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.

65

Quality

80%

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 ./backend/cli/skills/research/perplexity-search/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 concrete, executable examples and a validated setup workflow, weakened by notable redundancy across the models/cost/best-practices sections and a recap summary that inflate token cost. Reference structure is sound but underused.

Suggestions

Collapse the duplicated model-selection, cost, and query-design guidance: keep one canonical section and have 'Best Practices' and 'Summary' point to it rather than restating it.

Remove or drastically shorten the 'Summary' section — it recapitulates points already made and adds no new guidance.

Move the inlined model comparison and troubleshooting detail into the existing references (model_comparison.md, openrouter_setup.md) and link out, keeping SKILL.md a lean overview.

DimensionReasoningScore

Conciseness

Noticeably verbose with substantial redundancy: model selection recurs in 'Available Models', 'Cost Management', and 'Best Practices'; query design recurs in 'Crafting Effective Queries' and 'Best Practices'; a recap 'Summary' section restates earlier points, adding padding without new information.

2 / 5

Actionability

Fully executable throughout — copy-paste bash commands, a runnable Python module example, and concrete CLI flags covering common cases from simple search to batch processing.

5 / 5

Workflow Clarity

The setup workflow is clearly numbered with an explicit validation checkpoint ('Verify setup' via --check-setup), but the optional batch-processing example lacks per-result validation, a minor gap.

4 / 5

Progressive Disclosure

Good structure with well-signaled one-level-deep references (openrouter_setup.md, model_comparison.md, search_strategies.md — all real files), though model/troubleshooting detail is inlined despite dedicated reference files, a minor organization gap.

4 / 5

Total

15

/

20

Passed

Description

92%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 clearly answers both 'what' and 'when' with concrete trigger phrases and specific capability detail. Minor room to add a few more colloquial trigger synonyms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Perform AI-powered web searches', 'finding recent scientific literature', 'getting grounded answers with source citations', 'accessing information beyond the model knowledge cutoff' — with comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly states what it does ('Perform AI-powered web searches... via LiteLLM and OpenRouter') and when to use it ('This skill should be used when conducting web searches for current information...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural keyword coverage ('web searches', 'current information', 'scientific literature', 'source citations') but misses a few common variations users might say like 'search the web' or 'latest research'.

4 / 5

Distinctiveness Conflict Risk

Clear niche — Perplexity models via LiteLLM/OpenRouter with a single API key — with distinct triggers and minimal overlap risk against other skills.

5 / 5

Total

19

/

20

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
synthetic-sciences/openscience
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.