CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

64

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/literature/perplexity-search/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The content is highly actionable with concrete commands and examples, but it is verbose with redundant sections and references bundle files that are absent. Workflow validation checkpoints are largely missing.

Suggestions

Collapse the 'Best Practices' section into the existing 'Crafting Effective Queries', 'Available Models', and 'Cost Management' sections to remove redundancy and reduce tokens.

Add explicit validation/feedback steps to the batch-processing workflow (e.g. check each result's success flag and retry failures) to satisfy the workflow-clarity checkpoint requirement.

Create the referenced scripts/ and references/ files (perplexity_search.py, setup_env.py, search_strategies.md, model_comparison.md, openrouter_setup.md, assets/.env.example) so progressive-disclosure references resolve to real files.

DimensionReasoningScore

Conciseness

The body is highly detailed and largely on-task, but it is very long with redundant sections (e.g. 'Best Practices' repeats 'Crafting Effective Queries', 'Available Models', and 'Cost Management') and explains concepts Claude already knows, making it mostly efficient but padded.

2 / 3

Actionability

Provides copy-paste-ready CLI commands, a concrete Python module import example, and specific flags (--model, --output, --verbose, --check-setup), fully meeting the executable-guidance anchor.

3 / 3

Workflow Clarity

Setup steps are sequenced, but the batch-processing and search workflows lack explicit validation/checkpoint steps, and results handling has no verify-then-act feedback loop, leaving validation gaps.

2 / 3

Progressive Disclosure

References to scripts/ and references/ files are clearly signaled and one level deep, but those bundle directories do not actually exist, so the disclosure structure is not backed by real files and the body itself is oversized.

2 / 3

Total

9

/

12

Passed

Description

92%

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

The description is specific, trigger-rich, and explicitly covers both what the skill does and when to use it. It is slightly verbose and risks minor overlap with generic web-search skills.

Suggestions

Tighten the description to reduce verbosity; the model list and 'single OpenRouter API key' detail could move to the body to keep the description concise.

Add a more distinctive trigger phrase to separate it from generic web-search skills, e.g. emphasize 'Perplexity-sourced real-time web answers with citations'.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and capabilities such as 'web searches for current information,' 'finding recent scientific literature,' 'getting grounded answers with source citations,' and 'accessing information beyond the model knowledge cutoff,' matching the multiple-concrete-actions anchor.

3 / 3

Completeness

Explicitly states both what the skill does ('Perform AI-powered web searches...') and when to use it ('This skill should be used when conducting web searches for current information...'), satisfying the explicit what-and-when anchor above the 2 cap.

3 / 3

Trigger Term Quality

Covers natural user phrases a person would actually say ('web searches,' 'current information,' 'scientific literature,' 'source citations,' 'beyond the model knowledge cutoff'), giving good coverage of natural trigger terms.

3 / 3

Distinctiveness Conflict Risk

The web-search niche is reasonably distinct, but 'web searches for current information' could overlap with general search/web skills, so it is somewhat specific rather than a clearly conflict-free niche.

2 / 3

Total

11

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 24 missing

Warning

Total

14

/

16

Passed

Repository
wu-yc/LabClaw
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.