perplexity-cli-models

Model selection guide for perplexity-cli ask and chat commands. Use when choosing between sonar, sonar-pro, sonar-reasoning, and sonar-deep-research.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

87%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.

A tight, highly actionable single-file skill with executable examples and a clear decision flowchart. Its one weakness is the batch agent-usage section, which lacks the validation/feedback loop the rubric requires for batch operations.

Suggestions

Add a validation/checkpoint step to the 'Cost-Aware Agent Usage' batch loop (e.g. check exit status or parse error before synthesizing with sonar-pro) to raise workflow clarity.

Show how to verify a query actually used the intended model (e.g. inspecting the returned JSON's model field) so batch runs are auditable.

Note expected failure handling (rate limits, empty content) in the loop so Claude can recover rather than feed bad data into the synthesis step.

Dimension	Reasoning	Score
Conciseness	The body is lean — a comparison table, bullet lists, and executable commands — with no padding explaining what perplexity-cli or Sonar models are; every section earns its place.	5 / 5
Actionability	Each model section ships copy-paste-ready commands with the correct --model (and --reasoning/--mode) flags, covering the common cases per model.	5 / 5
Workflow Clarity	A clear decision flowchart sequences model choice, but the 'Cost-Aware Agent Usage' batch loop has no validation checkpoint or feedback loop, which caps batch-operation workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	The skill is self-contained with no bundle files and is organized into well-labeled sections (comparison, when-to-use, reasoning, flowchart, cost-aware), making navigation easy within a single file.	5 / 5
	Total	18 / 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 concise, well-targeted description that states both the capability and an explicit trigger clause with concrete model names. Only minor keyword-synonym coverage is missing.

Dimension	Reasoning	Score
Specificity	Names the domain and lists all four concrete model choices (sonar, sonar-pro, sonar-reasoning, sonar-deep-research) plus the ask/chat commands, giving comprehensive coverage of the selection action.	5 / 5
Completeness	It explicitly answers both what ('Model selection guide for perplexity-cli ask and chat commands') and when ('Use when choosing between...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	The 'Use when choosing between...' clause surfaces the specific model names a user would say, but broader natural phrasings (e.g. 'which model', 'fast vs cheap', 'research query') are absent.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche tied to perplexity-cli and the specific Sonar model names, so it is unlikely to trigger for an unrelated skill.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: slurpyb/perplexity-cli
Path: .claude/skills/web-search-with-perplexity/models/SKILL.md
Commit: 5624eaa

Reviewed: 2 days 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.