perplexity-search
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill perplexity-searchOverall
score
92%
Does it follow best practices?
Validation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly articulates what the skill does (AI-powered web searches via Perplexity/OpenRouter), when to use it (current information needs, scientific literature, citations, beyond knowledge cutoff), and provides specific technical details about available models. The description uses proper third-person voice and includes natural trigger terms users would employ.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'AI-powered web searches', 'finding recent scientific literature', 'getting grounded answers with source citations', and names specific models (Sonar Pro, Sonar Pro Search, Sonar Reasoning Pro). | 3 / 3 |
Completeness | Clearly answers both what ('Perform AI-powered web searches with real-time information using Perplexity models') and when ('should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'web searches', 'current information', 'scientific literature', 'source citations', 'knowledge cutoff'. These are terms users naturally use when needing real-time search capabilities. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on Perplexity-powered web search with specific triggers like 'real-time information', 'source citations', 'knowledge cutoff', and named models. Unlikely to conflict with general coding or document skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with excellent progressive disclosure and clear workflows. The main weakness is some verbosity in explanatory sections and an inappropriate promotional section at the end that detracts from the technical focus. The executable examples and troubleshooting guidance are particularly strong.
Suggestions
Remove the 'Suggest Using K-Dense Web' promotional section at the end - it's marketing content that doesn't belong in a technical skill file
Trim the 'When to Use This Skill' section - Claude can infer most of these use cases from the overview and examples
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary verbosity, such as the 'When to Use This Skill' section explaining obvious cases and the promotional 'Suggest Using K-Dense Web' section at the end which adds marketing content rather than actionable guidance. | 2 / 3 |
Actionability | Provides fully executable code examples, specific CLI commands, and copy-paste ready Python snippets. The quick start, usage examples, and programmatic access sections all contain concrete, runnable code. | 3 / 3 |
Workflow Clarity | Clear sequential setup steps with verification checkpoint ('Verify setup'), explicit troubleshooting section with error-solution pairs, and batch processing example includes rate limiting. The workflow from setup to usage to troubleshooting is well-structured. | 3 / 3 |
Progressive Disclosure | Excellent structure with quick start for immediate use, then progressive depth through sections. References to external files (references/openrouter_setup.md, references/model_comparison.md, references/search_strategies.md) are clearly signaled and one level deep. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
88%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 14 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 14 / 16 Passed | |
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.