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.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/perplexity-search/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable content with executable examples, a verified setup workflow, and clean one-level-deep references. The main weakness is verbosity from redundant sections that restate earlier guidance, plus a missing referenced asset file.

Suggestions

Remove or merge the "Best Practices" and "Summary" sections, which largely restate "Crafting Effective Queries", "Available Models", and "Cost Management"; this would tighten conciseness from 3 toward 4-5.

Add per-query error handling and retry to the batch-processing example (e.g., check the exit/JSON success flag and log failures) so the batch workflow has an explicit feedback loop.

Either create the referenced assets/.env.example file or remove the "assets/.env.example: Example environment file template" line from the Resources section so referenced bundle paths all resolve.

Dimension	Reasoning	Score
Conciseness	Mostly efficient actionable content, but several sections are padded: "Best Practices" restates "Crafting Effective Queries", "Available Models", and "Cost Management", and the closing "Summary" re-narrates the whole skill.	3 / 5
Actionability	Fully executable, copy-paste-ready bash and Python examples cover the common cases (simple search, --output, --model, --verbose, programmatic module use, batch loops).	5 / 5
Workflow Clarity	Setup is a clear numbered sequence with a validation checkpoint ("python scripts/perplexity_search.py --check-setup") and a troubleshooting section; minor gap is the batch example, which has no per-query error handling or retry.	4 / 5
Progressive Disclosure	Good structure with well-signaled, one-level-deep references to real files (references/openrouter_setup.md, model_comparison.md, search_strategies.md); minor gap is that the referenced assets/.env.example does not exist in the bundle.	4 / 5
	Total	16 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states concrete capabilities and gives an explicit "should be used when" trigger clause with multiple concrete triggers. It is well differentiated by the Perplexity/OpenRouter specifics but could add a few more natural synonyms and slightly more diverse action verbs.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("Perform AI-powered web searches", "finding recent scientific literature, getting grounded answers with source citations", "Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search… and Sonar Reasoning Pro") with minor gaps rather than the fully comprehensive, diverse action set of a 5.	4 / 5
Completeness	Explicitly answers both what ("Perform AI-powered web searches…using Perplexity models via LiteLLM and OpenRouter") and when ("This skill should be used when conducting web searches…finding recent scientific literature…") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage ("web searches for current information", "recent scientific literature", "source citations", "beyond the model knowledge cutoff"), but a few common synonyms users might say ("research", "look up", "real-time") are missing.	4 / 5
Distinctiveness Conflict Risk	Clear Perplexity-via-OpenRouter niche with named models and a single-API-key differentiator gives mostly distinct triggers; minor overlap risk remains with a generic "web search" skill.	4 / 5
	Total	17 / 20 Passed

Validation

87%

Warnings & errors only

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
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/perplexity-search/SKILL.md
Commit: d5ae560

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.