity API for web-grounded AI search. Use when user needs up-to-date information with source citations, factual queries about current events, or research-style answers. Default when user mentions Perplexity or needs current information with references.
Use Perplexity API for web-grounded AI search. Use when user needs up-to-date information with source citations, factual queries about current events, or research-style answers. Default when user mentions Perplexity or needs current information with references.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
This skill provides access to the Perplexity API for web-grounded AI search. It combines large language models with real-time web search, providing accurate, up-to-date answers with source citations. This is a security-hardened version that fixes command injection vulnerabilities found in the original perplexity-bash skill.
Use Perplexity when: You need current information (news, prices, events, recent developments) The user asks for source citations or references The user specifically mentions Perplexity or wants research-style answers Use built-in web search when: Simple factual queries Quick information lookup Basic URL or content retrieval
ModelUse CaseCostsonarDefault search, most queriesLowsonar-proAdvanced search, deeper understandingMediumsonar-reasoningComplex multi-step reasoningMediumsonar-reasoning-proAdvanced reasoning with deep contentHigh
# Simple query (uses sonar by default) scripts/perplexity_search.sh "What is the capital of Germany?" # With a different model scripts/perplexity_search.sh -m sonar-pro "Latest AI developments" # Markdown format with citations scripts/perplexity_search.sh -f markdown "Tesla stock analysis"
# High context for comprehensive results scripts/perplexity_search.sh -m sonar-reasoning -c high -f markdown \ "Compare AI models performance benchmarks" # With custom system prompt scripts/perplexity_search.sh -s "You are a technology analyst." \ "Analyze current tech trends"
FlagDescriptionDefault-m, --modelModel to usesonar-t, --max-tokensMaximum tokens (1-4096)4096--temperatureSampling temperature (0.0-1.0)0.0-c, --contextSearch context: low/medium/highmedium-s, --systemSystem prompt(none)-f, --formatOutput: text/markdown/jsontext--list-modelsList available models
low - Faster, fewer sources. Good for simple queries. medium (default) - Balanced for most use cases. high - Most comprehensive. Best for research.
Option 1: Config file (recommended) Create config.json in the skill directory: { "apiKey": "pplx-your-key-here" } Option 2: Environment variable export PERPLEXITY_API_KEY="your-key-here" Priority: Config file > environment variable.
bash (4.0+) curl python3 (for JSON construction only - no user input is eval'd)
This version addresses the following vulnerabilities found in the original: No command injection - User input is passed to Python via environment variables, never interpolated into code strings Input validation - All parameters are validated (numeric ranges, allowed model names, allowed context values) API key protection - The Authorization header is passed to curl via a temporary config file (curl -K, mode 600) and the request body via stdin (--data @-), so neither the API key nor the body appear in process listings (ps aux) Query length limit - Queries are capped at 8000 characters to prevent denial-of-wallet attacks Strict model allowlist - Only known valid models are accepted
Perplexity API is not free. Be mindful of usage: Simple queries: ~$0.005-$0.015 per query Deep research: ~$0.015-$0.03+ per query Default to sonar for most queries to keep costs low.
Error: No API key found - Set up API key as described above Error: curl not found - Install curl for your system Error: Invalid model - Use --list-models to see available models
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.